AI Tech for the ER

This forum made possible through the generous support of SDN members, donors, and sponsors. Thank you.

thegenius

Senior Wharf Rat
Lifetime Donor
20+ Year Member
Joined
Jul 12, 2004
Messages
5,520
Reaction score
5,234
I don't think we have a dedicated threat about this.

How are people's experiences using AI apps for generating ER notes. I generally think they are kind of crappy, in that they are extraordinarily verbose. Even in the "concise" mode. Anyone happy with a particular app?

I've tried Abridge and Speke

Here is a Speke MDM, compared to mine

Speke:
The patient, a female with a history of hysterectomy, presented with hematuria, fatigue, nausea, and persistent abdominal pain. She reported episodes of red urine and significant fatigue, nausea, and abdominal pain that have persisted. The initial differential diagnosis included urinary tract infection, nephrolithiasis, and hepatobiliary pathology. The patient denied any history of bladder infections or UTIs and reported no pain during urination. She is on medications including insulin, dapagliflozin, and metformin for diabetes management.

An abdominal ultrasound was performed, revealing acute cholecystitis with a normal common bile duct. Laboratory tests showed elevated liver enzymes (ALT 804 IU/L, AST 156 IU/L, Alk Phos 209 IU/L), elevated bilirubin levels (Total 1.8 mg/dL, Direct 0.90 mg/dL), and a low albumin level (3.3 Gm/dl). The patient's sodium level was slightly low at 135 mEq/L, and CO2 was low at 19.0 mEq/L. The patient's hemoglobin and hematocrit were elevated (Hgb 16.4 Gm/dl, Hct 48.6%). The patient's glucose level was normal at 94 mg/dL.

The treatment plan included initiating IV fluids and administering antiemetic medication for nausea. The patient was advised to follow up with a gastroenterologist for further evaluation and management of acute cholecystitis. Given the elevated liver enzymes and bilirubin, further hepatobiliary imaging and possible surgical consultation may be warranted. The patient was instructed to monitor her symptoms and return to the ED if her condition worsens.


Mine (that I put in the same note):

referred for RUQ abd pain, workup shows cholecystitis. d/w surgery and will admit..



So not only is the AI generated MDM incredibly verbose and 90% useless, it didn't even get it correct. I didn't discharge her. I admitted the patient. Who in the world wants to read these AI notes?

The problem is, as I see it, are the software engineers who write these apps are not doctors. Even if they have doctors consulting, the end product is just way too lengthy.
 
Only Chuds use these things.

Modern Slang Usage:

  • "Chud" is primarily a derogatory slang term used online, especially in U.S. internet culture, to describe people perceived as unpleasant, gross, or socially abnormal235.
  • More specifically, it is often used to insult individuals—usually men—who hold reactionary, regressive, or bigoted sociopolitical views, particularly those associated with the far right or "manosphere" communities1357.
  • The term is frequently deployed by critics on the political left to mock or dismiss individuals they see as embodying toxic or extremist attitudes, often combining accusations of racism, sexism, conspiracy theorizing, and a sense of superiority


you must be particularly spicy today, Dr. RF.
 
I don't think we have a dedicated threat about this.

How are people's experiences using AI apps for generating ER notes. I generally think they are kind of crappy, in that they are extraordinarily verbose. Even in the "concise" mode. Anyone happy with a particular app?

I've tried Abridge and Speke

Here is a Speke MDM, compared to mine

Speke:
The patient, a female with a history of hysterectomy, presented with hematuria, fatigue, nausea, and persistent abdominal pain. She reported episodes of red urine and significant fatigue, nausea, and abdominal pain that have persisted. The initial differential diagnosis included urinary tract infection, nephrolithiasis, and hepatobiliary pathology. The patient denied any history of bladder infections or UTIs and reported no pain during urination. She is on medications including insulin, dapagliflozin, and metformin for diabetes management.

An abdominal ultrasound was performed, revealing acute cholecystitis with a normal common bile duct. Laboratory tests showed elevated liver enzymes (ALT 804 IU/L, AST 156 IU/L, Alk Phos 209 IU/L), elevated bilirubin levels (Total 1.8 mg/dL, Direct 0.90 mg/dL), and a low albumin level (3.3 Gm/dl). The patient's sodium level was slightly low at 135 mEq/L, and CO2 was low at 19.0 mEq/L. The patient's hemoglobin and hematocrit were elevated (Hgb 16.4 Gm/dl, Hct 48.6%). The patient's glucose level was normal at 94 mg/dL.

The treatment plan included initiating IV fluids and administering antiemetic medication for nausea. The patient was advised to follow up with a gastroenterologist for further evaluation and management of acute cholecystitis. Given the elevated liver enzymes and bilirubin, further hepatobiliary imaging and possible surgical consultation may be warranted. The patient was instructed to monitor her symptoms and return to the ED if her condition worsens.


Mine (that I put in the same note):

referred for RUQ abd pain, workup shows cholecystitis. d/w surgery and will admit..



So not only is the AI generated MDM incredibly verbose and 90% useless, it didn't even get it correct. I didn't discharge her. I admitted the patient. Who in the world wants to read these AI notes?

The problem is, as I see it, are the software engineers who write these apps are not doctors. Even if they have doctors consulting, the end product is just way too lengthy.
I just want the bare minimum documentation to bill for the work I did. Until a robot does that, I'm not touching it.
 
I kind of feel that way. EIther the AI bot should
- significantly reduce time creating AND editing a note;
- increase average RVU/note
- reduce medmal liability risk

or it's not worth using.

Another problem is these AI bots are generally made for linear encounters. You see one pt, leave the room and that's it. ED is the exact opposite.
 
Modern Slang Usage:

  • "Chud" is primarily a derogatory slang term used online, especially in U.S. internet culture, to describe people perceived as unpleasant, gross, or socially abnormal235.
  • More specifically, it is often used to insult individuals—usually men—who hold reactionary, regressive, or bigoted sociopolitical views, particularly those associated with the far right or "manosphere" communities1357.
  • The term is frequently deployed by critics on the political left to mock or dismiss individuals they see as embodying toxic or extremist attitudes, often combining accusations of racism, sexism, conspiracy theorizing, and a sense of superiority


you must be particularly spicy today, Dr. RF.

What I'm really going for here are the chronically online types (Chuds) regardless of politics (because it's all theater now anyways, but that's a different rant) who want a bot or an app to do everything for them.

Taking pride in masculine self reliance and a DIY-ethos with accountability needs to come back.
 
Last edited:
The 2 I have tried and liked are Sayvant which has an MDM / med mal piece which I will admit I havent used but did see demoed and Time by Dr.H who is an EM doc. Both can be customized to your specific needs

They can all be trained on EM billing standards. I think the issue with off the shelf stuff is that it is really all made for clinics and not ED encounters. AFAIK both of these are made for EM and are trying to now make more generalizable versions for the masses.
 
I’ve played with Heidi and I think it has a role as a scribe replacement. It will listen to the HPI and output a reasonable text version, and can be coached into variations in form, brevity, etc

My main issue is 1/3 of patients have such quick HPI that I don’t want to futz with an AI scribe app (i twisted my ankle on the stairs), and 1/3 of patients are so altered, demented, or involve complex interpreter scenarios that I don’t think the AI app will have anything to do.

It worked great when I went in a room with a complex undifferentiated intelligent older woman with her involved daughter who brought a copy of her out of state recent hospitalization records and could rapidly answer every question I had about her complex recent health issues.

I don’t see a lot of those patients per shift.
 
I’ve played with Heidi and I think it has a role as a scribe replacement. It will listen to the HPI and output a reasonable text version, and can be coached into variations in form, brevity, etc

My main issue is 1/3 of patients have such quick HPI that I don’t want to futz with an AI scribe app (i twisted my ankle on the stairs), and 1/3 of patients are so altered, demented, or involve complex interpreter scenarios that I don’t think the AI app will have anything to do.

It worked great when I went in a room with a complex undifferentiated intelligent older woman with her involved daughter who brought a copy of her out of state recent hospitalization records and could rapidly answer every question I had about her complex recent health issues.

I don’t see a lot of those patients per shift.
I use an AI scribe in a clinic setting and this is the exact scenario where I find it helpful. Most of the rest of the time it just lets me not sit there typing in the room.
 
From what I’ve heard from others it doesn’t seem like most AI products are quite good enough yet for charting, but I think it will get there. AI needs to integrate with the EMR. I think Epic and Cerner will do that. We waste so much time typing and dictating. I think AI is the answer to this and will completely replace dictating sometime in the next 5-10 years. Not sure how I feel about a significant change mid career, but it can’t be worse. At least I hope, or I might be end career.
 
From what I’ve heard from others it doesn’t seem like most AI products are quite good enough yet for charting, but I think it will get there. AI needs to integrate with the EMR. I think Epic and Cerner will do that. We waste so much time typing and dictating. I think AI is the answer to this and will completely replace dictating sometime in the next 5-10 years. Not sure how I feel about a significant change mid career, but it can’t be worse. At least I hope, or I might be end career.
Politely disagree; we can dissect it out if you want. Later, though.
 
If AI wrote down everything that the patient and I discussed, every patient would be CBC/CMP/UA/PT/INR/Mg/Lactic/Culturesx2/Lipase/TSH/Trop/BNP/UDS/Tylenol level/Aspirin level/ETOH/Osmol/ABG/VBG/EKG/Chest X-ray/CT head/MRI brain/CT c-spine/CTA chest/CT abdomen-pelvis/US gallbladder/US DVT both extremities/MRI lumbar spine/Vitamin B level/Iron panel/PTH/FSH/Strep/Covid/Flu/RSV (all ages)/Ddimer

+/- preg test (even if age 85)

The patients have no filter and AI certainly cannot filter the patient. It takes me 3-5 mins to see the average patient, and 2-3 mins to document. Why do I need AI?
 
If AI wrote down everything that the patient and I discussed, every patient would be CBC/CMP/UA/PT/INR/Mg/Lactic/Culturesx2/Lipase/TSH/Trop/BNP/UDS/Tylenol level/Aspirin level/ETOH/Osmol/ABG/VBG/EKG/Chest X-ray/CT head/MRI brain/CT c-spine/CTA chest/CT abdomen-pelvis/US gallbladder/US DVT both extremities/MRI lumbar spine/Vitamin B level/Iron panel/PTH/FSH/Strep/Covid/Flu/RSV (all ages)/Ddimer

+/- preg test (even if age 85)

The patients have no filter and AI certainly cannot filter the patient. It takes me 3-5 mins to see the average patient, and 2-3 mins to document. Why do I need AI?
Think of it this way: once you see a full department, the AI driven workups will take 12+ hours each, you can write your notes and go to lunch.
 
The error is thinking that AI can’t encounter a million patients and equate those with the end results filtering out the noise.
 
The error is thinking that AI can’t encounter a million patients and equate those with the end results filtering out the noise.

Will the lawyers let the AI filter out the noise?

Honest question.

Separate but related thought: We are flirting with every patient encounter with full audio and video backup forever.

Will AI be called to testify?

“The patient said she had chest pain. Why didn’t you put it in the note?”
 
If AI wrote down everything that the patient and I discussed, every patient would be CBC/CMP/UA/PT/INR/Mg/Lactic/Culturesx2/Lipase/TSH/Trop/BNP/UDS/Tylenol level/Aspirin level/ETOH/Osmol/ABG/VBG/EKG/Chest X-ray/CT head/MRI brain/CT c-spine/CTA chest/CT abdomen-pelvis/US gallbladder/US DVT both extremities/MRI lumbar spine/Vitamin B level/Iron panel/PTH/FSH/Strep/Covid/Flu/RSV (all ages)/Ddimer

+/- preg test (even if age 85)

The patients have no filter and AI certainly cannot filter the patient. It takes me 3-5 mins to see the average patient, and 2-3 mins to document. Why do I need AI?
I tend to agree. I think AI for physician charting is currently a solution looking for a problem. I can crank out a note on a patient in a few minutes. It's a note I feel comfortable with and defending in the event of a bad outcome on my decision making and thought process. I think I'd spend more time reading and editing an AI note other than me just doing it from the start. Now, you want AI to do some of the ridiculous nurse charting and questions they have to ask? Go for it.
 
The error is thinking that AI can’t encounter a million patients and equate those with the end results filtering out the noise.

This is one of the points I wanted to discuss. I don't think AI could filter thru the nonsense that patients say, especially if we "teach" it via the honest examples of HPIs written by a GOOD emergency physician.
 
I tend to agree. I think AI for physician charting is currently a solution looking for a problem.
I think we're basically looking at this problem very narrowly through our EM lens. The pajama-time primary care docs would rather quit that lose their scribes.

With good templates/smartphrases/smarttext/Dragon shortcuts/whathaveyou, EM docs are probably #1 in the world at maximizing per-patient efficiency of evaluation and documentation. An basic AI scribe doesn't have that much to add.

But, then, there are some shops that use human scribe services – yeah they do your note, but they also queue up orders, set up discharge paperwork, etc. The next generation of Epic/Cerner integrated scribe products will do a lot of that for you, just based on your conversation content, as well. Now we're getting somewhere – even if the note-writing speed/quality is a wash.

And, then, yeah, further versions will obviously allow docs more control over the style, format, and content of different sections – scribe companies need to do this to allow for all the various permutations of outpatient settings, so that'll trickle down back to the ED.

Eventually it'll be second-nature to us all, even if that day is not yet today.
 
I think we're basically looking at this problem very narrowly through our EM lens. The pajama-time primary care docs would rather quit that lose their scribes.

With good templates/smartphrases/smarttext/Dragon shortcuts/whathaveyou, EM docs are probably #1 in the world at maximizing per-patient efficiency of evaluation and documentation. An basic AI scribe doesn't have that much to add.

But, then, there are some shops that use human scribe services – yeah they do your note, but they also queue up orders, set up discharge paperwork, etc. The next generation of Epic/Cerner integrated scribe products will do a lot of that for you, just based on your conversation content, as well. Now we're getting somewhere – even if the note-writing speed/quality is a wash.

And, then, yeah, further versions will obviously allow docs more control over the style, format, and content of different sections – scribe companies need to do this to allow for all the various permutations of outpatient settings, so that'll trickle down back to the ED.

Eventually it'll be second-nature to us all, even if that day is not yet today.
Our scribes can barely write sentences, would rather misspell a consultants name than look it up, and forget to do most of the things I ask them to do. They also do not do any of those other things you mentioned. Some of my partners think we need to pay them more. I think we need to let them all go and move on with our lives.
 
I think AI will replace scribes. The bad ones are never worth it. The good ones leave for medical school or another better endeavor. They do help with other tasks (maybe their better use), but I also think there is room for some automation. I’ve never been a fan of using scribes.

Even only a few minutes charting per patient (say 2-3 minutes) adds up to around 30-60 minutes total of charting per shift. I’m skeptical and think most exaggerate how little time they spend charting, or it shows with a bare bones or completely templated note that doesn’t always help with billing, peer review/medmal or downstream patient care. On top of that, time spent clicking through the EMR repeatedly during a patient’s ED course adds even more uncounted time. We are highly efficient at multi tasking and optimizing time, yet we still spend a lot of time sitting at a computer documenting what someone else tells us and what we think along with other small tasks. This is an area ripe for improvement and a change will significantly increase job satisfaction for many. Again, I don’t think it’s fully developed yet, but I think it will be the future even if others don’t agree that it will be or see its potential benefit yet.
 
Our scribes can barely write sentences, would rather misspell a consultants name than look it up, and forget to do most of the things I ask them to do. They also do not do any of those other things you mentioned. Some of my partners think we need to pay them more. I think we need to let them all go and move on with our lives.

Who TF still has scribes?
 
Will the lawyers let the AI filter out the noise?

Honest question.

Separate but related thought: We are flirting with every patient encounter with full audio and video backup forever.

Will AI be called to testify?

“The patient said she had chest pain. Why didn’t you put it in the note?”

I have an FM friend who changed jobs recently. He took over a retiring doc's panel at this semi-corporate practice.

The new operation utilizes one of these AI scribes to generate the note automatically. He, like many of us here, thought it was clunky and didn't help much, but remained optimistic about its potential because he's a futurist and tech enthusiast.

A patient complained about him when he refused to continue a dangerous controlled substance regimen from the last doc, and recommended that they start tapering/weaning.

The result?

The MEDICAL director pulled up the FULL AI RECORDING of the visit for "QA purposes" to corroborate what my friend had told them, since it became a he-said-she-said kind of situation.

Scary.

I don't know why anybody would want to serve in a patient-facing role after an experience like that.

Get out of EM ASAP.
 
For real?
With how amazingly good dictation is; you guys still have scribes?

Hunh.

I cannot dictate a string of sentences without stopping and editing it. So dictating for me is slow.
Cerner is a terrible system and I cannot easily write a simple note, write simple patient instructions. It takes too long.
And, our hospital pays for scribes.

Henceforth, I use them.

I use Epic at Kaiser and it is quite easy for me to write a note in <= 4 minutes for about 50% of my encounters. This includes patient instructions.

TL;DR
- Cerner Sucks
- Hospital pay for scribes
- I rotate among a handful of them and they know how I work well.
- when we move to EPIC in a few years, I'll be writing my own notes most likely.
 
I cannot dictate a string of sentences without stopping and editing it. So dictating for me is slow.
Cerner is a terrible system and I cannot easily write a simple note, write simple patient instructions. It takes too long.
And, our hospital pays for scribes.

Henceforth, I use them.

I use Epic at Kaiser and it is quite easy for me to write a note in <= 4 minutes for about 50% of my encounters. This includes patient instructions.

TL;DR
- Cerner Sucks
- Hospital pay for scribes
- I rotate among a handful of them and they know how I work well.
- when we move to EPIC in a few years, I'll be writing my own notes most likely.

For as much as I kick and moan about MediTECH, the pDoc dictation system is T-O-P.
 
So a few things.. If you use the AI scribe product you have to control the data. I would NOT EVER use it if the hospital controlled any piece of it. The cost is fairly tiny.

We use one and we own the data, everything is erased. There is no audio recording and most of the AI scribe services also do not retain or record the audio. Instead it transcribes it in real time so as not to have any audio.

We have it set up whereby the hospital will never touch any of the product. If they want us to use their product that is integrated with cerner / epic and they own the info no one will use it.

I think you guys underestimate the power here. AI will be literally 100x better in 4 years. IMO it is passable right now. Imagine a world where it can siphon through a huge chart, get you the pertinent info, provide a differential and if you dont order something that might be useful it can suggest it for you. We are all very down on this due to the stupid pop ups we all have to deal with cause they are rudimentary and their triggers suck. But to think that the AI cant look through the note and past medical history and suggest you consider a spinal epidural abscess in a patient with back pain, fever, IVDA and you can click “nah fam” and then it will get you the MDM to medicolegally protect you.. that day isnt here but it is near. Look at how much money was invested in AI scribe companies.. it’s gigantic. VC and PE isnt dumb.. they see a major ROI. I can provide a list of other things it can help with.. its coming.. we dont all have to be early adopters but it is coming like a freight train one way or the other.
 
The main issue as i see it is its still clunky to carry my phone, it is still clunky to tell AI who the patient is.. i dont see a simple solution. The busier you are the more it makes sense to use it. You can train it to help with your billing.
 
I think you guys underestimate the power here. AI will be literally 100x better in 4 years. IMO it is passable right now. Imagine a world where it can siphon through a huge chart, get you the pertinent info, provide a differential and if you dont order something that might be useful it can suggest it for you. We are all very down on this due to the stupid pop ups we all have to deal with cause they are rudimentary and their triggers suck. But to think that the AI cant look through the note and past medical history and suggest you consider a spinal epidural abscess in a patient with back pain, fever, IVDA and you can click “nah fam” and then it will get you the MDM to medicolegally protect you.. that day isnt here but it is near. Look at how much money was invested in AI scribe companies.. it’s gigantic. VC and PE isnt dumb.. they see a major ROI. I can provide a list of other things it can help with.. its coming.. we dont all have to be early adopters but it is coming like a freight train one way or the other.

I don't think we do. As of right now it's nascent and not integrated into the EMR. And it's clunky. It doesn't speed me up right now. But yes it will at some point be excellent
 
I don't think we do. As of right now it's nascent and not integrated into the EMR. And it's clunky. It doesn't speed me up right now. But yes it will at some point be excellent

My argument here is once again: "the problem is the patient." They're so unreliable and ineffective that I think that they're the rate-limiter.

Keep in mind that I work in Gomerland.
 
I do agree it IS coming and a well integrated—
combination product with

(1) AI-transcriber (obvious scribe replacement)

(2) AI-chart searcher (patient has CP, please pull all ekg, cath, echos and cardiology notes from last 5yr across all linked EMR, display in a separate searchable window).

(3) AI MDM compiler, ddx assistant, decision support and discharge instruction maker (AI, low risk chest pain shared decision making MDM and discharge please— it would customize based on the workup, warn you if heart score >3, etc etc. It would cross reference the patients insurance and pharmacy to recommend actual covered drugs!)

(4) AI alerts that are NOT trash (eg alert me my antibiotic doesn’t match the last urine culture, warn me about sepsis without being wrong 95% of the time)

That would be amazing. And I suspect it’s coming.

However, using the current half baked products doesn’t necessarily speed the process or make me a happier doctor.
 
My argument here is once again: "the problem is the patient." They're so unreliable and ineffective that I think that they're the rate-limiter.

Keep in mind that I work in Gomerland.
You're not wrong about that part. Where I (and I'd guess most of the others here) think you are wrong is how quickly the tech will overcome that part. It's not happening tomorrow, but 3-4 years? I can see it.
 
You're not wrong about that part. Where I (and I'd guess most of the others here) think you are wrong is how quickly the tech will overcome that part. It's not happening tomorrow, but 3-4 years? I can see it.

I hear you, bro - and I agree that where people thing I'm wrong is that generalized patient dumba$$ery can be overcome by AI...

... but I don't see how AI can recognize what is nonsense at ALL. It's still just a transcription of an audio recording being analyzed.
 
AI will not edit. We all edit. Why do we edit? To paint a picture. AI will just write down word for word. Will we be able to edit it afterwards to tailor it a direction or will it ALL be in the medical record is the important question.

Last thing we need:

CC: right toe pain, patient says chronic cough in passing, nothing is done about the chronic cough because it is chronic and not the issue at hand, patient develops lung cancer 3 years from now, lawyers then hunt you down and ask “why was the chronic cough ignored?”
 
AI will not edit. We all edit. Why do we edit? To paint a picture. AI will just write down word for word. Will we be able to edit it afterwards to tailor it a direction or will it ALL be in the medical record is the important question.

Last thing we need:

CC: right toe pain, patient says chronic cough in passing, nothing is done about the chronic cough because it is chronic and not the issue at hand, patient develops lung cancer 3 years from now, lawyers then hunt you down and ask “why was the chronic cough ignored?”
I disagree here. It does a good job right now at editing out the nonsense. It’s not perfect for sure but reality is you and I could walk into a patient room and leave there with 2 different ideas of what they want / need. This is where your admin gets it wrong. They want all ED docs to be uniform in our practice pattern thats just not reality. Ai is no different. I do think AI will improve patient care, I think it will remove some of the mental work from us. For example, i dont care if the patients pain started 2 days ago or 4 days ago. AI and a human scribe can pick that up and it doesnt waste any space in your brain.

In reviewing a lot of charts / complaints one of the issues always seems to be the docs dont review (or remember) whats in the triage note. It is there in plain sight. AI can help you with it. From what I hear Oracle is going to release their first big attempt at AI with cerner later this year. I predict 25% of people will think it is awesome. 50% will be “meh” and 25% will think it sucks. 2-3 years from then it will just be the norm.
 
I hear you, bro - and I agree that where people thing I'm wrong is that generalized patient dumba$$ery can be overcome by AI...

... but I don't see how AI can recognize what is nonsense at ALL. It's still just a transcription of an audio recording being analyzed.
And I hear you...but you'd be surprised at how good the current, basically first gen, medical AI transcription actually is. It's not great, and sometimes it's not even good, but for the most part it is decent or better at picking out relevant stuff and ignoring the crap.

In reviewing a lot of charts / complaints one of the issues always seems to be the docs dont review (or remember) whats in the triage note. It is there in plain sight. AI can help you with it. From what I hear Oracle is going to release their first big attempt at AI with cerner later this year. I predict 25% of people will think it is awesome. 50% will be “meh” and 25% will think it sucks. 2-3 years from then it will just be the norm.
For the first 3 months that I used it (Dax in Epic), I was in the 25% Awesome category. I'm now on the border of awesome/meh and only use it for the HPI (which nobody but lawyers cares about anyway). I look forward to seeing what the next couple of years will bring.
 
And I hear you...but you'd be surprised at how good the current, basically first gen, medical AI transcription actually is. It's not great, and sometimes it's not even good, but for the most part it is decent or better at picking out relevant stuff and ignoring the crap.


For the first 3 months that I used it (Dax in Epic), I was in the 25% Awesome category. I'm now on the border of awesome/meh and only use it for the HPI (which nobody but lawyers cares about anyway). I look forward to seeing what the next couple of years will bring.
I think Dax is the least ideal. But i tend to agree that the HPI is the most useful bit. I use mine and barely review it at all. Needs some work on the MDM but i think that can be taught in due time. The differential diagnosis can be very helpful in the ED for billing under the COPA.
 
In reviewing a lot of charts / complaints one of the issues always seems to be the docs dont review (or remember) whats in the triage note. It is there in plain sight. AI can help you with it. From what I hear Oracle is going to release their first big attempt at AI with cerner later this year. I predict 25% of people will think it is awesome. 50% will be “meh” and 25% will think it sucks. 2-3 years from then it will just be the norm.
The bigger issue is the triage nurse. I look at the triage stuff because it’s not uncommon they put something crazy in there you have to address. The triage note needs to be just a few words.
 
And I hear you...but you'd be surprised at how good the current, basically first gen, medical AI transcription actually is. It's not great, and sometimes it's not even good, but for the most part it is decent or better at picking out relevant stuff and ignoring the crap.


For the first 3 months that I used it (Dax in Epic), I was in the 25% Awesome category. I'm now on the border of awesome/meh and only use it for the HPI (which nobody but lawyers cares about anyway). I look forward to seeing what the next couple of years will bring.
Yes quoting myself here, but it's hilarious. Just got done seeing a guy who missed his last appt with me because he was hospitalized for cardiac stuff, had AVR/3V CABG and an aortic aneurysm repair. He went to SNF afterwards and was telling me that the first thing he did when he got discharged from SNF was to go to a Mexican restaurant and have a beer.

Dax AI writes:
Social History - Had a beer after getting out of rehab.

Factually true. Not at all what he said.
 
Top