I'm a co-founder at Cardiogram. In multiple N=14,011 studies with UCSF Cardiology, we've shown that heart rate sensors on consumer wearables can detect multiple major health conditions like sleep apnea, hypertension, diabetes, and atrial fibrillation (https://cardiogr.am/research). These conditions affect more than one billion people worldwide, and are frequently undiagnosed -- for example, more than 80% of people with sleep apnea don't know they have it.
We're live on iOS and Android, and we could use help in several areas: mobile and frontend engineering, senior machine learning engineers, and payer relations (the reimbursement from health insurers that Steve talks about). If that sounds like you, please email me at brandon@cardiogr.am!
It sounds so logical and inevitable where this technology is heading for health care. Over 10 years ago, I paid $1200 to wear a Holter monitor[1] for 24 hours.
In contrast, a consumer wearable like Apple Watch is $399. Arguably, the Holter monitor fee also included the doctor's time to read the ECG recording. But it also seems like a lot of the rudimentary analysis of heart data from wearables will be done in the cloud with machine learning. Hence, the price of basic diagnosis goes way down.
With the increasing aging population in USA, Europe, and Japan that will want to stay on top of medical issues, it seems like a big business opportunity. A bunch of players are going to compete in this space. Good luck to you!
[1] link for those not familiar with the device: https://www.google.com/search?q=holter+monitor
EDIT: A lot of folks seem to be interpreting my comment as implying there is no value in this technology. That is absolutely not the case. There is huge value in widely deployed screening like this (especially since it looks like the specificity is quite high). My point is that these devices will not be replacing diagnostic equipment (in fact, it may very well increase its use as more conditions that would otherwise have gone undetected will now be flagged for further diagnostic testing).
I don't have any real desire to move to SF but I do miss the fact that a lot of the cool jobs only happen down there. Ah well.
thanks
I suffer from chronic pain, and doctors are seriously unreliable when it comes to diagnosing something relatively complex, even though the research is there and has been available for many years.
I would be interested in joining a project that would become a tool that helps diagnose complex conditions, or at least provide a path for diagnosis.
The backend is written in Node with PostgreSQL as the database. Since it's a large dataset (terabytes), we rely quite a bit on PostgreSQL 10's partitioning feature for our larger tables: https://www.postgresql.org/docs/10/static/ddl-partitioning.h...
The machine learning code is written in Python, using Keras, TensorFlow, Pandas, scikit-learn, statsmodels. Our AAAI-2018 paper has a bit more info on how DeepHeart (our deep neural network) works. We also do feature engineering and traditional machine learning models when appropriate: https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16...
This doesn't mean that Apple won't be successful in healthcare. It's just that the main challenge isn't in creating a nicer product. The challenge is in showing a net positive impact on patient outcomes.
There are also a number of people who die of heart attacks with no symptoms. If Apple can get even 1% of them to the ER that would be a huge win. If the false positive rate is 80% that is still enough real positives that ERs will be get used to telling people "This time it is nothing, but it is good you came in anyway because sometimes this is all the warning you get".
The real worry is false negatives - someone who has chest pain and decides not to go because the watch says all is okay. These people will die when a hospital could save them.
False positives are not harmless http://theconversation.com/routine-mammograms-do-not-save-li...
The Apple Watch cannot detect heart attacks.
Apple Watch isn’t really any different here, except potentially in scale. While that does mean potential impact is large, there is no a priori reason to assume apple has got it wrong; it’s not that difficult to find the right people for this sort of project.
It would be very interesting to see an ROC curve ...
I'm not saying that the healthcare features in the new Apple Watch are bad; just that it will be interesting to see what their net contribution to healthcare will be.
This happened to me just a few months ago. I'm sitting in the passenger's seat of a car and, out of the blue, I get a call from a weird Caller ID which, of course, I hang up on. I get another call, this time from a regular looking number in the local area code. I reluctantly answer it (in spite of my friend driving telling me to hang up) and it's nearby emergency services. I'm of course totally confused and ended up hanging up on them when they start asking my name etc.
It turns out there's a setting you can change to make this harder to do by accident but I had no idea until I looked it up.
Having said that, I love the direction Apple is taking with this product. Smart watches have been on the market for quite a number of years now but they're pretty much restricted to being gimmicky devices only as most people don't find it very useful or have a real need for it. If Apple could achieve the breakthrough in blood glucose monitoring feature then I strongly believe we will see mass adoption in very near future.
Because they fill that lock screen with junk making it a butt dial magnet.
This is no longer the case.
The study that I am joining "MIPACT" is not well publicized, and I only heard about it through a friend at work. I wonder how many similar projects they are supporting around the country.
This is nothing against the Watch tech itself. There's probably a lot of cool applications for that tech. I just don't think Apple's advancement of wearables is monumental to the healthcare industry, or potentially disruptive.
> The FDA – Running Hard to Keep Up With Disruption
Honestly, I don't really know what he's talking about with this 'disruption.' Just because the FDA is trying to keep pace with all the tech being built by health tech startups, it doesn't mean anything is getting disrupted. I have yet to see what I would consider a disruptive technology sweeping over the healthcare industry.
Some examples:
I always wondered why I had a lot of trouble sleeping. Doctors laughed at me, until an orthodontist told me I should get checked for sleep apnea. Turns out I had very severe sleep apnea. I would have like this diagnosed much sooner in my life.
My Dad had afib, had it been diagnosed sooner, his surgery wouldn't have been a "get it done now" situation.
Once the true positives outweigh the false positives, everyone's going to consider these essential for health. That moment will probably be in 2-5 years.
I 100% agree. I think we are on the cusp of the "cyborg" era, like it or not. Humans will wear health tracking devices at all times. Already 10M+ do, from basically 0 a decade ago.
Personally the sleep tracking and heart rate data from wearing my bands since 2014 led me to a diagnosis and fix for a number of health issues.
But the real promise lies ahead, as new and better sensors are engineered. In addition to helping with traditional health issues, devices will increasingly allow the conscious part of your mind to have real-time self-awareness of the biological factors going on that influence your thoughts and decisions and answer questions like these:
- Did you say "no" to that thing because it was the right decision or because your blood glucose level was so low? - Was your high productivity level today a fluke or influenced by the high caffeine level in your system? - How "tired" are you really?
Some people might not like it, but I don't know if they'll have a choice. Not taking advantage of these technologies would put them at a disadvantage in school, work, sports, and perhaps all other areas in life.
I think that moment is more like 10-20 years out, but otherwise agree with you.
I think most doctors and patients would agree that getting information in a timely manner is more important than the mechanism by which it is transferred. While interoperability is something to strive for it's not the thing holding the system back.
This is what I'm talking about. We're so far away from actual interoperability it's not even funny.
> The time it takes to request and receive records on a patient is measured in days not minutes.
Yup.
> While interoperability is something to strive for it's not the thing holding the system back.
Not sure I follow you. The siloed data seems to be a pain point for most docs. Patient is admitted for evaluation of X, Y, Z concerning symptoms. Patient was admitted to a different hospital a week ago for the same symptoms. Different hospital is on a different system, so I can't get the patient's history from that visit. Guess I need to have the records faxed over tomorrow morning. In the meantime, let me go order a bunch of tests that are probably totally redundant to what was run last week, but I can't get that data right now, so gotta run them again. Huh, that's a interesting x-ray. Wish I had the prior.
EHR vendors are actively working to enhance their applications to cope with new data streams coming in from consumer wearables as well as connected home healthcare devices such as smart scales and blood pressure monitors.
Is this actually the case? I haven't heard any talk of this at my institution, or on r/medicine.
UHC is the U.S.'s largest insurer, and they claim to have validation data that shows this program saves money.
Most of their competitors? Garmin's latest watches won't even talk to an ANT scale anymore (well, there's $300 kinda wasted). Garmin still has their line of ANT+ accessories, though.
Moreso, I view ANT+ as the protocol for the athlete that isn't going to be using an Apple Watch during their workouts. "Oh, your $600 Garmin power meter pedals don't work over BLE with your Apple Watch?", asks no one ever. There are BLE heart monitors, foot pods, and power meters if you absolutely must use your sensors with something Apple. No, it's probably the optimal solution, but it's the solution Apple's market will be happy with.
I had a routine EKG last week for a pilot medical certificate. Before the EKG, the nurse rubbed a cold gel on my skin, at the places where she then placed the EKG contacts. I'm assuming this gel was to ensure good contact. If doctors have to rub this gel before an EKG, why doesn't the Apple Watch need this, to ensure good contact?
It probably varies by person, but heart monitor chest straps such as those that come with higher-end exercise watches, can benefit from the gel. However, most folks (including myself) either just slap 'em on dry, or with a little spit, and they usually work fine. But at the doctor's office "usually" probably doesn't cut it. If a little gel changes "usually" to "always", then they probably apply as a matter of course.
That's my long-winded way of saying that a little gel on your wrist and finger would help (I guess; I've not seen the watch yet, nor am I a medical professional). But for the not-a-lab-or-medical-office setting, it's good enough.
If you can't use it though, you can't use it. The data may have glitches, anomalous readings, but most of it will be pretty good most of the time, or they wouldn't bother with the feature. I'm also not sure what the apple watch's sensing mechanism is. Is it reading voltage or is it measuring something else that's correlated?
The watch is always running, can throw out large quantities of glitches & anomalous readings, and only produces an alert to seek followup.
The Apple Watch is positioned as a cardiac event monitor. Those are intended for extended wear and only need to take measurements between a single pair of electrodes to function.
For instance, a Zio Patch is a modern version designed to be compact and unobtrusive.
Here's a comparison between a Zio Patch and the old school tech of a Holter Monitor.
https://www.medgadget.com/2014/01/zio-wireless-patch-may-be-...
One of the tech journalists at Ziff Davis who took part in Apple's heart study ended up being dignosed with Afib by his cardiologist. He wrote about the process he went through.
TLDR: The watch flagged that there was a potential problem, he was given a traditional tape on cardiac event monitor to wear for an extended period to confirm the watch data, and was then diagnosed and treated.
https://www.zdnet.com/article/how-apple-watch-saved-my-life/
For me, this was the money quote: "I've had EKGs a number of times, and there was never any indication anything was wrong."
As EKGs go it’s a relatively basic test, is the equivalent of having a single wire.
I’m very curious to see what doctors/etc. make of it once the feature is released.
If so, there could be open-source iOS apps that enable privacy-oriented health data collection on the watch, e.g. with E2E encrypted messaging initiated by the device owner, when data review is wanted.
iCloud Syncing for your HealthKit data encrypts and stores your data in iCloud, similar to iCloud Keychain. If this is enabled, HealthKit information is stripped from iCloud backups, if you use them. You can also do local encrypted backups through iTunes. If you don’t use any of the above options, HealthKit data stays on the device.
On device, HealthKit has lots of permissions for apps to access health data, including per app reading and writing permissions for each data category.
Apple Watch can only be connected to iPhone, though (not iPod touch) so have it sync to a device without LTE baseband radio is not possible.
https://developer.apple.com/documentation/healthkit/protecti...
That said, I believe health data is end to end encrypted within icloud.
1) its heart rate monitoring while running was terrible. I run in a HR range and AW3 wasn't accurate enough for that. It would show a rate too low and then impossibly high within a couple minutes... couldn't use it to pace myself.
2) battery life. If you run for 2 hours, you likely can't get through the day. I had to charge it every night. In the case of a medical monitoring device, I guess you'll have to settle for being monitored for only part of the day???
I ended up buying a Garmin Forerunner 935 and its HR is more accurate and battery life is much better. (But not saying Garmin is OK for health care either)
- The GPS on the watch was terrible, often dropping out for me, and leaving out a mile here and there. Is this an Apple thing? My Garmin is way more accurate.
- I need an always-on mode. I realize it drains the battery, but I own the battery and that is my choice. I need to be able to glance down and see my pace immediately, not fiddle with my wrist flicking until it comes on.
- I'm also bummed that there's no Spotify support yet, and that it's not a true standalone LTE device. I want to ditch my phone and have a watch only.
Often when glancing at my AW when running it would show the wrong screen. It would either show "now playing" music (even though I don't run with headphones) or my Strava app... when I actually wanted to see the heart rate app.
I'm not familiar with this term. I just had an image of our Human Resources officer shooting at people running on an indoor track with a nerf gun.
Well I do think 'not very soon' - because I only know a handful of people (all doing computery things) with an Apple Watch or FitBit/Android thingy, and even of those fond of tech it's only a minority.
I cannot even fathom how long it would take to have this data even be acknowledged or just being able to be interchanged with German doctors and hospitals.
A toilet that analyzes specimen data and alerts you of potential issues.
This is a parody but actually has some great product ideas :)
Overall I guess I’m missing things... like why is this idea being parodied?
Why Tim Cook is Steve Ballmer and Why He Still Has His Job at Apple (2016)
https://steveblank.com/2016/10/24/why-tim-cook-is-steve-ball...
Anyone basing serious health stuff on this is crazy.
Cross that data with customer loyalty card data regarding groceries purchases for the next decades, and one can practically automate ineligibility.
Maybe through ML Apple could enhance the accuracy and precision of the measurements but given Apple's history with iterating on intelligent features(Siri), it won't happen for a while. If Apple wants to have a meaningful impact on the health of their users, then maybe they ought to use the ECG sharing feature as a means of getting their foot in the door of the medical records industry where their product approach and design rigour is much needed. Moreover, Apple could leverage the ECG feature as part of the product experience to motivate people to engage in activities that get them moving which, at the end of the day, is where most users derive the most value from.
You know what’s worse than a false positive? A real positive and no way to know about it.
If the false positives result in investigations that carry medical risk then it's possible that on the whole, more harm than good is done.
There's also an interesting consideration around real positives that we've never detected in the past and that never presented any symptoms or negative outcomes. It's possible that we now start detecting cases which previously the patient went their whole life without knowing about and would be totally unaffected by, and introducing medical interventions that have downsides.
How it all stacks up in the end we can't possibly know, but this development isn't automatically "good".
