Comment by clusterhacks | Hacker News Reader

Comment by clusterhacks | Hacker News Reader

I work as a data engineer in an academic medical research institution.

Most electronic medical records (EMR) systems are really about billing. Yes, there are clinically relevant data fields available but a large amount of what we were after as researchers was only available in free-text. Data abstraction is still mostly a human-expert driven activity. It would be fun if that could be better automated but there is significant ambiguity in clinical notes and pathology reports.

And don't get me started on data-ownership "turf wars." We often got significant pushback and simple refusal to have regular data feeds of IRB-approved data fields for collection with patients who were consented to studies.

Nothing was more annoying to me to get shot-down when trying to get data from our hospital EMR (again, data that was specifically approved for research use by IRB for patients already consented to studies) only to hear later about private enterprise "partnerships" that had full and unlimited access to all EMR data . . .

This is extremely spot on, Cerner goes to far as to tie almost everything to a billing encounter (FIN). Yet the documents still come over as PDFs that clinicians have to parse through.

IME the billing-centric view is mostly a US-centric view. If you talk to folks who've done EHR deployments in other countries (my dataset is mostly Canada/UK), a not insignificant amount of work is put into tweaking Epic/Cerner/etc. _away_ from being so billing focused. Your other points still resonate, though anecdotally I've seen less private sector interest in doing analysis over providing infrastructure or other COTS software here.

> a large amount of what we were after as researchers was only available in free-text

Is there no way to parse this? Surely the EMR systems could have a simple key-value syntax. Patient history is too complex to be expressed that way but there is a lot of other valuable data that could. Blood pressure, for example. Ideally, things like lab results would already be stored as structured data.

With existing tech? No, not really.

Most of those lab values are more or less worthless outside of context - which is why so much time is spent on training docs on physio, pathophys, and history taking. I know that it's frustrating to hear, but it's why every "helpful" tech solution to date has resulted in increasing doc griping and burnout.

Even simple charts for numerical variables would be helpful though. For example, evaluating growth over time is important in pediatrics. In my country, mothers receive a booklet with all the charts and pediatricians are supposed to fill it with data during consults. When I open one of these, I usually find only two or three data points. Surely EMR software could do the same thing automatically.

https://www.cdc.gov/growthcharts/index.htm

In the US, growth charts for peds are already built into every EMR I know of. But even that isn't particularly nuanced: I want different charts at different ages based on, for instance, whether the kid is bottle or breast-fed. The difference will impact an interpretation of being under- or over-weight, and using the wrong ones can create the appearance that the kid is dropping off the growth curve at around two years old (which is to say, without context you can't even interpret just the trend itself). The EMRs aren't even at the "IF feeding==bottle, display.curveA; ELSE display.curveB" level of sophistication.

Which is another way of saying "even where it looks like the numbers matter unto themselves without context, nope, you still can't meaningfully interpret them without context."

Certain EMRs have lab data and diagnostics stored like this. That data is used in ML algorithms. That data lies outside of free-text.

I mean they kinda do since lots and lots of systems support HL7 which can best be described as "JSON but so so so much worse" or "CSV with '|' kinda."

"Lots of systems" is a stretch, only a few do. In fact, "support" is a stretch. Most EMRs (Cerner, Epic etc) only support HL7 as much as it gets them their CMMI / Promoting Interoperability certifications which are not relevant for actual use.

That being said, it is JSON but much worse

This is a bit of a simplification. HL7 is the standards body, not the standard itself - which (for everyone else who may not know) is "HL7 v2".

FHIR is an actually-JSON (+XML) health data protocol that is gaining adoption (most recently because of CMS Interoperability and Patient Access Final Rule), so it's not all bad.

FHIR is a breath of fresh air but it's so kinda worse because while it's great you still need the HL7 parser logic lying around in your code and now a bunch of additional code paths for FHIR

:/

Prior to FHIR, there was actually an XML-based HL7 v3 as well. Mercifully, it collapsed under the weight of its own spec and rarely shows up in the wild these days. CDA still survives, but it's much easier to work with and being slowly made obsolete by FHIR resources.

I'm working on dev tools in this space. Care to exchange notes with me? Email is in profile.

The US is a money and capitalism first culture. This is before things like privacy. I'm not suggesting what is right or should be but rather an observation of what is the case.

Yep. Here's my anecdotal story:

I am involved with phone call centers. I have a lot of numbers. I use phone numbers like others use throwaway catch-all email addresses.

I signed up for the covid vaccine through my family doctor who partners with a hospital. They required registration (no walk ups) and the online form was branded (domain, privacy policy, everything) to the hospital. I used a unique email address and a unique phone number. I'm a curious person.

To confirm the appointment they send you a text. Guess what number the text went to? Not the one I typed in. It was to a unique number that I only used with my Google billing account. (I was using a corporate computer in no way tied to Google.)

I looked into it and the hospital partners with a fourth-party health care scheduling servicer, who then has some sort of partnership with Google cause all I saw was that Google bought a low-percentage stake in the company.

Something tells me the integration between these types of companies and Google is much stronger than the article lets on.

Yep.

tl;dr :

EHR are mostly about charts.

EMR are mostly about billing.

The risks of unfettered access to EMR is that conditions can be inferred and future profitabilit of patients predicted so that they can be steered to different types and qualities of care (for good or for evil).

For-profit healthcare will overall optimize for profits before patient outcomes. It's as certain as gravity. FPH should be illegal.

Any organization that does not optimize value capture will be short-lived. Neither for-profit, nonprofit nor governmental business models are necessarily aligned towards improving patient outcomes over revenue. However revenue is a critical feedback loop to enforce change in the face of poor outcomes.

The Medicare agency cut off funding for heart transplants at [a nonprofit hospital] last year after the Chronicle-ProPublica investigation documented an outsized number of patient deaths and unusual surgical complications following the procedure in recent years.

https://www.houstonchronicle.com/news/investigations/article...

Pretty much all the numerical results in my chart (vitals, lab results etc) are stored numerically, and are importable / graphable in Apple Health.

Apple Health is a great example of using the FHIR standard to establish a personal health record.

Reply on news.ycombinator.com