Scale yourself

One of the things I wish people would consider more often when thinking about AI is how they can use it to scale themselves. What are some time-consuming things that they currently have to do themselves that AI could do for them to streamline their output and increase their productivity? Productivity for giving them more time to do the things only they can do, the things they want to do, or the things they love to do. (And to help stop procrastinating on things they have to do.)

I have a habit of trying to scale myself. These days, it’s often related to EPI (exocrine pancreatic insufficiency, which some areas of the world know by the acronym PEI). I developed a strong knowledge base first from personal experience, then by doing research – including a systematic review where I read hundreds, plural, of research papers on key topics related to design protocols and guidelines. As a result of both personal and research experience, I have a lot of knowledge. It gets tapped almost daily in the EPI support groups that I’m a part of.

Whenever I notice myself answering the same question repeatedly, I make a mental note of it. Eventually, if a topic comes up often enough, I turn my response into a blog post. This way, I can provide a well-structured, comprehensive answer with more time and context than a quick comment on social media allows – and with the ability to give the same, high quality answer to multiple people (and in some cases, hundreds or thousands of people rather than the few who might see the comment buried in a response thread).

A few examples of this include:

One of my favorite things with this approach is then seeing other people begin to share the links to my longer-form content to help answer common questions. By writing things down in a shareable way, it also enables and supports other people to scale your work by sharing it easily. This has started to happen more and more with the elastase blog post, in part because there are so few resources that cover this information all in one place.

For me, I lean toward writing, but for other people that could be videos, podcast/audio recording, or other formats that can capture things you know and make them shareable, thus scaling yourself.

For me, this approach of “scaling myself” and thinking about longer form content to post online instead of re-typing similar answers over and over again isn’t unique to EPI.

I have been doing this for over a decade. I developed this pattern early after we developed and shared OpenAPS (the first open source automated insulin delivery algorithm) with the world. Early on, I found myself answering the same technical questions repeatedly in online discussions with the same answers. Typing out explanations on my phone was inefficient, and if one person had a question, others likely had the same one. Instead of repeating myself, I took the time to document answers. I would often pause, write up the information in the documentation, and share that instead. This made it easier and quicker to go find and share a link instead of retyping responses, and it also took less time, so I was willing to do it more quickly than if I had to delay what I was doing in real life in order to type out a long yet already-answered question. Over time, I had to do less one-off typing on my phone (and could save that time and energy for true, one-off unique questions) and could share links with a lot more information more easily.

How do I use AI to scale this type of work?

A lot of the above tasks are related to writing. There are different ways you can use AI for writing, without having it write something completely. You can give it notes – whether you type or voice dictate them – and have it clean up your notes, so you can focus on thinking and not about typing or fixing typos that break your flow. You can have it convert the notes into full sentences. You can ask it to write a paragraph or an article based on the notes. You can ask it to suggest wording for a particular sentence you want to clarify for your audience.

If you think about the AI as an intern and/or a partner/collaborator who you would ask to review or edit for you, you’ll likely find even more ways to integrate AI into different parts of your writing process, even if it’s not doing the full writing for you.

I have also tried to task the AI with writing for me, with mixed results. This doesn’t mean I don’t use it, but I’ve been practicing and learning where it generates usable content and where it doesn’t.

A lot of it depends on the prompt and the topic (as much as it does the output in terms of style, length, intended audience etc).

If it’s a topic that’s “known”, it can write more content that I can take and edit and transform, as opposed to when I am trying to write about a concept that is far from the current knowledge base. (I mean far for both humans and of AI – a lot of my work is bleeding edge, pushing fields towards new developments and leading humans there.) Sometimes I ask it to write something and end up using none of the content, but by saying “ugh no” my brain has jumped to saying to myself “it should really say…” and I am able to more quickly springboard into manually writing the content I was previously slow on. In other words, it can be a brainstorming tool in the opposite sense, showing me what I do not want to say on a topic! And on some of my frontier/bleeding edge topics, it reflects what is commonly ‘known’ and when what is known is now wrong (example, as always, of how it’s commonly incorrectly reported that chronic pancreatitis is the most common cause of EPI), it helps me more clearly distinguish the new content from the old, wrong, or misinformed.

(Also, it’s worth reminding you what I have to remind myself, that AI is changing constantly and new tools override what is known about what tasks do and don’t do well! For example, in between writing this and posting it, OpenAI released GPT4.5, which is reportedly better at writing-related tasks than GPT-4o and other older models. I’ll have to test it and see if that’s true and for what kinds of writing tasks!)

This isn’t the only way you can scale yourself with AI, though. Scaling yourself doesn’t have to be limited to writing and documentation style tasks. AI and other tools can help with many tasks (more examples here and here), such as:

  • Cleaning and transforming data into different formats
  • Converting a CSV file into a more readable table
  • Writing code to automate tedious data processing
  • Drafting plain-language instructions for engineers or programmers
  • Checking whether instructions or explanations are clear and understandable, and identifying any gaps in logic that you missed on your first pass

By leveraging AI and other automation tools, you can free up time and energy for higher-value work: the things you are uniquely suited to do in the world, and the things that you want or love to do. And do them more easily!

Pro tip: if you find yourself procrastinating a task, this may be a good sign that you could use AI for some of it. 

I’m trying to use noticing procrastination as a trigger for considering AI for a task.

An example of this is an upcoming post with a bunch of math and meaty cost analysis that I originally did by hand. I needed (wanted) to re-do these estimates with different numbers, but procrastinated a bit because having to carefully re-do all the estimates and replace them throughout the blog post seemed tedious, so my brain wanted to procrastinate. So, I took the blog post and dumped it in with a prompt asking it to write Jupyter Notebook code to replicate the analyses explained via the plain language post, with the ability to adjust all input variables and see the results in a table so I could compare the original and updated numbers. It took less than 1 minute to generate this code and about 5 minutes for me to copy/paste, update the numbers, run it, and evaluate the output and decide what to update in the post. Manually, this would’ve taken 30-60 minutes due to needing to check my work manually and trace it throughout the post. Instead, this automated the tedious bit and will result in this new post coming out next week rather than weeks from now (read about it here – it’s an analysis on how cost-effect Life for a Child is, a charity supporting people living with diabetes in low- and middle-income countries that can use your help to save lives.)

Scale yourself: automate more, so you can handle what matters, a blog by Dana M. Lewis from DIYPS.orgI encourage you to think about scaling yourself and identifying a task or series of tasks where you can get in the habit of leveraging these tools to do so. Like most things, the first time or two might take a little more time. But once you figure out what tasks or projects are suited for this, the time savings escalate. Just like learning how to use any new software, tool, or approach. A little bit of invested time up front will likely save you a lot of time in the future.

How Long Does It Take for Pancreatic Enzyme Replacement Therapy (PERT) to Start Working for People With Exocrine Pancreatic Insufficiency (EPI / PEI)?

How long does it take for pancreatic enzyme replacement therapy to start working? A blog from Dana M. Lewis on DIYPS.orgIf you have been prescribed pancreatic enzyme replacement therapy (PERT), aka enzymes for exocrine pancreatic insufficiency (EPI or PEI), you may be wondering how long it will take before you start to feel better or it starts to work. This is a common question, and the answer depends on several factors, including the dosage, meal composition, and how well your body uses the enzymes. Some improvements can be seen within a single meal, while other benefits take longer to manifest. It also depends on whether you have EPI, or if you have EPI in concert with other types of gastrointestinal conditions, because some of your symptoms may be coming from other conditions.

Immediate Effects of PERT

PERT should start working with your very first meal, if your dose is in the ballpark of being ideal for you and your food intake. The enzymes help break down fats, proteins, and carbohydrates so your body can absorb nutrients more effectively. If you are taking somewhere in the ballpark of the right dose, you may notice immediate improvements in digestion, such as:

  • Less bloating or cramping after eating
  • Reduced gas
  • A decrease in diarrhea or greasy, foul-smelling stools

These improvements should occur on a per-meal basis. If you take PERT with one meal but not another, you may notice a stark difference in symptoms after each of those meals. This is a good indicator that the enzymes are working when you do take them.

Why Some People Don’t See Immediate Improvement With PERT

While PERT can provide relief after a meal or noticeable effects within a day or so, many people do not take a sufficient dose initially. Under-dosing is common, which means you may still experience symptoms as you fine-tune your enzyme intake.

Here are some reasons why you might not see immediate results:

  • Not taking enough enzymes: Many people are prescribed a starting dose well below the standard guidelines, and this may not be enough for their specific needs. This is because your body is unique, and what you eat varies from what other people eat. The combination of these two factors means that your dose is not going to be the same as someone else’s, regardless of which “category” of EPI you fall into or even with an identical fecal elastase test result. If you still experience symptoms, you may need to increase your dose of enzymes.
  • Miscalculating enzyme dosing: If you eat a small salad with a few bites of chicken, this is likely a lower fat and lower protein meal, when you compare it to a large hamburger with bacon and cheese and a side of french fries. These meals likely need different doses of enzymes. The dose you start with may work for some of your existing meals, but don’t be surprised if you have symptoms with meals with more protein or more fat than your lower quantity meals. Some people can use the same, fixed dose for all their meals…but that usually means their meals don’t vary a lot. Other people like me can have a wide range of meal quantities, so we adjust our dosing for every meal. (It gets easier over time!)
  • Enzyme timing may be wrong: PERT needs to be taken with the first few bites of a meal, and sometimes additional enzymes are needed if the meal is prolonged. It’s ok if you get halfway through a meal and haven’t taken your enzymes – start taking them then. But don’t take them well before you eat or well after. The point is to get them into your system at the same time that you are eating (or drinking any drink with fat/protein). If you have a 5 course meal at a restaurant that lasts 2 hours, you will need to take more enzymes even if your usual dose would normally cover the total quantity of what you consumed. The fact that it’s so spread out matters. Rule of thumb most people use is 20-30 minutes, so if you’re eating longer than that, you likely need another pill (or more than one more).
  • Other gastrointestinal conditions: Some people have additional digestive issues such as SIBO or other conditions like pancreatitis that have their own symptoms, and it can be challenging to tell what are EPI-specific symptoms due to enzyme dosing or timing issues as opposed to symptoms of these other conditions.

Here are some example scenarios where you might not see the improvements right away:

  • If you eat a hamburger with fries as your first meal, but your prescription is for two pills of 10,000 lipase of PERT. This is unlikely to be enough for the meal, as the standard dose for regular meals is 40-50,000 units; many people need more than that; and this type of meal is higher in fat and protein than a standard meal. Thus, symptoms.
  • If you take your PERT 30 minutes before you eat, even if the dose matches your food perfectly, the timing is off and the enzymes won’t be where they need to be to help digest your food. Thus, symptoms.

Short-Term vs. Long-Term Improvements

Short-Term (Days to Weeks)

Once you find the right PERT dosage, the most noticeable and immediate improvements should occur within your first several meals and across a few days, including:

  • Reduction in diarrhea or loose stools
  • Less bloating and discomfort after eating
  • Improved stool consistency
  • Decreased urgency to use the bathroom

If you are still experiencing symptoms after a few days of consistent PERT use, consider adjusting your dose, especially in the context of looking at what quantity is in your meal. (You’ll find some other tips here walking you through how to look at what’s in your food and how to track it, including tools like PERT Pilot for tracking it on your phone over time.)

Long-Term (Weeks to Months)

While digestion-related symptoms can improve within days, some longer-term health effects take weeks or months to resolve or notice improvements. These include:

  • Nutritional deficiencies: If you have been malabsorbing fats and nutrients for a long time, it may take months of improved digestion to correct deficiencies in fat-soluble vitamins (A, D, E, K), iron, or B12.
  • Weight stabilization: Weight gain or stabilization may occur over weeks to months. (Not everyone gains weight, but if you’re looking for weight gain to occur after you improve digestion with enzymes, it will take some time).
  • Improved energy levels: Once your body starts absorbing nutrients more efficiently, you may notice a gradual increase in energy.

Do some people see improvement on these and other symptoms sooner? Yes! However, it’s different for everyone, so don’t expect every single symptom to magically get better after your first few days on PERT.

How to Know If PERT Is Working for You

The key to determining if PERT is effective lies in tracking your symptoms and adjusting accordingly. Signs that your PERT is working include:

  • Well-formed stools without oiliness or a greasy appearance
  • Normal bowel movement frequency (not too frequent or urgent)
  • Reduction in gas, bloating, and stomach discomfort
  • Gradual improvements in weight and energy levels over time, if those were bothersome to you before

Note a key factor that does NOT tell you if PERT is working for you, which is that changes in fecal elastase score do not tell you anything about whether your enzymes are working for you. Elastase is not affected directly by your enzymes, meaning the elastase test measures human elastase (and enzymes are not human elastase, so they’re not measured by the elastase test). Elastase can naturally fluctuate a bit over time; test precision is not perfect; and for a lot of reasons it’s common to see different numbers in elastase. Read this blog post for a lot more detail, but a change from 23 to 84, or from 154 to 137, or from 58 to 101 are not meaningful changes and do not change the diagnosis of EPI. The categorization of EPI as ‘moderate’ or ‘severe’ does not matter for either diagnosis overall (EPI is EPI) and does not matter for whether or not enzymes are effective because elastase can’t answer that question.

When to Adjust or Reassess Enzyme Dosing

If you do not see some improvements within a few meals or a few days, it may indicate that your dose is too low or not properly timed or you are eating different size meals and need to pay attention to your dose size relative to what you are eating. Work with your healthcare provider to fine-tune your dosage (note that they may not be aware of the guidelines for starting doses or aware that dose ranges vary person to person), and consider tracking your meals and symptoms to identify patterns. Once you’ve ruled that out, say by tracking your meals and increasing your doses and eating consistently sized meals, you may want to investigate other conditions contributing to symptoms.

For most people, PERT should start showing effects within a single meal if the dose is in the ballpark of being correct, even if it’s not fully covering your meal. However, because under-dosing is common, it may take days or weeks of adjustments to see consistent improvement or to improve or eliminate all symptoms.

Immediate symptoms like bloating, diarrhea, and gas should improve quickly (days to weeks), while long-term nutritional recovery (if you had any nutritional deficiencies) may take longer (weeks to months).
A gif showing a square moving along a spectrum from "too little" to "too much enzyme". Too little enzyme and you have symptoms, not enough and you reduce but don't eliminate symptoms. Enough enzymes and you eliminate symptoms. Too much risks constipation.

Other posts you may find helpful:

Beware “too much” and “too little” advice in Exocrine Pancreatic Insufficiency (EPI / PEI)

If I had a nickel every time I saw conflicting advice for people with EPI, I could buy (more) pancreatic enzyme replacement therapy. (PERT is expensive, so it’s significant that there’s so much conflicting advice).

One rule of thumb I find handy is to pause any time I see the words “too much” or “too little”.

This comes up in a lot of categories. For example, someone saying not to eat “too much” fat or fiber, and that a low-fat diet is better. The first part of the sentence should warrant a pause (red flag words – “too much”), and that should put a lot of skepticism on any advice that follows.

Specifically on the “low fat diet” – this is not true. A lot of outdated advice about EPI comes from historical research that no longer reflects modern treatment. In the past, low-fat diets were recommended because early enzyme formulations were not encapsulated or as effective, so people in the 1990s struggled to digest fat because the enzymes weren’t correctly working at the right time in their body. The “bandaid” fix was to eat less fat. Now that enzyme formulations are significantly improved (starting in the early 2000s, enzymes are now encapsulated so they get to the right place in our digestive system at the right time to work on the food we eat or drink), medical experts no longer recommend low-fat diets. Instead, people should eat a regular diet and adjust their enzyme intake accordingly to match that food intake, rather than the other way around (source: see section 4.6).

Think replacement of enzymes, rather than restriction of dietary intake: the “R” in PERT literally stands for replacement!

If you’re reading advice as a person with EPI (PEI), you need to have math in the back of your mind. (Sorry if you don’t like math, I’ll talk about some tools to help).

Any time people use words to indicate amounts of things, whether that’s amounts of enzymes or amounts of food (fat, protein, carbs, fiber), you need to think of specific numbers to go with these words.

And, you need to remember that everyone’s body is different, which means your body is different.

Turning words into math for pill count and enzymes for EPI

Enzyme intake should not be compared without considering multiple factors.

The first reason is because enzyme pills are not all the same size. Some prescription pancreatic enzyme replacement therapy (PERT) pills can be as small as 3,000 units of lipase or as large as 60,000 units of lipase. (They also contain thousands or hundreds of thousands of units of protease and amylase, to support protein and carbohydrate digestion. For this example I’ll stick to lipase, for fat digestion.)

If a person takes two enzyme pills per meal, that number alone tells us nothing. Or rather, it tells us only half of the equation!

The size of the pills matters. Someone taking two 10,000-lipase pills consumes 20,000 units per meal, while another person taking two 40,000-lipase pills is consuming 80,000 units per meal.

That is a big difference! Comparing the two total amounts of enzymes (80,000 units of lipase or 20,000 units of lipase) is a 4x difference.

And I hate to tell you this, but that’s still not the entire equation to consider. Hold on to your hat for a little more math, because…

The amount of fat consumed also matters.

Remember, enzymes are used to digest food. It’s not a magic pill where one (or two) pills will perfectly cover all food. It’s similar to insulin, where different people can need different amounts of insulin for the same amount of carbohydrates. Enzymes work the same way, where different people need different amounts of enzymes for the same amount of fat, protein, or carbohydrates.

And, people consume different amounts and types of food! Breakfast is a good example. Some people will eat cereal with milk – often that’s more carbs, a little bit of protein, and some fat. Some people will eat eggs and bacon – that’s very little carbs, a good amount of protein, and a larger amount of fat.

Let’s say you eat cereal with milk one day, and eggs and bacon the next day. Taking “two pills” might work for your cereal and milk, but not your eggs and bacon, if you’re the person with 10,000 units of lipase in your pill. However, taking “two pills” of 40,000 units of lipase might work for both meals. Or not: you may need more for the meal with higher amounts of fat and protein.

If someone eats the same quantity of fat and protein and carbs across all 3 meals, every day, they may be able to always consume the same number of pills. But for most of us, our food choices vary, and the protein and fat varies meal to meal, so it’s common to need different amounts at different meals. (If you want more details on how to figure out how much you need, given what you eat, check out this blog post with example meals and a lot more detail.)

You need to understand your baseline before making any comparisons

Everyone’s body is different, and enzyme needs vary widely depending on the amount of fat and protein consumed. What is “too much” for one person might be exactly the right amount for another, even when comparing the same exact food quantity. This variability makes it essential to understand your own baseline rather than following generic guidance. The key is finding what works for your specific needs rather than focusing on an arbitrary notion of “too much”, because “too much” needs to be compared to specific numbers that can be compared as apples to apples.

A useful analogy is heart rate. Some people have naturally higher or lower resting heart rates. If someone tells you (that’s not a doctor giving you direct medical advice) that your heart rate is too high, it’s like – what can you do about it? It’s not like you can grow your heart two sizes (like the Grinch). While fitness and activity can influence heart rate slightly, individual baseline differences remain significant. If you find yourself saying “duh, of course I’m not going to try to compare my heart rate to my spouse’s, our bodies are different”, that’s a GREAT frame of mind that you should apply to EPI, too.

(Another example is respiratory rate, where it varies person to person. If someone is having trouble breathing, the solution is not as simple as “breathe more” or “breathe less”—it depends on their normal range and underlying causes, and it takes understanding their normal range to figure out if they are breathing more or less than their normal, because their normal is what matters.)

If you have EPI, fiber (and anything else) also needs numbers

Fiber also follows this pattern. Some people caution against consuming “too much” fiber, but a baseline level is essential. “Too little” fiber can mimic EPI symptoms, leading to soft, messy stools. Finding the right amount of fiber is just as crucial as balancing fat and protein intake.

If you find yourself observing or hearing comments that you likely consume “too much” fiber – red flag check for “too much!” Similar to if you hear/see about ‘low fiber’. Low meaning what number?

You should get an estimate for how much you are consuming and contextualize it against the typical recommendations overall, evaluate whether fiber is contributing to your issues, and only then consider experimenting with it.

(For what it’s worth, you may need to adjust enzyme intake for fat/protein first before you play around with fiber, if you have EPI. Many people are given PERT prescriptions below standard guidelines, so it is common to need to increase dosing.)

For example, if you’re consuming 5 grams of fiber in a day, and the typical guidance is often for 25-30 grams (source, varies by age, gender and country so this is a ballpark)…. you are consuming less than the average person and the average recommendation.

In contrast, if you’re consuming 50+ grams of fiber? You’re consuming more than the average person/recommendation.

Understanding where you are (around the recommendation, quite a bit below, or above?) will then help you determine whether advice for ‘more’ or ‘less’ is actually appropriate in your case. Most people have no idea what you’re eating – and honestly, you may not either – so any advice for “too much”, “too little”, or “more” or “less” is completely unhelpful without these numbers in mind.

You don’t have to tell people these numbers, but you can and should know them if you want to consider evaluating whether YOU think you need more/less compared to your previous baseline.

How do you get numbers for fiber, fat, protein, and carbohydrates?

Instead of following vague “more” or “less” advice, first track your intake and outcomes.

If you don’t have a good way to estimate the amount of fat, protein, carbohydrates, and/or fiber, here’s a tool you can use – this is a Custom GPT that is designed to give you back estimates of fat, protein, carbohydrates, and fiber.

You can give it a meal, or a day’s worth of meals, or several days, and have it generate estimates for you. (It’s not perfect but it’s probably better than guessing, if you’re not familiar with estimating these macronutrients).

If you don’t like or can’t access ChatGPT (it works with free accounts, if you log in), you can also take this prompt, adjust it how you like, and give it to any free LLM tool you like (Gemini, Claude, etc.):

You are a dietitian with expertise in estimating the grams of fat, protein, carbohydrate, and fiber based on a plain language meal description. For every meal description given by the user, reply with structured text for grams of fat, protein, carbohydrates, and fiber. Your response should be four numbers and their labels. Reply only with this structure: “Fat: X; Protein: Y; Carbohydrates: Z; Fiber; A”. (Replace the X, Y, Z, and A with your estimates for these macronutrients.). If there is a decimal, round to the nearest whole number. If there are no grams of any of the macronutrients, mark them as 0 rather than nil. If the result is 0 for all four variables, please reply to the user: “I am unable to parse this meal description. Please try again.”

If you are asked by the user to then summarize a day’s worth of meals that you have estimated, you are able to do so. (Or a week’s worth). Perform the basic sum calculation needed to do this addition of each macronutrient for the time period requested, based on the estimates you provided for individual meals.

Another option is using an app like PERT Pilot. PERT Pilot is a free app for iOS (and for Android) for people with EPI that requires no login or user account information, and you can put in plain language descriptions of meals (“macaroni and cheese” or “spaghetti with meatballs”) and get back the estimates of fat, protein, and carbohydrates, and record how much enzymes you took so you can track your outcomes over time. (Android users – email me at Dana+PERTPilot@OpenAPS.org if you’d like to test the forthcoming Android version!) Note that PERT Pilot doesn’t estimate fiber, but if you want to start with fat/protein estimates, PERT Pilot is another way to get started with seeing what you typically consume. (For people without EPI, you can use Carb Pilot, another free iOS app that similarly gives estimates of macronutrients.)

Beware advice of "more" or "less" that is vague and non-numeric (not a number) unless you know your baseline numbers in exocrine pancreatic insufficiency. A blog by Dana M. Lewis from DIYPS.orgTL;DR: Instead of arbitrarily lowering or increasing fat or fiber in the diet, measure and estimate what you are consuming first. If you have EPI, assess fat digestion first by adjusting enzyme intake to minimize symptoms. (And then protein, especially for low fat / high protein meals, such as chicken or fish.) Only then consider fiber intake—some people may actually need more fiber rather than less than what they were consuming before if they experience mushy stools. Remember the importance of putting “more” or “less” into context with your own baseline numbers. Estimating current consumption is crucial because an already low-fiber diet may be contributing to the problem, and reducing fiber further could make things worse. Understanding your own baseline is the key.

You Can Create Your Own Icons (and animated gifs)

Over the years, I’ve experimented with different tools for making visuals. Some of them are just images but in the last several years I’ve made more animations, too.

But not with any fancy design program or purpose built tool. Instead, I use PowerPoint.

Making animated gifs

I first started using PowerPoint to create gifs around 2018 or 2019. At the time, PowerPoint didn’t have a built-in option to export directly to GIF format, so I had to export animations as a movie file first and then use an online converter to turn them into a GIF. Fortunately, in recent years, PowerPoint has added a direct “Export as GIF” feature.

The process of making an animated GIF in PowerPoint is similar to adding animations or transitions in a slide deck for a presentation. I’ve used this for various projects, including:

Am I especially trained? No. Do I feel like I have design skills? No.

Elbow grease and determination to try is what I have, with the goal of trying to use visuals to convey information as a summary or to illustrate a key point to accompany written text. (I also have a tendency to want to be a perfectionist, and I have to consciously let that go and let “anything is better than nothing” guide my attempts.)

Making icons is possible, too

Beyond animations, I’ve also used PowerPoint to create icons and simple logo designs.

I ended up making the logos for Carb Pilot (a free iOS app that enables you to track the macronutrients of your choice) and PERT Pilot (a free iOS app that enables people with exocrine pancreatic insufficiency, known as EPI or PEI, to track their enzyme intake) using PowerPoint.

This, and ongoing use of LLMs to help me with coding projects like these apps, is what led me to the realization that I can now make icons, too.

I was working to add a widget to Carb Pilot, so that users can have a widget on the home screen to more quickly enter meals without having to open the app and then tap; this saves a click every time. I went from having it be a single button to having 4 buttons to simulate the Carb Pilot home screen. For the “saved meals” button, I wanted a list icon, to indicate the list of previous meals. I went to SF Symbols, Apple’s icon library, and picked out the list icon I wanted to use, and referenced it in XCode. It worked, but it lacked something.

A light purple iOS widget with four buttons - top left is blue and says AI: top right is purple with a white microphone icon; bottom left is periwinkle blue with a white plus sign icon; bottom right is bright green with a custom list icon, where instead of bullets the three items are an apple, cupcake, and banana mini-icons. It occurred to me that maybe I could tweak it somehow and make the bullets of the list represent food items. I wasn’t sure how, so I asked the LLM if it was possible. Because I’ve done my other ‘design’ work in PowerPoint, I went there and quickly dropped some shapes and lines to simulate the icon, then tested exporting – yes, you can export as SVG! I spent a few more minutes tweaking versions of it and exporting it. It turns out, yes, you can export as SVG, but then the way I designed it wasn’t really suited for SVG use. When I had dropped the SVG into XCode, it didn’t show up. I asked the LLM again and it suggested trying PNG format. I exported the icon from powerpoint as PNG, dropped it into XCode, and it worked!

(That was a good reminder that even when you use the “right” format, you may need to experiment to see what actually works in practice with whatever tools you’re using, and not let the first failure be a sign that it can’t work.)

Use What Works

There’s a theme you’ll be hearing from me: try and see what works. Just try. You don’t know if you don’t try. With LLMs and other types of AI, we have more opportunities to try new and different things that we may not have known how to do before. From coding your own apps to doing data science to designing custom icons, these are all things I didn’t know how to do before but now I can. A good approach is to experiment, try different things (and different prompts), and not be afraid to use “nontraditional” tools for projects, creative or otherwise. If it works, it works!

Facing Uncertainty with AI and Rethinking What If You Could?

If you’re feeling overwhelmed by the rapid development of AI, you’re not alone. It’s moving fast, and for many people the uncertainty of the future (for any number of reasons) can feel scary. One reaction is to ignore it, dismiss it, or assume you don’t need it. Some people try it once, usually on something they’re already good at, and when AI doesn’t perform better than they do, they conclude it’s useless or overhyped, and possibly feel justified in going back to ignoring or rejecting it.

But that approach misses the point.

AI isn’t about replacing what you already do well. It’s about augmenting what you struggle with, unlocking new possibilities, and challenging yourself to think differently, all in the pursuit of enabling YOU to do more than you could yesterday.

One of the ways to navigate the uncertainty around AI is to shift your mindset. Instead of thinking, “That’s hard, and I can’t do that,” ask yourself, “What if I could do that? How could I do that?”

Sometimes I get a head start by asking an LLM just that: “How would I do X? Layout a plan or outline an approach to doing X.” I don’t always immediately jump to doing that thing, but I think about it, and probably 2 out of 3 times, laying out a possible approach means I do come back to that project or task and attempt it at a later time.

Even if you ultimately decide not to pursue something because of time constraints or competing priorities, at least you’ve explored it and possibly learned something even in the initial exploration about it. But, I want to point out that there’s a big difference between legitimately not being able to do something and choosing not to. Increasingly, the latter is what happens, where you may choose not to tackle a task or take on a project: this is very different from not being able to do so.

Finding the Right Use Cases for AI

Instead of testing AI on things you’re already an expert in, try applying it to areas where you’re blocked, stuck, overwhelmed, or burdened by the task. Think about a skill you’ve always wanted to learn but assumed was out of reach. Maybe you’ve never coded before, but you’re curious about writing a small script to automate a task. Maybe you’ve wanted to design a 3D-printed tool to solve a real-world problem but didn’t know where to start. AI can be a guide, an assistant, and sometimes even a collaborator in making these things possible.

For example, I once thought data science was beyond my skill set. For the longest time, I couldn’t even get Jupyter Notebooks to run! Even with expert help, I was clearly doing something silly and wrong, but it took a long time and finally LLM assistance to get step by step and deeper into sub-steps to figure out the step that was never in the documentation or instructions that I was missing – and I finally figured it out! From there, I learned enough to do a lot of the data science work on my own projects. You can see that represented in several recent projects. The same thing happened with iOS development, which I initially felt imposter syndrome about. And this year, after FOUR failed attempts (even 3 using LLMs), I finally got a working app for Android!

Each time, the challenge felt enormous. But by shifting from “I can’t” to “What if I could?” I found ways to break through. And each time AI became a more capable assistant, I revisited previous roadblocks and made even more progress, even when it was a project (like an Android version of PERT Pilot) I had previously failed at, and in that case, multiple times.

Revisiting Past Challenges

AI is evolving rapidly, and what wasn’t possible yesterday might be feasible today. Literally. (A great example is that I wrote a blog post about how medical literature seems like a game of telephone and was opining on AI-assisted tools to aid with tracking changes to the literature over time. The day I put that blog post in the queue, OpenAI announced their Deep Research tool, which I think can in part address some of the challenges I talked about currently being unsolved!)

One thing I have started to do that I recommend is keeping track of problems or projects that feel out of reach. Write them down. Revisit them every few months, and explore them with the latest LLM and AI tools. You might be surprised at how much has changed, and what is now possible.

Moving Forward with AI

You don’t even have to use AI for everything. (I don’t.) But if you’re not yet in the habit of using AI for certain types of tasks, I challenge you to find a way to use an LLM for *something* that you are working on.

A good place to insert this into your work/projects is to start noting when you find yourself saying or thinking “this is the way we/I do/did things”.

When you catch yourself thinking this, stop and ask:

  • Does it have to be done that way? Why do we think so?
  • What are we trying to achieve with this task/project?
  • Are there other ways we can achieve this?
  • If not, can we automate some or more steps of this process? Can some steps be eliminated?

You can ask yourself these questions, but you can also ask these questions to an LLM. And play around with what and how you ask (the prompt, or what you ask it, makes a difference).

One example for me has been working on a systematic review and meta analysis of a medical topic. I need to extract details about criteria I am analyzing across hundreds of papers. Oooph, big task, very slow. The LLM tools aren’t yet good about extracting non-obvious data from research papers, especially PDFs where the data I am interested may be tucked into tables, figure captions, or images themselves rather than explicitly stated as part of the results section. So for now, that still has to be manually done, but it’s on my list to revisit periodically with new LLMs.

However, I recognized that the way I was writing down (well, typing into a spreadsheet) the extracted data was burdensome and slow, and I wondered if I could make a quick simple HTML page to guide me through the extraction, with an output of the data in CSV that I could open in spreadsheet form when I’m ready to analyze. The goal is easier input of the data with the same output format (CSV for a spreadsheet). And so I used an LLM to help me quickly build that HTML page, set up a local server, and run it so I can use it for data extraction. This is one of those projects where I felt intimidated – I never quite understood spinning up servers and in fact didn’t quite understand fundamentally that for free I can “run” “a server” locally on my computer in order to do what I wanted to do. So in the process of working on a task I really understood (make an HTML page to capture data input), I was able to learn about spinning up and using local servers! Success, in terms of completing the task and learning something I can take forward into future projects.

Another smaller recent example is when I wanted to put together a simple case report for my doctor, summarizing symptoms etc, and then also adding in PDF pages of studies I was referencing so she had access to them. I knew from the past that I could copy and paste the thumbnails from Preview into the PDF, but it got challenging to be pasting 15+ pages in as thumbnails and they were inserting and breaking up previous sections, so the order of the pages was wrong and hard to fix. I decided to ask my LLM of choice if it was possible to automate compiling 4 PDF documents via a command line script, and it said yes. It told me what library to install (and I checked this is an existing tool and not a made up or malicious one first), and what command to run. I ran it, it appended the PDFs together into one file the way I wanted, and it didn’t require the tedious hand commands to copy and paste everything together and rearrange when the order was messed up.

The more I practice, the easier I find myself switching into the habit of saying “would it be possible to do X” or “Is there a way to do Y more simply/more efficiently/automate it?”. That then leads to portions which I can decide to implement, or not. But it feels a lot better to have those on hand, even if I choose not to take a project on, rather than to feel overwhelmed and out of control and uncertain about what AI can do (or not).

Facing uncertainty with AI and rethinking "What if you could?", a blog post by Dana M. Lewis on DIYPS.orgIf you can shift your mindset from fear and avoidance to curiosity and experimentation, you might discover new skills, solve problems you once thought were impossible, and open up entirely new opportunities.

So, the next time you think, “That’s too hard, I can’t do that,” stop and ask:

“What if I could?”

If you appreciated this post, you might like some of my other posts about AI if you haven’t read them.

How Medical Research Literature Evolves Over Time Like A Game of Telephone

Have you ever searched for or through medical research on a specific topic, only to find different studies saying seemingly contradictory things? Or you find something that doesn’t seem to make sense?

You may experience this, whether you’re a doctor, a researcher, or a patient.

I have found it helpful to consider that medical literature is like a game of telephone, where a fact or statement is passed from one research paper to another, which means that sometimes it is slowly (or quickly!) changing along the way. Sometimes this means an error has been introduced, or replicated.

A Game of Telephone in Research Citations

Imagine a research study from 2016 that makes a statement based on the best available data at the time. Over the next few years, other papers cite that original study, repeating the statement. Some authors might slightly rephrase it, adding their own interpretations. By 2019, newer research has emerged that contradicts the original statement. Some researchers start citing this new, corrected information, while others continue citing the outdated statement because they either haven’t updated their knowledge or are relying on older sources, especially because they see other papers pointing to these older sources and find it easiest to point to them, too. It’s not necessarily made clear that this outdated statement is now known to be incorrect. Sometimes that becomes obvious in the literature and field of study, and sometimes it’s not made explicit that the prior statement is ‘incorrect’. (And if it is incorrect, it doesn’t become known as incorrect until later – at the time it’s made, it’s considered to be correct.) 

By 2022, both the correct and incorrect statements appear in the literature. Eventually, a majority of researchers transition to citing the updated, accurate information—but the outdated statement never fully disappears. A handful of papers continue to reference the original incorrect fact, whether due to oversight, habit (of using older sources and repeating citations for simple statements), or a reluctance to accept new findings.

The gif below illustrates this concept, showing how incorrect and correct statements coexist over time. It also highlights how researchers may rely on citations from previous papers without always checking whether the original information was correct in the first place.

Animated gif illustrating how citations branch off and even if new statements are introduced to the literature, the previous statement can continue to appear over time.

This is not necessarily a criticism of researchers/authors of research publications (of which I am one!), but an acknowledgement of the situation that results from these processes. Once you’ve written a paper and cited a basic fact (let’s imagine you wrote this paper in 2017 and cite the 2016 paper and fact), it’s easy to keep using this citation over time. Imagine it’s 2023 and you’re writing a paper on the same topic area, it’s very easy to drop the same citation from 2016  in for the same basic fact, and you may not think to consider updating the citation or check if the fact is still the fact.

Why This Matters

Over time, a once-accepted “fact” may be corrected or revised, but older statements can still linger in the literature, continuing to influence new research. Understanding how this process works can help you critically evaluate medical research and recognize when a widely accepted statement might actually be outdated—or even incorrect.

If you’re looking into a medical topic, it’s important to pay attention not just to what different studies say, but also when they were published and how their key claims have evolved over time. If you notice a shift in the literature—where newer papers cite a different fact than older ones—it may indicate that scientific understanding has changed.

One useful strategy is to notice how frequently a particular statement appears in the literature over time.

Whenever I have a new diagnosis or a new topic to research on one of my chronic diseases, I find myself doing this.

I go and read a lot of abstracts and research papers about the topic; I generally observe patterns in terms of key things that everyone says, which establishes what the generally understood “facts” are, and also notice what is missing. (Usually, the question I’m asking is not addressed in the literature! But that’s another topic…)

I pay attention to the dates, observing when something is said in papers in the 1990s and whether it’s still being repeated in the 2020s era papers, or if/how it’s changed. In my head, I’m updating “this is what is generally known” and “this doesn’t seem to be answered in the literature (yet)” and “this is something that has changed over time” lists.

Re-Evaluating the Original ‘Fact’

In some cases, it turns out the original statement was never correct to begin with. This can happen when early research is based on small sample sizes, incomplete data, or incorrect assumptions. Sometimes that statement was correct, in context, but taken out of context immediately and this out of context use was never corrected. 

For example, a widely cited statement in medical literature once claimed that chronic pancreatitis is the most common cause of exocrine pancreatic insufficiency (EPI). This claim was repeated across numerous papers, reinforcing it as accepted knowledge. However, a closer examination of population data shows that while chronic pancreatitis is a known co-condition of EPI, it is far less common than diabetes—a condition that affects a much larger population and is also strongly associated with EPI. Despite this, many papers still repeat the outdated claim without checking the original data behind it.

(For a deeper dive into this example, you can read my previous post here. But TL;DR: even 80% of .03% is a smaller number than 10% of 10% of the overall population…so it is not plausible that CP is the biggest cause of EPI/PEI.)

Stay Curious

This realization can be really frustrating, because if you’re trying to do primary research to help you understand a topic or question, how do you know what the truth is? This is peer-reviewed research, but what this shows us is that the process of peer-review and publishing in a journal is not infallible. There can be errors. The process for updating errors can be messy, and it can be hard to clean up the literature over time. This makes it hard for us humans – whether in the role of patient or researcher or clinician – to sort things out.

But beyond a ‘woe is me, this is hard’ moment of frustration, I do find that this perspective of literature as a process of telephone makes me a better reader of the literature and forces me to think more critically about what I’m reading, and take papers in context of the broader landscape of literature and evolving knowledge base. It helps remove the strength I would otherwise be prone to assigning any one paper (and any one ‘fact’ or finding from a single paper), and encourages me to calibrate this against the broader knowledge base and the timeline of this knowledge base.

That can also be hard to deal with personally as a researcher/author, especially someone who tends to work in the gaps, establishing new findings and facts and introducing them to the literature. Some of my work also involves correcting errors in the literature, which I find from my outsider/patient perspective to be obvious because I’ve been able to use fresh eyes and evaluate at a systematic review level/high level view, without being as much in the weeds. That means my work, to disseminate new or corrected knowledge, is even more challenging. It’s also challenging personally as a patient, when I “just” want answers and for everything to already be studied, vetted, published, and widely known by everyone (including me and my clinician team).

But it’s usually not, and that’s just something I – and we – have to deal with. I’m curious as to whether we will eventually develop tools with AI to address this. Perhaps a mini systematic review tool that scrapes the literature and includes an analysis of how things have changed over time. This is done in systematic review or narrative reviews of the literature, when you read those types of papers, but those papers are based on researcher interests (and time and funding), and I often have so many questions that don’t have systematic reviews/narrative reviews covering them. Some I turn into papers myself (such as my paper on systematically reviewing the dosing guidelines and research on pancreatic enzyme replacement therapy for people with exocrine pancreatic insufficiency, known as EPI or PEI, or a systematic review on the prevalence of EPI in the general population or a systematic review on the prevalence of EPI in people with diabetes (Type 1 and Type 2)), but sometimes it’s just a personal question and it would be great to have a tool to help facilitate the process of seeing how information has changed over time. Maybe someone will eventually build that tool, or it’ll go on my list of things I might want to build, and I’ll build it myself like I have done with other types of research tools in the past, both without and with AI assistance. We’ll see!

TL;DR: be cognizant of the fact that medical literature changes over time, and keep this in mind when reading a single paper. Sometimes there are competing “facts” or beliefs or statements in the literature, and sometimes you can identify how it evolves over time, so that you can better assess the accuracy of research findings and avoid relying on outdated or incorrect information.

Whether you’re a researcher, a clinician, or a patient doing research for yourself, this awareness can help you better navigate the scientific literature.

A screenshot from the animated gif showing how citation strings happen in the literature, branching off over time but often still resulting in a repetition of a fact that is later considered to be incorrect, thus both the correct and incorrect fact occur in the literature at the same time.

The prompt matters when using Large Language Models (LLMs) and AI in healthcare

I see more and more research papers coming out these days about different uses of large language models (LLMs, a type of AI) in healthcare. There are papers evaluating it for supporting clinicians in decision-making, aiding in note-taking and improving clinical documentation, and enhancing patient education. But I see a wide-sweeping trend in the titles and conclusions of these papers, exacerbated by media headlines, making sweeping claims about the performance of one model versus another. I challenge everyone to pause and consider a critical fact that is less obvious: the prompt matters just as much as the model.

As an example of this, I will link to a recent pre-print of a research article I worked on with Liz Salmi (published article here pre-print here).

Liz nerd-sniped me about an idea of a study to have a patient and a neuro-oncologist evaluate LLM responses related to patient-generated queries about a chart note (or visit note or open note or clinical note, however you want to call it). I say nerd-sniped because I got very interested in designing the methods of the study, including making sure we used the APIs to model these ‘chat’ sessions so that the prompts were not influenced by custom instructions, ‘memory’ features within the account or chat sessions, etc. I also wanted to test something I’ve observed anecdotally from personal LLM use across other topics, which is that with 2024-era models the prompt matters a lot for what type of output you get. So that’s the study we designed, and wrote with Jennifer Clarke, Zhiyong Dong, Rudy Fischmann, Emily McIntosh, Chethan Sarabu, and Catherine (Cait) DesRoches, and I encourage you to check out the article here pre-print and enjoy the methods section, which is critical for understanding the point I’m trying to make here. 

In this study, the data showed that when LLM outputs were evaluated for a healthcare task, the results varied significantly depending not just on the model but also on how the task was presented (the prompt). Specifically, persona-based prompts—designed to reflect the perspectives of different end users like clinicians and patients—yielded better results, as independently graded by both an oncologist and a patient.

The Myth of the “Best Model for the Job”

Many research papers conclude with simplified takeaways: Model A is better than Model B for healthcare tasks. While performance benchmarking is important, this approach often oversimplifies reality. Healthcare tasks are rarely monolithic. There’s a difference between summarizing patient education materials, drafting clinical notes, or assisting with complex differential diagnosis tasks.

But even within a single task, the way you frame the prompt makes a profound difference.

Consider these three prompts for the same task:

  • “Explain the treatment options for early-stage breast cancer.”
  • “You’re an oncologist. Explain the treatment options for early-stage breast cancer.”
  • “You’re an oncologist. Explain the treatment options for early-stage breast cancer as you would to a newly diagnosed patient with no medical background.”

The second and third prompt likely result in a more accessible and tailored response. If a study only tests general prompts (e.g. prompt one), it may fail to capture how much more effective an LLM can be with task-specific guidance.

Why Prompting Matters in Healthcare Tasks

Prompting shapes how the model interprets the task and generates its output. Here’s why it matters:

  • Precision and Clarity: A vague prompt may yield vague results. A precise prompt clarifies the goal and the speaker (e.g. in prompt 2), and also often the audience (e.g. in prompt 3).
  • Task Alignment: Complex medical topics often require different approaches depending on the user—whether it’s a clinician, a patient, or a researcher.
  • Bias and Quality Control: Poorly constructed prompts can inadvertently introduce biases

Selecting a Model for a Task? Test Multiple Prompts

When evaluating LLMs for healthcare tasks—or applying insights from a research paper—consider these principles:

  1. Prompt Variation Matters: If an LLM fails on a task, it may not be the model’s fault. Try adjusting your prompts before concluding the model is ineffective, and avoid broad sweeping claims about a field or topic that aren’t supported by the test you are running.
  2. Multiple Dimensions of Performance: Look beyond binary “good” vs. “bad” evaluations. Consider dimensions like readability, clinical accuracy, and alignment with user needs, as an example when thinking about performance in healthcare. In our paper, we saw some cases where a patient and provider overlapped in ratings, and other places where the ratings were different.
  3. Reproducibility and Transparency: If a study doesn’t disclose how prompts were designed or varied, its conclusions may lack context. Reproducibility in AI studies depends not just on the model, but on the interaction between the task, model, and prompt design. You should be looking for these kinds of details when reading or peer reviewing papers. Take results and conclusions with a grain of salt if these methods are not detailed in the paper.
  4. Involve Stakeholders in Evaluation: As shown in the preprint mentioned earlier, involving both clinical experts and patients in evaluating LLM outputs adds critical perspectives often missing in standard evaluations, especially as we evolve to focus research on supporting patient needs and not simply focusing on clinician and healthcare system usage of AI.

What This Means for Healthcare Providers, Researchers, and Patients

  • For healthcare providers, understand that the way you frame a question can improve the usefulness of AI tools in practice. A carefully constructed prompt, adding a persona or requesting information for a specific audience, can change the output.
  • For researchers, especially those developing or evaluating AI models, it’s essential to test prompts across different task types and end-user needs. Transparent reporting on prompt strategies strengthens the reliability of your findings.
  • For patients, recognizing that AI-generated health information is shaped by both the model and the prompt. This can support critical thinking when interpreting AI-driven health advice. Remember that LLMs can be biased, but so too can be humans in healthcare. The same approach for assessing bias and evaluating experiences in healthcare should be used for LLM output as well as human output. Everyone (humans) and everything (LLMs) are capable of bias or errors in healthcare.

Prompts matter, so consider model type as well as the prompt as a factor in assessing LLMs in healthcare. Blog by Dana M. LewisTLDR: Instead of asking “Which model is best?”, a better question might be:

“How do we design and evaluate prompts that lead to the most reliable, useful results for this specific task and audience?”

I’ve observed, and this study adds evidence, that prompt interaction with the model matters.

A Tale of Three Artificial Intelligence (AI) Experiences in Healthcare Interactions

AI tools are being increasingly used in healthcare, particularly for tasks like clinical notetaking during virtual visits. As a patient, I’ve had three recent experiences with AI-powered notetaking tools during appointments with the same clinician. Each time, I consented to its use, but the results were very different across the three encounters. The first two involved similar tools with mostly good results but surprising issues around pronouns and transparency of the consent process. The third was a different tool with a noticeable drop in quality. But what really stands out, when I compare these to a visit without AI, is that human errors happen too — and the healthcare system lacks effective processes for identifying and correcting errors, no matter the source.

Encounter One: Good Notes, Incorrect Pronouns

At the start of my first virtual appointment, my clinician asked for my permission to use an AI-powered tool for notetaking. I consented. After the visit, I reviewed the clinical note, and the summary at the top described me using “he/him” pronouns. I’m female, so they should have been “she/her”.

The rest of the note was detailed and clinically accurate and useful. But the pronoun error stood out. It seemed like the AI defaulted to male pronouns when gender information wasn’t explicitly mentioned, which made me wonder whether the model was trained with gender bias or if this was a design flaw in this tool.

Encounter Two: Clarifying Pronouns, Learning About Chart Access

At the next appointment, my clinician again asked for consent to use an AI-powered notetaker. I agreed and pointed out the pronoun error from the previous visit, clarifying that I am female and use she/her pronouns. My clinician looked at the prior note and was equally puzzled, commenting that this issue had come up with other patients — both directions, sometimes assigning female pronouns to male patients and vice versa. The clinician mentioned that the AI system supposedly had access to patient charts and should be able to pull gender information from existing records. That really surprised me: the consent statement had described the tool as a notetaking aid, but nothing had been said about access to my full chart. I would have given permission either way, but the fact that this hadn’t been disclosed upfront was disappointing. I had understood this to be a passive notetaking tool summarizing the visit in real time, not something actively pulling and using other parts of my health record.

This time, the pronouns in the note were correct (which could be because we talked about it and I declared the pronouns), and the overall summary was again accurate and detailed. But the fact that this was a recurring issue, with my provider seeing it in both directions across multiple patients, made it clear that pronoun errors weren’t a one-off glitch.

Encounter Three: A Different AI with Worse Results

By the third appointment, I knew what to expect. The clinician again asked for consent to use an AI notetaker, and I agreed. But after reviewing the note from this visit, two things stood out.

First, the quality of the notetaking was noticeably worse. Several errors were obvious, including situations where the note reflected the exact opposite of what had been discussed. For example, I had said that something did not happen, yet the note recorded that it did.

Second, this time the note disclosed the specific software used for notetaking at the bottom of the document. It was a different tool than the one used in the first two visits. I hadn’t been told that a different AI tool was being used, but based on the change in quality and the naming disclosure, it was clear this was a switch.

This experience reinforced that even when performing the same task — in this case, AI notetaking — the software can vary widely in accuracy and quality. I much preferred the output from the first two visits, even with the initial pronoun error, over the third experience where clinically significant details were recorded incorrectly.

Notably, there doesn’t seem to be a process or method (or if there is one, it is not communicated to patients or easily findable when searching) to give the health system feedback on the quality and accuracy of these tools. Which seems like a major flaw in most health systems’ implementations of AI-related tools, assessing and evaluating only from the healthcare provider perspective and overlooking or outright ignoring the direct impact on patients (which influences patient care, the clinician-patient relationship, trust with the health system….).

A Human-Only Encounter: Still Not Error-Free

To give further context, I want to compare these AI experiences with a separate virtual visit where no AI was involved. This was with a different clinician who took notes manually. The pronouns were correct in this note, but there were still factual inaccuracies.

A small but clear example: I mentioned using Device A, but the note stated I was using Device B. This was not a critical error at the time, but it was still incorrect.

The point here is that human documentation errors are not rare. They happen frequently, even without AI involved. Yet the narrative around AI in healthcare often frames mistakes as uniquely concerning when, in reality, this problem already exists across healthcare.

A Bigger Issue is Lack of Processes for Fixing Errors

Across all four encounters — both AI-assisted and human-driven — the most concerning pattern was not the errors themselves but the failure to correct them, even after they were pointed out.

In the first AI note where the pronouns were wrong, the note was never corrected, even after I brought it up at the next appointment. The error remains in my chart.

In the human-driven note, where the wrong device was recorded, I pointed out the error multiple times over the years. Despite that, the error persisted in my chart across multiple visits.

Eventually, it did affect my care. During a prescription renewal, the provider questioned whether I was using the device at all because they referenced the erroneous notes rather than the prescription history. I had to go back, cite old messages where I had originally pointed out the error, and clarify that the device listed in the notes was wrong.

I had stopped trying to correct this error after multiple failed attempts because it hadn’t impacted my care at the time. But years later, it suddenly mattered — and the persistence of that error caused confusion and required extra time, adding friction into what should have been a seamless prescription renewal process.

My point: the lack of effective remediation processes is not unique to either AI or human documentation. Errors get introduced and then they stay. There are no good systems for correcting clinical notes, whether written by a human or AI.

So, What Do We Do About AI in Healthcare?

Critics of AI in healthcare often argue that its potential for errors is a reason to avoid the technology altogether. But as these experiences show, human-driven documentation isn’t error-free either.

The problem isn’t AI.

It’s that healthcare systems as a whole have poor processes for identifying and correcting errors once they occur.

When we evaluate AI tools, we need to ask:

  • What types of errors are we willing to tolerate?
  • How do we ensure transparency about how the tools work and what data they access?
  • Most importantly, what mechanisms exist to correct errors after they’re identified?

This conversation needs to go beyond whether errors happen and instead focus on how we respond when they do.  It’s worth thinking about this in the same way I’ve written about errors of commission and omission in diabetes care with automated insulin delivery (AID) systems (DOI: 10.1111/dme.14687; author copy here). Errors of commission happen when something incorrect is recorded. Errors of omission occur when important details are left out. Both types of errors can affect care, and both need to be considered when evaluating the use of AI or human documentation.

In my case, despite the pronoun error in the first AI note, the notetaking quality was generally higher than the third encounter with a different AI tool. And even in the human-only note, factual errors persisted over years with no correction.

Three encounters with AI in healthcare - reflecting on errors of omission and commission that happen both with humans and AI , a blog post by Dana M. Lewis from DIYPS.orgAI can be useful for reducing clinician workload and improving documentation efficiency. But like any tool, its impact depends on how it’s implemented, how transparent the process is, and whether there are safeguards to address errors when they occur.

The reality is both AI and human clinicians make mistakes.

What matters, and what we should work on addressing, is how to fix errors in healthcare documentation and records when they occur.

Right now, this is a weakness of the healthcare system, and not unique to AI.

Infection is not inevitable: how to stop the spread of infections like COVID-19, flu, RSV, colds, and more in your house

I observe a number of people who seem to think it’s inevitable that once someone gets sick, the rest of the house is going to get sick with 100% certainty.

Nope.

First of all, household transmission rates are less than 100% for all of these conditions, even if you didn’t take any precautions or make any behavior changes.

Secondly, with knowledge about how these things spread and some mitigation measures, you can reduce this a lot – and in some cases to nearly zero.

I will caveat: that of course depending on the situation some of these precautions may not make sense or be possible. For example, if you have kids, your exposures may be different. We don’t have kids in our house, so we are dealing with adult to adult possible transmission. That being said, some of these things may still be worth doing to some degree, to cut down the risk of exposure and/or to limit the viral dose you are exposed to, even in a situation that is less straightforward like a parent taking care of sick kids.

PS – if you’re reading this in January 2025 and don’t read the rest, make sure you’ve gotten your flu shot (yes, it helps) for the 2024-2025 flu season. No, it’s not too late. If you’re >65, you should also check about the RSV vaccine (which like the flu shot is a seasonal vaccine). It’s not too late and given the current high rates of RSV and flu (and soon to be uptick in COVID), they can help prevent getting or limit the severity if you do get exposed.

Our experience preventing the spread of RSV and the common cold

I can speak with recent, practical experience on this.

Twice.

First, let’s talk about RSV.

Before Thanksgiving, Scott and I were exposed to a nibling (aka a niece or nephew – of which we have 10 plus several honorary ones!) who had what we thought was a lingering cough from a cold from a few weeks ago. Because I am avoiding infection, I wore a mask inside and did not get up close to the nibling, so as a result of all of this likely had minimal exposure. Scott did not mask and had spent a lot more time with this nibling hanging all over him and coughing near or on him. Within 48 hours, he started to get symptoms of something.

We activated our plan for household transmission avoidance. Well, with a rolling start: Scott recognized by Thanksgiving evening that he was starting to feel unwell and had a tiny bit of coughing. I thought I could hear something in his chest differently, in addition to the occasional cough, so I went into full precaution mode while Scott did a partial precaution mode. This meant we set up air purifiers by each of our beds, and a fan pointed in my direction so all air was blowing away from me. I also wore a mask to go to sleep in. (This was super annoying and I don’t like doing this, especially because I usually take a shower and go to bed with wet hair. Wearing an n95 with head straps on wet hair plus having a fan and purifier blowing on me is chilly and unfun.) I would’ve preferred Scott to mask, too, or go to the guest bedroom to sleep, but it was late in the evening; he wasn’t convinced he was really sick; and I was too exhausted to argue about it on top of the fact that we were leaving on a trip the next morning. So he did not mask that night.

The next morning, though, he was definitely sick. He tested negative for COVID, and the nibling and everyone else from that house had been testing for COVID and negative, so we were fairly confident based on serial testing that this was not COVID. At the time, the thought was this was a common cold.

Since we were planning to mask in indoor spaces, anyway, including in the airport and on the plane, we felt comfortable going on our trip as planned, because we would be unlikely to infect anyone else. (This includes no indoor dining: we don’t take off our masks and eat inside.)

Because Scott realized he was sick, he masked from that point forward (with a non-valved N95). We both masked in the car, in the airport, on the plane, and again when we arrived while driving in the rental car. Then a challenge: we needed to eat dinner (we got takeout), and we were sharing a hotel room overnight. We switched from a hotel room with a king bed to a room with two queen beds, which would give us some more space overnight. But we took turns eating dinner unmasked in the hotel room (it was too cold to be outside) with the far-UVC lights on and the purifiers around each of us when we ate. While we ate, the other person was masked. (And I went first, so there was no unmasked air from Scott while I was eating and he went second). We also took turns showering, again with me going first and him not having been in the bathroom unmasked until after I had gone in. Other than that, we stayed masked in the hotel room including overnight, again with purifiers between us and the far-UVC lights running.

(This hotel did not have windows that opened to outside, but if there had been windows I would’ve eaten in front of the open window and we would’ve likely kept it cracked open and the heat turned up, to improve the room’s ventilation).

The next day, we had more of a drive, and again we masked. We also slightly rolled down the windows in the backseat to improve ventilation. Scott sometimes took his mask off for comfort stretches, because he was driving, but put it back on fully and sealed it before coughing. I kept my mask on without ceasing. We did a 4.5 hour drive this way.

Luckily, once we arrived at our destination, there was a spare bedroom, so that became Scott’s headquarters. He stayed masked in the living room/shared areas. He sat downwind outside and masked up when coughing if anyone was outside. We left the sliding door to the outside cracked open, in order to keep the air in the common areas well-ventilated. This worked, because we were able to keep CO2 levels (a proxy for ventilation) down below 700 ppm most of the time.

Because we had separate bedrooms, we did not mask while sleeping the rest of the week, because we each had our own rooms (and own airflow). I did keep a purifier running in my room all week, but that’s my habit regardless because I’m so allergic to dust.

And guess what? It all worked. We masked again on the drive back to the airport and in the airport and on the plane and again once we got home.

I never got RSV. The four other adults we spent time with and shared a house with….also did not get RSV. So we are pretty confident that the transmission chain stopped completely at Scott.

In summary, what worked:

  • Masking in shared spaces, and two-way masking when it wasn’t possible to ventilate
  • When we had to sleep in the same room, two-way masking even for sleeping overnight
  • Scott masking in shared spaces that were well ventilated, and often left the room to go cough even when masked (or coughing outside). This often meant he masked, but the rest of us did not mask inside the whole time.
  • Generally keeping distance. Droplets were managed by the N95 mask, and we were ventilating to reduce aerosol transmission risk, but still keeping physical distance to further reduce the risk.

RSV is *very* transmissible especially with aerosols, and Scott was coughing a lot all day and night. (At one point, his Sleep Cycle app was estimating 18 coughs per hour). It took a long time for that to get down to normal, so he continued to sleep in our guest room when we got back and we continued to ventilate well even when we gradually reduced masking once he stopped coughing. It took about 10 or so days for all of his biometrics to normalize, and about 14 days for his cough to completely go away. It probably was closer to three weeks before he finally felt all recovered.

So with that timing in mind, you know what happens 4 weeks after Thanksgiving? Christmas/other end of year holiday gatherings.

We had plans to see 8 kids and 8 adults (plus us) for Christmas. And at Christmas, it seemed like everyone had a cold already. So again, I went in and mostly masked except for when I was in front of an open window and the room was well ventilated, without anyone coughing actively in the room. (If anyone was in the room with me and coughing, especially the kids, I would mask even with the window open).

I did not get the cold that 8-10 (out of 16) people eventually got.

But…Scott did. And this time, he was mostly masked, but he still spent more time up close with kids who were coughing quite a bit. And this is where some of the dynamics of knowing WHAT people have is helpful. You can’t always know, but you can sometimes use the symptoms to figure out what people have.

For example, based on symptoms of the nibling who passed on germs to Scott around Thanksgiving, and Scott’s symptoms (instant, incredible chest cough but no runny nose, sore throat, fever, or aches) we had ultimately guessed that Scott had RSV. We then knew that the biggest risk was either droplets from coughing (especially because the volume of coughing), which could be reduced drastically by masking, or aerosols, which again would be helped by his masking and also ventilation, and in closed spaces, two-way masking (me masking).

For the Christmas germs, everyone seemed to have mild symptoms with congestion, runny noses, some coughs. But no fevers or aches and it seemed less severe. Given our recent experience with RSV, we narrowed it down to likely being a cold (rhinovirus), given again everyone testing repeatedly negative for COVID.

Given that, we knew the risk was going to be highest for us from droplets and fomites. So we again masked in shared spaces; Scott went to sleep in the guest bedroom as soon as he started getting symptoms; and we both did a lot of hand washing. Scott washed his hands before touching any of my things and regularly wiped down the kitchen. I tried not to go in the kitchen much (our main overlapping shared space), but also wash my hands after any time that I did. He didn’t have much of a cough and it was more controlled, so he would hold his cough until he could cover it with a mask or be in the room by himself. We also did our usual running of purifiers and opened windows and ran fans to increase ventilation to keep CO2 low.

And again? It worked. I did not get the cold, either from any of the ~8+ folks who did across the holiday period, or from Scott. Scott’s vitals all returned to normal at the five day mark, although we continued to mask in the car through day 7, to be more cautious (due to my personal situation).

So, infection is not inevitable, even in small houses and apartments.

Here’s what we’ve taken away from these experiences with more aerosol-based (RSV) transmission diseases and more droplet and fomite-based (cold) experiences:

  1. Two-way N95 masking works. Mask in the car, run the fan, keep the windows cracked, run purifiers at home, and ventilate spaces, but you still want two-way masking when something is aerosolized and you’re in the same spaces. This can prevent transmission.
  2. Keep distance when someone is coughing and sneezing (and if they have a cough or sneeze type illness, you want 6 foot distance even when they’re not actively coughing or sneezing, because they make droplets just from breathing and talking). The person who’s coughing and sneezing should mask, even inside, unless they are in their own room in private (and it’s not a shared room).Keep your air ventilated (if you haven’t, read my post about ventilation and using a Co2 monitor)Depending on the illness, to fully protect yourself you’ll need to commit to wearing a mask at all times indoors to protect yourself if the person who is sick is not masking. (Eg, Scott got a cold while mostly masked around heavily coughing niblings, but not throughout the whole house the whole day). With adults, the adults who are sick should definitely mask if they’re in shared spaces with other adults. (It’s harder with kids, and it should be a conversation depending on the age of the kids about them masking in shared spaces, such as if they want to play with Uncle Scott, or help them understand that someone may not want to play up close if they’re sick and coughing and not willing to mask. That’s fine, but that’s a choice they can make when kids are old enough to understand.)
  3. Have the infected person sleep in a different space (on the couch or in another room if you have a spare bedroom). If you have to share a room, both should mask.
  4. Use cleaning wipes to wipe down shared surfaces (e.g. fridge handles, microwave, counters, bathroom surfaces like the flush on the toilet or sink faucet, etc) and wash your hands after using these shared spaces every time. Fomites can last longer than you’d expect.
  5. Use metrics from your wearable devices (eg Apple Watch or Oura ring or similar) to track when your temperature, respiratory rate, heart rate, cough rate, etc. return to normal. That tied with symptom elimination can help you determine how long you’re likely most infectious for. The general estimates of contagiousness for each condition generally seem to be right (e.g., two weeks for an adult with RSV and 5-7 days for a cold) in our recent experiences. I would continue precautions for at least those minimum time frames, if you can.
  6. Yes, there’s a cost to these precautions, in terms of human contact. There was no hugging or hand holding or kissing or any touch contact during these time periods. I felt pretty lonely, especially because it was me we were trying to protect (because I am at high risk for bad outcomes due to immunosuppression right now), and I’m sure Scott also felt lonely and isolated. That part sucked, but we at least knew it was a fixed period of time, which helped.

What we’d do differently next time

Infection is not inevitable -how to reduce transmission of illness in your household (including COVID-19, RSV, flu, and the common cold), written by Dana M. Lewis from DIYPS.orgThis basically has been our plan for if either of us were to get COVID-19 (or the flu), and it’s good to know this plan works for a variety of conditions including RSV and the common cold. The main thing we would do differently in the future is that Scott should have masked the very first night he had symptoms of RSV, and he has decided that he’ll be masking any time he’s in the same room as someone who’s been coughing, as that’s considerably less annoying than being sick. (He really did not like the experience of having RSV.) I obviously did not get it from that first night when he first had the most minor symptoms of RSV, but that was probably the period of highest risk of transmission of either week, given the subsequent precautions we took after that.

Combined, everything we did worked, and we’ll do it again when we need to in the future, which should not be very often. We went five full years without either of us getting any type of infection (yay), and hopefully that continues from here on out. We’ll also continue to get regular COVID-19 boosters; annual flu shots; and other annual shots if/when they become available (e.g. when we reach the age, getting the RSV vaccine).

Remember, if you’re reading this in January 2025, RSV and flu levels are very high in the US right now, with COVID-19 expected to pick up again soon. It’s not too late to get your boosters and given the rates of respiratory illness, consider situational masking even if you don’t typically mask.

When Life Pelts You with Lemons

“When life gives you lemons, make lemonade.”

A friendly raccoon holds a baseball bat at home plate, while a lemon comes out of a pitching machine. There are a few lemons on the ground nearby. It sounds nice. Hopeful. Productive. It implies the lemons are gently handed to you. They’re probably clean, ripe, and maybe sitting in a cute little basket. Like life’s just giving you a quirky unexpected opportunity.

But sometimes? Life doesn’t hand you lemons, or give you a bat to gently bat them when they’re pitched your way.

It hurls them.

Fast. Hard. Repeatedly.

And instead of ingredients, they feel more like projectiles.

You’re not inspired. You’re bruised. You didn’t ask for this. And you don’t want them.

Lemonade pressure

Especially in the context of chronic illness, there’s often an unspoken expectation:

  • That once you get through the shock of diagnosis, you’ll spin it into something meaningful.
  • That you’ll have a story of triumph.
  • That you’ll make… lemonade.

The raccoon is at home plate wearing protective gear like a catcher, watching as a lemon is hurled from the pitching machine. And sometimes people do. That’s valid. Sometimes I’ve done that.

But other times? You’re just trying to survive the experience.

And that’s valid, too.

But. 

Not every moment of suffering has to become a productivity project or a beautiful narrative arc. There might eventually be a nice narrative arc, but it’s really hard when there’s not one, even if there will eventually be one.

Sometimes, things just hurt. And it’s not always possible to fix it or make it better (for yourself or anyone who follows). That makes it even harder, on top of an already hard situation.

So it’s important to remind yourself, no matter what you are going through:

You’re not obligated to make your suffering palatable to others. You don’t have to polish it up, find a silver lining, or fix an unfixable thing.

You can just exist and survive. That’s enough. It’s not a failure.

Sometimes, the most honest response to being pelted with lemons is to let them fall.

Let them sit there. Let them rot.

You’re not lazy. You’re not ungrateful. You’re human. (You’re a sail, not an anchor.)

What’s the alternative when you get pelted?

The raccoon is walking away, we see lemons on the ground but the raccoon isn't trying to catch or bat them. Forget the default script. There’s no “right” way to respond.

  • Maybe you’ll do something with those lemons later.
  • Maybe you never will.
  • Maybe someone else will pick them up.

You don’t have to choose right now, and even if you do choose, you don’t have to stick with that choice forever.

You don’t owe lemonade to anyone. Not to yourself, not to society, not to your past or future self.

Maybe you grieve. Maybe you rest. Maybe you rage. Maybe you do nothing.

And maybe, just maybe, that’s exactly what you’re supposed to do right now.