Vinay, This is my area of expertise on which I have been publishing since the very first article on Medical Informatics I wrote for Science many decades ago. ChatGPT, on which I have pretty deep experience, is a language engine, not an all-knowing "artificial intelligence". As you play with it more, you will discover that we have yet to achieve "artificial stupidity"....and it is a long slog from there to anything "intelligent".
I am shocked to see you endorsing "cookbook medicine" as the better default for the future. Without an ontologic understanding of what is happening with each patient, ONE BY ONE, there can be words that sound good but that will likely be wrong. None of that is today possible (or even being pursued) in large language engines. The cookbook will be often wrong in unpredictable ways. I know that the government (witness the cookbook response to covid) would love this kind of health care...but it is wrong on every level.
Half a century ago there was a program called Eliza that, similarly (but much more simply) did psychiatric interviews with users. It was very persuasive (and people would interact with it for hours) but, in actuality, had nothing to contribute. Perhaps large language engines may facilitate writing notes and replace scribes...I agree that much medical documentation is nonsense. But the leap to "doctoring" and the default that doctors will just be dumber (yes, happening now but that is LCME's fault and the failure of schools like UCSF (and mine) to push back) but cookbook language processing will take over is a leap way too far.
“This point has been made by others, but the deeper point I want to make is just how silly it is we spend so much time documenting. This is largely done for billing purposes, and these documents are mostly read by no one. This entire billing system needs reformation.”
This is so true. Imagine if lawyers had to document this thoroughly for every hour they bill us, or if your mechanic had to write a paragraph justifying each oil change… it’s just insane and I can’t believe this is real life
agencies that promulgate medical guidelines in the United States, Canada and Europe that do not received pharmaceutical funding
answer from Chat gpt:
There are several agencies that promulgate medical guidelines in the United States, Canada, and Europe that do not receive pharmaceutical funding. These agencies include:
United States:
American Diabetes Association (ADA)
American College of Cardiology/American Heart Association (ACC/AHA)
National Institutes of Health (NIH)
Centers for Disease Control and Prevention (CDC)
US Preventive Services Task Force (USPSTF)
Canada:
Canadian Diabetes Association
Canadian Cardiovascular Society
Canadian Agency for Drugs and Technologies in Health
Europe:
European Association for the Study of Diabetes (EASD)
European Society of Cardiology (ESC)
European Medicines Agency (EMA)
National Institute for Health and Care Excellence (NICE)
These agencies are non-profit organizations or government entities that are dedicated to promoting evidence-based medicine and providing guidance for healthcare professionals. They may receive funding from other sources, such as government grants or donations from private foundations, but they do not receive funding from pharmaceutical companies.
It's important to note that while these agencies strive to provide unbiased and independent guidance, they may still have conflicts of interest or be influenced by other factors. Patients and healthcare professionals should always carefully evaluate the evidence and consider multiple sources of guidance when making healthcare decisions.
Then asked this:
tell mee about conflicts of interest for American Diabetes Association and pharmaceutical companies
Chat GPT answer:
The American Diabetes Association (ADA) is a non-profit organization that is dedicated to the prevention and treatment of diabetes. Like many medical organizations, the ADA receives funding from a variety of sources, including pharmaceutical companies. This funding can be in the form of grants, donations, or sponsorship of events.
While the ADA states that it takes steps to ensure that its relationships with industry partners do not compromise its integrity or independence, there have been concerns about conflicts of interest between the organization and pharmaceutical companies.
For example, a 2016 analysis published in JAMA Internal Medicine found that between 2011 and 2014, the ADA received more than $29 million in funding from pharmaceutical companies. The analysis also found that 22% of the ADA's top leaders had financial ties to pharmaceutical companies.
This has led to concerns that the ADA's recommendations and guidelines may be influenced by the pharmaceutical industry, potentially leading to biased recommendations that prioritize the use of certain medications over others. However, the ADA has stated that its relationships with industry partners do not influence its recommendations or guidelines.
To address concerns about conflicts of interest, the ADA has taken steps to increase transparency and accountability. For example, the organization now requires that its leaders disclose any financial relationships with industry partners, and it has implemented policies to limit the influence of industry on its activities and decision-making processes.
Overall, while conflicts of interest between the ADA and pharmaceutical companies may exist, the organization has taken steps to mitigate these conflicts and to ensure that its recommendations and guidelines are evidence-based and independent.
Good article and good speculation, VP. AI will change medicine and just about every other field. At issue is basic human ignorance. Unlimited application of AI like Chat GPT will kill millions. It can disrupt economies and be weaponized. It has some good things going for it that will save time and money. But unlimited use of it, or even frequent use of it will be used (through greed and failure to comprehend) for all manner of gaslighting, deception, psyops, and destruction of truly human processes.
Vinay. You are a solid dude but you are super impressed by superficial hype. Teslas, Elon Musk, ChatGPT. This is hype -- it's nothing other than an example of how easily fooled people are. Yawn. Just wait, you'll see what I mean.
ChatGPT will help the mediocre have an easier time being mediocre. Those how want to excel, want to create, want to inspire, want their reach to exceed their grasp will not choose Chat GPT, as they understand Chat GPT can mimic, but not produce these all too human qualities.
It is because of the major impact on clinical practice that organized medicine and doctors in general will get it banned, or severely regulated and curtailed. Elon Musk and Steve Wozniak have just come out for a temporary moratorium on further development of AI. It's that big of a threat in non-medical fields. If allowed to progress too far too fast, it may be too late to ban or regulate it.
Medical writing is so obtuse and ponderous that Chat GPT will easily supersede. It is incumbent upon writers to learn how to think and write more clearly. Otherwise AI takes over.
Same in common journalism. So much of today's journalism fails the basic test of who, what, when, why, and where? Don't make it a guessing game or click bait. That is where GPT will take over.
It's learning medicine from you and other fellow doctors. There is one issue: the latest medical journals and discoveries are not available to the Chat engine, either with copyright issues or behind a pay wall. It can't know or respond to the latest literature since that part of the Internet is off limits. I think Chat will speed up many aspects of our lives, but it won't necessarily replace them.
great read. As a Respiratory Therapist, I asked GPT 4 why we place neo's on PC-CMV mode for non invasive ventilation instead of AC. It told me that CMV and AC were the same mode. I then provided sources to correct this error, and it was able to learn and regurgitate the newly formulated information. creepy, but cool.
Have you tried GPT -4? It expands future applications in medical practice.In short order one will be able literally speak to it- rapidly eliminating many job positions and EHR’s.
Key is training of physicians and mid levels in its use. I am developing a training program for FQHC’s which are typically behind in everything. As AI is adapted in practice situations, those who do not adapt will quickly be left behind. FQHC quality of care leaves much to be desired already. Rapid utilization of AI in practice will yet further widen the quality gap- yet further leaving the underserved with nth rate care.
The ChatGPT apocalypse.... not worried. Actual intelligence is a long way off for machine learning.
How many honest, trustworthy assessments of the Covid pandemic and vaccine landscape could ChatGPT actually navigate? I know that I have struggled with all of the "official" misinformation and have learned (through my intelligence) to depend on experts like you, Dr. Prasad... and Dr. Makary and Monica Ghandi and Jay Bhattacharya... but Chat GPT would never recognize the nuances.
Vinay, you are my guy, but this essay disappointed me. I am not a data/statistics nerd like you and you fill this gap in my capabilities. Since you came onto my radar, I have followed you faithfully through the entire Covid pandemic along with others of your ilk, such as Zubin Damania, Marty Makary, Monica Gupta, Scott Atlas, John Iaoniddis, Martin Kuldorff, and Jay Battacharya. You all gave me hope that there were still independent and critically thinking physicians out there pushing back against the groupthink of our bureaucratic public health "experts". I read your essay with dismay, however, and not a little alarm. The picture you painted, intentionally or not, was so dystopic that I had a hard time believing anyone would think this without serious angst at the potential destruction of all that is human and humane in medicine. If there is one common thread in nearly all of the modern progress of medicine it has been an erosion of the most important and sacred thing about it: the doctor/patient relationship. This is built on a foundation of competence, trust, and shared humanity. Dare I say there is also a very real spiritual component to it whether one is a theist, agnostic, or atheist. There is much more to medicine than simple data mining from electronic medical records then parsing this into a plan of treatment according to pre-established algorithms. Like the attending mentioned in one of the earlier comments, after 45 years as a physician, I can walk into a room with a new patient and quickly ascertain a number of important things without much more than a quick glance. Age, sex, race, ethnicity, body habitus, body language, eye contact, demeanor, voice inflection, facial expressions, and more are quickly synthesized into a picture that is then filled in and adjusted based on taking a history and performing an examination. As I learned in medical school, and which as been proven countless times in my own experience, nine times out of ten, the diagnosis can be made by the history and interview alone. All else is just confirmatory. I would strongly recommend you read the book, Mortal Lessons- Notes on the Art of Surgery, by Richard Selzer, if you can find it. Last copyright was 1976 and my copy is falling apart. If you can put your hands on a copy, go to the chapter, The Surgeon as Priest, and read pages 33-36. No AI, ChatGPT, or any other electronic/virtual manner of medical practice will ever come remotely close to approaching, much less surpassing this as an example of the highest level of medical practice. If we lose that to a computer algorithm, we are sunk. Warm regards and keep up the good work. Rick
Vinay: Respectfully, if your team produces 200 articles per annum, who's gonna read them?
Another chatGPT instance which will inevitably end up producing readers digest, condensed summaries. We already produce way faster than we can consume.
Written by chatGPT, read by chatGPT seems like a weird way to go about things.
Vinay, This is my area of expertise on which I have been publishing since the very first article on Medical Informatics I wrote for Science many decades ago. ChatGPT, on which I have pretty deep experience, is a language engine, not an all-knowing "artificial intelligence". As you play with it more, you will discover that we have yet to achieve "artificial stupidity"....and it is a long slog from there to anything "intelligent".
I am shocked to see you endorsing "cookbook medicine" as the better default for the future. Without an ontologic understanding of what is happening with each patient, ONE BY ONE, there can be words that sound good but that will likely be wrong. None of that is today possible (or even being pursued) in large language engines. The cookbook will be often wrong in unpredictable ways. I know that the government (witness the cookbook response to covid) would love this kind of health care...but it is wrong on every level.
Half a century ago there was a program called Eliza that, similarly (but much more simply) did psychiatric interviews with users. It was very persuasive (and people would interact with it for hours) but, in actuality, had nothing to contribute. Perhaps large language engines may facilitate writing notes and replace scribes...I agree that much medical documentation is nonsense. But the leap to "doctoring" and the default that doctors will just be dumber (yes, happening now but that is LCME's fault and the failure of schools like UCSF (and mine) to push back) but cookbook language processing will take over is a leap way too far.
“This point has been made by others, but the deeper point I want to make is just how silly it is we spend so much time documenting. This is largely done for billing purposes, and these documents are mostly read by no one. This entire billing system needs reformation.”
This is so true. Imagine if lawyers had to document this thoroughly for every hour they bill us, or if your mechanic had to write a paragraph justifying each oil change… it’s just insane and I can’t believe this is real life
I asked this:
agencies that promulgate medical guidelines in the United States, Canada and Europe that do not received pharmaceutical funding
answer from Chat gpt:
There are several agencies that promulgate medical guidelines in the United States, Canada, and Europe that do not receive pharmaceutical funding. These agencies include:
United States:
American Diabetes Association (ADA)
American College of Cardiology/American Heart Association (ACC/AHA)
National Institutes of Health (NIH)
Centers for Disease Control and Prevention (CDC)
US Preventive Services Task Force (USPSTF)
Canada:
Canadian Diabetes Association
Canadian Cardiovascular Society
Canadian Agency for Drugs and Technologies in Health
Europe:
European Association for the Study of Diabetes (EASD)
European Society of Cardiology (ESC)
European Medicines Agency (EMA)
National Institute for Health and Care Excellence (NICE)
Scottish Intercollegiate Guidelines Network (SIGN)
These agencies are non-profit organizations or government entities that are dedicated to promoting evidence-based medicine and providing guidance for healthcare professionals. They may receive funding from other sources, such as government grants or donations from private foundations, but they do not receive funding from pharmaceutical companies.
It's important to note that while these agencies strive to provide unbiased and independent guidance, they may still have conflicts of interest or be influenced by other factors. Patients and healthcare professionals should always carefully evaluate the evidence and consider multiple sources of guidance when making healthcare decisions.
Then asked this:
tell mee about conflicts of interest for American Diabetes Association and pharmaceutical companies
Chat GPT answer:
The American Diabetes Association (ADA) is a non-profit organization that is dedicated to the prevention and treatment of diabetes. Like many medical organizations, the ADA receives funding from a variety of sources, including pharmaceutical companies. This funding can be in the form of grants, donations, or sponsorship of events.
While the ADA states that it takes steps to ensure that its relationships with industry partners do not compromise its integrity or independence, there have been concerns about conflicts of interest between the organization and pharmaceutical companies.
For example, a 2016 analysis published in JAMA Internal Medicine found that between 2011 and 2014, the ADA received more than $29 million in funding from pharmaceutical companies. The analysis also found that 22% of the ADA's top leaders had financial ties to pharmaceutical companies.
This has led to concerns that the ADA's recommendations and guidelines may be influenced by the pharmaceutical industry, potentially leading to biased recommendations that prioritize the use of certain medications over others. However, the ADA has stated that its relationships with industry partners do not influence its recommendations or guidelines.
To address concerns about conflicts of interest, the ADA has taken steps to increase transparency and accountability. For example, the organization now requires that its leaders disclose any financial relationships with industry partners, and it has implemented policies to limit the influence of industry on its activities and decision-making processes.
Overall, while conflicts of interest between the ADA and pharmaceutical companies may exist, the organization has taken steps to mitigate these conflicts and to ensure that its recommendations and guidelines are evidence-based and independent.
Good article and good speculation, VP. AI will change medicine and just about every other field. At issue is basic human ignorance. Unlimited application of AI like Chat GPT will kill millions. It can disrupt economies and be weaponized. It has some good things going for it that will save time and money. But unlimited use of it, or even frequent use of it will be used (through greed and failure to comprehend) for all manner of gaslighting, deception, psyops, and destruction of truly human processes.
"We'll see", said the wise man.
Vinay. You are a solid dude but you are super impressed by superficial hype. Teslas, Elon Musk, ChatGPT. This is hype -- it's nothing other than an example of how easily fooled people are. Yawn. Just wait, you'll see what I mean.
ChatGPT will help the mediocre have an easier time being mediocre. Those how want to excel, want to create, want to inspire, want their reach to exceed their grasp will not choose Chat GPT, as they understand Chat GPT can mimic, but not produce these all too human qualities.
It is because of the major impact on clinical practice that organized medicine and doctors in general will get it banned, or severely regulated and curtailed. Elon Musk and Steve Wozniak have just come out for a temporary moratorium on further development of AI. It's that big of a threat in non-medical fields. If allowed to progress too far too fast, it may be too late to ban or regulate it.
Medical writing is so obtuse and ponderous that Chat GPT will easily supersede. It is incumbent upon writers to learn how to think and write more clearly. Otherwise AI takes over.
Same in common journalism. So much of today's journalism fails the basic test of who, what, when, why, and where? Don't make it a guessing game or click bait. That is where GPT will take over.
It's learning medicine from you and other fellow doctors. There is one issue: the latest medical journals and discoveries are not available to the Chat engine, either with copyright issues or behind a pay wall. It can't know or respond to the latest literature since that part of the Internet is off limits. I think Chat will speed up many aspects of our lives, but it won't necessarily replace them.
Will be wonderful when you allow Chat GPT to finally proofread your articles.
great read. As a Respiratory Therapist, I asked GPT 4 why we place neo's on PC-CMV mode for non invasive ventilation instead of AC. It told me that CMV and AC were the same mode. I then provided sources to correct this error, and it was able to learn and regurgitate the newly formulated information. creepy, but cool.
Have you tried GPT -4? It expands future applications in medical practice.In short order one will be able literally speak to it- rapidly eliminating many job positions and EHR’s.
Key is training of physicians and mid levels in its use. I am developing a training program for FQHC’s which are typically behind in everything. As AI is adapted in practice situations, those who do not adapt will quickly be left behind. FQHC quality of care leaves much to be desired already. Rapid utilization of AI in practice will yet further widen the quality gap- yet further leaving the underserved with nth rate care.
Two words: "stochastic parrots"
The ChatGPT apocalypse.... not worried. Actual intelligence is a long way off for machine learning.
How many honest, trustworthy assessments of the Covid pandemic and vaccine landscape could ChatGPT actually navigate? I know that I have struggled with all of the "official" misinformation and have learned (through my intelligence) to depend on experts like you, Dr. Prasad... and Dr. Makary and Monica Ghandi and Jay Bhattacharya... but Chat GPT would never recognize the nuances.
Vinay, you are my guy, but this essay disappointed me. I am not a data/statistics nerd like you and you fill this gap in my capabilities. Since you came onto my radar, I have followed you faithfully through the entire Covid pandemic along with others of your ilk, such as Zubin Damania, Marty Makary, Monica Gupta, Scott Atlas, John Iaoniddis, Martin Kuldorff, and Jay Battacharya. You all gave me hope that there were still independent and critically thinking physicians out there pushing back against the groupthink of our bureaucratic public health "experts". I read your essay with dismay, however, and not a little alarm. The picture you painted, intentionally or not, was so dystopic that I had a hard time believing anyone would think this without serious angst at the potential destruction of all that is human and humane in medicine. If there is one common thread in nearly all of the modern progress of medicine it has been an erosion of the most important and sacred thing about it: the doctor/patient relationship. This is built on a foundation of competence, trust, and shared humanity. Dare I say there is also a very real spiritual component to it whether one is a theist, agnostic, or atheist. There is much more to medicine than simple data mining from electronic medical records then parsing this into a plan of treatment according to pre-established algorithms. Like the attending mentioned in one of the earlier comments, after 45 years as a physician, I can walk into a room with a new patient and quickly ascertain a number of important things without much more than a quick glance. Age, sex, race, ethnicity, body habitus, body language, eye contact, demeanor, voice inflection, facial expressions, and more are quickly synthesized into a picture that is then filled in and adjusted based on taking a history and performing an examination. As I learned in medical school, and which as been proven countless times in my own experience, nine times out of ten, the diagnosis can be made by the history and interview alone. All else is just confirmatory. I would strongly recommend you read the book, Mortal Lessons- Notes on the Art of Surgery, by Richard Selzer, if you can find it. Last copyright was 1976 and my copy is falling apart. If you can put your hands on a copy, go to the chapter, The Surgeon as Priest, and read pages 33-36. No AI, ChatGPT, or any other electronic/virtual manner of medical practice will ever come remotely close to approaching, much less surpassing this as an example of the highest level of medical practice. If we lose that to a computer algorithm, we are sunk. Warm regards and keep up the good work. Rick
PS- also written by me........................
Vinay: Respectfully, if your team produces 200 articles per annum, who's gonna read them?
Another chatGPT instance which will inevitably end up producing readers digest, condensed summaries. We already produce way faster than we can consume.
Written by chatGPT, read by chatGPT seems like a weird way to go about things.