Making a test with 0% false negative rate is a piece of cake:
if (test_taken == true) {
test_result = true;
}
No negatives means no false negatives. ;)
But seriously, this is the classic trade-off between high sensitivity (no false negatives) and high specificity (essentially no false positives). Usually, the lower you set your threshold for detection the more likely you are to tell some people they have the disease when they actually don't. Where you set that bar depends on what you're trying to accomplish and forces you consider the harms associated with telling people they have disease when they don't or missing disease in someone who does.
The accuracy will improve over time, but the real challenge for all of these health tools is that they accomplish a job most people aren't trying to do.
A lot of people say they care about or would be curious to follow things like their weight, BP, or heart rate, but very few people actually do. The barriers aren't even very high--taking your morning, resting heart rate or stepping on a scale is dead easy, it's just not very valuable information to most of us.
Heck, what most people who have hypertension, pre-diabetes, or obesity really want is for the disease to just go away. Since a quick pill or surgery for many of these problems don't exist, not thinking about the condition is the next best thing.
These health tools are getting a ton of press lately and I have no doubt that they'll be very useful for doctors and the committed few, but the real problem to be solved is motivating people to care about their health like they care about their bank accounts.
This is a combination of posters not understanding what the technology is used for and the tech guy exaggerating the urgency of the situation.
Remote cardiac monitoring isn't for people who are imminently going to die of catastrophic heart attacks or who risk dropping into a fatal arrhythmia (wonky heart rhythm). In fact, there isn't even solid evidence that it saves lives. What it is used for is investigating patients who have vague symptoms which might be related to transient changes in their heart beat.
These are people who come to their doctor at the age of 54 and say "I felt my heart beating really quickly and felt kind of faint" or "I felt kind of dizzy and then passed out. It's happened twice in the last month." The more traditional way to investigate these patients are with what's called a Holter monitor, as alluded to by a previous poster. These are little belt packs you carry around while wired-up and that record your ECG for 24-48 hours at a time. The main weakness? You said it: the device only has a 24-48 hour windows to capture the weird, often rare, rhythm.
There are different ways remote cardiac monitoring systems report their results and I'm not sure which this particular company was using, but it doesn't really matter. Some of them only report weird stretches, others only report events when the patient says they're feeling symptom X, others are reporting continuously.
Take-home message: this is not life-or-death data. When doctors (at least those who are allowed to keep practicing) think a patient needs critical cardiac monitoring, they admit them to hospital.
This was a tech guy, looking to jump the queue by trying to raise a red flag because his servers were being used for--OMFG!--cardiac monitoring. A lot of my doctor buddies use similar strategies when they're caught speeding by the police. "I just got called in to the hospital!"
From the website I think this analysis is correct. Holters store the 24 hour data on the machine as well. The 12 leads are not continuous but set pieces which also store locally. If they were providing real-time monitoring with alerts then this would be more serious. This seems to be a backup system, ironically itself without backups.
b) Good to know from responses that amazon's paid support is crap. They'll officially tell you "were on it".
c) People are bashing this person for relying on amazon not failing all at once. I would be surprised if they hosted on amazon relying on each individual node being up 99.98% of the time. That is crazy. You build on cloud computing knowing that each one node can fail at any moment, but you build it to fall over to another node. From experience, sometimes nodes just... die... or get really unstable.
d) People bashing the dude vs offering future advice. I'm sure if his company is in deep shit, he's well aware of it.
Yeah, the medical training model fosters a culture of working ridiculously long hours and shunning those that don't. As a first year surgical resident it's not uncommon to work 110-hour weeks and anything less than 80 feels like a joke.
And, as other posters have pointed out, this is despite legislation limiting the number of work hours. The fact of the matter is that if you were to actually work to the letter of the law you'd be sneered at, receive poor evaluations, and patients would suffer because there'd be no one around to do the work.
Most programs argue that these hours are necessary to train surgeons since there's not only the usual cognitive side of medicine, but also the technical side of cutting, sewing, etc. That being said, 70% of the hours I put in at the hospital are BS "scut" work which could be automated, streamlined, or passed off to assistants. The actual challenging decision points are few and far between.
Thus, even the 10,000 hour rule--which a lot of programs use to defend their dismal hours--misses the mark completely since, well, the practice isn't focused.
I don't think surgeons are going to be replaced by robots in a significant way for some time, but I would like to see the hands-on part of surgery being performed by techs. A three year, well planned course would be plenty to turn you into a competent operator--as competent as many just-licensed MDs. After all, do you really need 10 years of academic training (four year undergrad, fours of medical school, two years of little operating as a junior resident) to screw bones back together? Why should we expect surgeons to be technically AND intellectually gifted?
