Health Care Fraud Takedown

https://www.fbi.gov/news/stories/2015/june/health-care-fraud-takedown/health-care-fraud-takedown

by doctoroz • 11 years ago

104 57 11 years ago

i wonder how the medicare fraud strike force is currently doing this, and how we, as technologists can improve the process.

working around HIPAA makes this an particularly hairy problem but from what i understand it is still possible to create a compliant solution for hospitals, emr vendors, and insurance companies, and even patients to detect medical fraud.

i couldn't find much but maybe some work is already being done in this space?

Axsuul• 11 years ago

Perhaps big data companies like Palantir are assisting with this?

threeseed2• 11 years ago

Possibly. But just as likely they are running their own Hadoop platform and have hired some data scientists.

Most large organisations these days are running their own analytics platform.

kevin_thibedeau• 11 years ago

My favorite is using Benford's law to find anomalous digit distributions in phony numbers.

jacquesm2• 11 years ago

It's a very reliable method and it is surprising that with the amount of publicity mentioning this either in passing or as a direct cause for a further investigation that it remains effective. After all, you'd imagine that wanna-be fraudsters would 'Benford-Proof' their numbers.

anigbrowl2• 11 years ago

Benford's law is surprisingly effective in detecting unnatural patterns in data; I believe the IRS relies heavily on it. Then, alert eyes at the payment end, and encuragement to low-level clerical staff to cooperate in implicating their bosses or be left holding the bag. This works better for white-collar crime, since the criminal higher-ups are that much less likely to successfully put out a hit on persons who informed against them, though sometimes not for lack of trying.

https://en.wikipedia.org/?title=Benford%27s_law

newman314• 11 years ago

I wonder this is applied to find bad actors in the financial sector...

TazeTSchnitzel• 11 years ago

https://en.wikipedia.org/?title=Benford%27s_law

Now that is a weird Wikipedia URL. The normal one's /wiki/Pagename, and you sometimes see /w/index.php?title=Pagename, but /?title=Pagename? What produced that?

dbarlett2• 11 years ago

At a hackathon back in 2013, someone mentioned analyzing Medicare claim data to find impossible or improbable scenarios, like a doctor performing two lengthy procedures on the same day at hospitals 500 miles apart.

mturmon• 11 years ago

There was a famous case in LA of a couple of doctors working impossible shifts (more than 24 hours in a day, or 24 hours a day for over a week straight):

http://articles.latimes.com/2005/apr/26/local/me-kingdrew26

Eventually the facility was closed and some of the administrators were canned.

_zbap5• 11 years ago

So here's what medical fraud looks like: http://i.imgur.com/jMvUqqK.jpg

Sorry, crappy excel graph, but, it was meant to be a quick and dirty look at 12 GB of prescription data that got analyzed by a few programs I wrote back in 2009, give or take a year. Took days to crunch numbers after it was written. Anyhow, looks like an imaginary city skyline, right?

Going from left to right, lets call it the X axis, are various diagnostic codes used to prescribe medication. So on the left side it's like code 400, on the right side 500. In between is 401.3, and so on. Been awhile, so can't remember the exact numbers but bear with me. The drugs range from opiates to diflucan for yeast infections, to whatever else. So you kind of see a distribution range that's normal.

On the Y-axis, are years. Here's the slightly confusing part of the graph: I striped 4-5 clinics worth of data on that axis. So on that axis, only 6 years of data are shown per clinic. What shows up after the first 6 long rows is a different clinic, and so on.

The Z-axis is a frequency of prescriptions. Like, how tall a tower is means how many prescriptions were written for a particular medication, by a particular clinic, on a particular year.

If you look at the nearest 6 long rows, that's 1 clinic, 6 years of operation and you see nothing but flat lines. No yeast infections, no eye drops, no steroids. Just some really insanely tall towers. One of the towers gets clipped from the graph because it's that insanely taller.

The tallest towers were the most expensive drugs and treatments that the government reimbursed the clinic for, so they took a shortcut and just went for those. The kicker is that they only got caught when we started investigating. There was a tip. Someone reported something weird about the clinic. So, we went up to the state and asked for an anonymized data dump of the clinic in question, and then absolutely nothing happened. The state stalled for 6 months before finally giving the data up. Turns out, they were only alerted to the fraud after we asked questions about the clinic, and they wanted to take corrective actions before disclosing anything to us so that it didn't seem like they were sleeping on the job.

I don't know what to say. I get it, this stuff is complicated, the data sets are huge, and there are more blindspots than you'd think. Lack of oversight is too strong of an accusation for me to wield, but there was definitely a fear of criticism. What I'm trying to say here is that computational detection is only a small fraction of the real issue. The bigger issue is the guarded cultural environment in which all these agencies exist, and without intimate knowledge of how they work and what is possible, there's no silver bullet.

thaumasiotes3• 11 years ago

So it looks like you've got data for four clinics in there. Of the three non-fraudulent clinics, two show pretty elevated levels of that particularly lucrative code, the one that clips the ceiling for the fraudulent clinic. How much of that is fraud?

The fraudulent clinic has something really bizarre going on, too. In the first year (years being in order lavender, red, yellow, green, black, and peach), they've got a big spike at the ultra-lucrative code and some other big spikes at other codes. In year 2 (red), they've got just the one spike, a smaller version of their second-biggest spike from year 1. In year 3 (yellow), they've got one "spike", but it's tiny. In years 4 and 5 they've got practically nothing at all. What were they doing then? Didn't they want any money at some point in that three-year period?

remarkEon3• 11 years ago

Mind linking where you got the data?

rak2• 11 years ago

There is a lot of public information available about this stuff. I would start with looking into Zone Integrity Program Contractors (for Part A and B), Medicare Drug Ingretity Contracts (Part D), and Recovery Audit Contractors (Part A and B, mostly focusing on over and under paymentments through periodic auditing).

There are also groups you can find out more information on that handle fraud for medical labs that fall under CLEA regulation (Labs/PINS group) and ambulatory services fraud. There is also a contractor that's focused on provider screening services.

It's a pretty big subject to sum up how they're doing this but it does involve some interesting analysis techniques and there are plenty of pain points that could probably be improved.

It's really interesting and exciting work for technologist who want to get in on it.

iandanforth• 11 years ago

My impression is that money lost to fraud is a tiny fraction of money lost to legal wasteful spending, lawyers fees, and drug company profits.

Is there any reason to believe these law enforcement activities are an efficient use of time and labor?

anigbrowl2• 11 years ago

I think they're effective insofar as proposals for reform are often deflected by allegations of fraud and deliberate waste - 'if you can't root out the rampant fraud why should we trust you to reform a broken system?!'

You see this argument in immigration politics a lot too - 'we can't discuss reform until the border is secured.' I agree that meaningful reform would probably substantially reduce the profitability of fraud and make it easier to detect as well, but that's political reality for you.

justinsb• 11 years ago

Yes: it was 700 million dollars. And are you suggesting that law enforcement's time would be better spent investigating legal activities?

savanaly• 11 years ago

The larger portion of the value of criminal determent is the crimes it actually deters. We would have to calculate the cost of those crimes (tough to do-- the cost to society is not the same as the amount stolen, after all, since the money goes in the pockets of the criminals) that would have been committed if it was well known there was no enforcement.

ac29• 11 years ago

If it cost less than than $712 million to recover this $712 million, it was more than justified. Most law enforcement doesnt have nearly that ROI.

These were major frauds -- $712MM in fraud by 243 people.

threeseed2• 11 years ago

I never understand arguments like this.

You do realise that companies/organisations are capable of doing more than one thing at a time.

sliverstorm• 11 years ago

712M is 0.15% of the entire yearly Medicare budget. Maybe there's bigger waste that we are still fighting, but that's a hell of a lot to be losing to fraud, and they doubtless haven't caught all the fraudsters yet.

thr0waway8• 11 years ago

Highest paid doctors in the world, and it still wasn't enough for them. And in case you believe their sob stories about Medicare not paying them enough, read this: http://www.slate.com/blogs/moneybox/2013/01/23/chart_us_gove...

sharpests• 11 years ago

Only 19 of the 240 individuals were physicians. And most primary care doctors in canada make more money than I do, and I'm a surgeon.

As for the medicare thing, it's not just that medicare doesn't pay enough, it's that about half the time in my practice, medicare simply doesn't pay anything at all.

Finally, if you want to talk about fraud in medicine, the cited problem isn't the major fraud issue; it's just the most newsworthy (easily quantifiable money amount) and therefore an easier target for the men in black.

Not sobbing; I make a good living and am quite happy.

jacquesm2• 11 years ago

Only 19 of the 240 individuals were physicians.

Only?

How does that number compare to the %age of physicians in the total population of medical professionals?

And why does it matter that GPs in Canada earn more than a surgeon in the US?

FireBeyond• 11 years ago

Medicare pays pretty reasonably. There is definitely ideological and other talking points in place, that I discussed here: https://news.ycombinator.com/item?id=7604698

njloof• 11 years ago

Not always; ask any hospital if their anesthesiology department operates at a loss. The answer is almost always yes. You can't have surgery without anaesthesia, yet the cost of the service (including the market price of anaesthesiologists) outstrips the reimbursement.

remarkEon3• 11 years ago

It's rather disgusting that these people were fraudulently billing mental health services, seeing as how there are many real people who actually need these services. I'm thinking of veterans of the last 14 years of war. And anyone else who legitimately needs help.

jrapdx3• 11 years ago

Yes it is disgusting, maddening, and in a way, bizarre considering that Medicare reimbursement for psychiatric services is shamefully inadequate. (No question, Medicare reimbursement does not come close to covering the costs of providing mental health care, hence many professionals won't take Medicare patients.)

That makes it hard to understand such fraudulent claims, yet the FBI statement documents claims or payments for psychotherapy that wasn't provided. Seems like a poor way to defraud the government. The only thing I can think of is billing a large volume of false claims and thinking low-value services like mental-health care would slip under the radar.

I'm very glad to see a few "scam artists" were caught. They deserve what's coming to them, but the ongoing occurrence of fraud suggests fundamental problems remain unaddressed.

remarkEon3• 11 years ago

Honestly, it's embarrassing that people who pretend to be professionals would do something like this. I agree that there needs to be structural changes to how we address this issue. I'm not read up enough on the structure of the problem to propose solutions, but I do know that some people who need the help might get some help, but eventually run into a wall.

mgkimsal• 11 years ago

If someone bills Medicare for something for me, do I not get a record of that, indicating the transaction?

I'd expect to have received something saying that "provider X was paid for you to have equipment Y (or counseling session Z). If this does not seem accurate, please call 1-800-McGruff". I'd think that would alert people about fraud far more quickly, no?

hga• 11 years ago

Indeed; being disabled, I'm on Medicare rather early for it, and I get informed of everything that's billed and associated with me for Medicare Part B, doctor's office etc. sorts of things (haven't had to go to the hospital so I don't know about the original Part A). I also have deductibles to pay, including before my Medigap insurance kicks in.

That said, they could be billing fictitious people, or people sick enough the extra stuff is easy to miss with all the other charges ... and that's very possibly how many of these fraudulent outfits were found. There are plenty of us with personalities in the direction of OCD, my 79 year old mother for instance, who's I'll admit is pretty healthy and was a RN before I was born, wouldn't miss anything. Last time I was in the ER for a nasty fall I later called them up to query a charge of $90 for a TDa?P inoculation, and was satisfied with their explanation that they had to keep plenty of non-expired medicines on hand for everything, including unexpected events. In their case, they had been the primary hospital that received the injured from the 9/11 attack on the Pentagon, and closer to home, a lot more people would have died than the ~160 in the EF-5 tornado that hit my home town and took out the other hospital, if they hadn't had ample supplies (see http://stormdoctor.blogspot.com/2011/06/first-response-mode-... for an idea of just how intense that was)

elliottcarlson• 11 years ago

Personal story that relates to this:

A few years back, my wife was finishing up classes to become a cardiovascular technician. Part of the process to become fully certified is kind of a chicken/egg scenario - to become ARDMS certified, you need to work under a cardiologist for a year - but most cardiologists don't want to hire someone that isn't already ARDMS certified. Anyhow - she was pretty frustrated in how hard it was becoming to get a foot in to the industry when she finally heard back from one practice. The interview is conducted in an apartment on the 50th floor of a luxury building in downtown Manhattan - there were a few other people there just doing work on laptops. She gets the job, but she immediately felt something was off - but she wasn't sure what.

For the most part she would help in the "office" and do billing and coding from some other offices this doctor owned. Sometimes she would be sent out to one of these offices to actually scan people (which is what she actually enjoyed and wanted to be doing). And sometimes the doctor would take the whole team of people working in the "office" out to very fancy dinners where no expense was spared.

A few months (I think it was about 6 months - but could be wrong) in to this job, my wife needed a day off for her own doctors appointment, and it turned out to be a good day to take off - the office was raided by a joint task force of the FBI and Secret Service - they took the main guy in to custody, confiscated all the laptops, etc. My wife got a call later that afternoon from one of the other girls telling her what happened. Eventually my wife was asked to come in to talk with the FBI twice - they had pictures of her outside of the building smoking - knew what she had eaten at one of the dinners, etc. She was cleared from any involvement since she really had no clue what was actually happening.

In the end, the guy was arrested for Medicare and Medicaid fraud - he had purchased a radiological service from a doctor that was retiring, and assumed that doctors identity. He was charged with billing out $32 million in services that were never performed - $20M to Medicaid, $12M to Medicare. It definitely seems they were on to him for a little while at least - though I can't find any more details besides the original press regarding his arrest.

Sadly, my wife lost this time and does not feel right putting it on her resume - so she remained in the chicken and egg scenario and eventually she went back to school to broaden her applicable skills so she can actually work in the field - and hopefully, actually get that certification...

a8da6b0c91d• 11 years ago

I dare you not to notice some patterns with the names: http://www.justice.gov/opa/documents-and-resources-june-2015...

mfringel• 11 years ago

They all seem to have a pretty standard set of letters and diacritics.

Care to elaborate?

DanBC• 11 years ago

They sound like fairly normal American names to me.

What am I missing?

asanagi• 11 years ago

Exactly. What's missing?

rak2• 11 years ago

I used to work for a CMS contractor that was involved in th is kind of work. The level of effort put into fraud, abuse, and waste prevention for Medicare and Medicaid are amazing. There's still a lot of room for improvement, but it was a memorable experience working in that field.

hippich• 11 years ago

For a second I thought it is about how hospitals bill tens of thousands dollars only to settle for 5% of the total with insurance company (if you are lucky to have one, otherwise you are screwed)

imaginenore• 11 years ago

Which is the real scam, but somehow billing $20 for an aspirin pill is A-okay.

Health Care Fraud Takedown

Related Stories