Clinical Query At Beth Israel Deaconess Hospital–Self Service Analytics Using Boolean Expressions–A Goldmine of Valu
Posted Sep 12 2012 11:01am
This is a great article and a lot of work went into this process and when you follow the link and read the article in it’s entirety you will get a better idea of what all was created here and the creative intelligence of Dr. Halamka. This is huge and the safety precautions with throwing in some arbitrary de-identified patients is great and works to make re-identification pretty much not possible. By using Boolean expressions you are down to a true or false with the search which would make it fast and efficient versus a long string of SQL statements to process. Some of the old visual basic expressions of Microsoft were built around this, wrote enough of these myself and that’s part of what made me logical I joke.
I always say when it comes to having CIOs, CEOs, etc. in today’s medical world it helps tremendously to have folks in those positions with “hands on” experience and this example is no exception. It doesn’t get much better when you have the CIO, Dr. Halamka in there writing code as he talks about how he wrote part of their medical records system which was up and running in the early days before many of the EHR companies existed. Good stuff. If you know anything about the history that dates back to Dr. Halamka’s arrival here with their entire system crashing I think it was on his 3rd day, then you know he had a lot of work to do as of course in 3 days you can’t get anything done, so nice kudos for sure on what has been accomplished here.
Also with “hands on experience” and the valuable information he has we items as such at the link below with recommending holding off on some integration processes and this helps government figureheads who are responsible for setting dates for compliance and yet have not one stick of IT or computer science knowledge in their backgrounds. (I sure wish we could start fixing some of those issues soon <grin>.)
In other posts around the Medical Quack you read about how myself and others quote that those who control the code control the world and this is a great “positive” here as there are those who write code for other purposes and slowly the world is coming to know who they are and if you read here enough you have a pretty good idea, so yes there’s power in the code and those algorithms. You just can’t replace the value of “hands on” knowledge and competency with coding and queries. I would almost say that working with Dr. Halamka could almost be like having a live “Wikipedia” walking around when one has a question and that’s a big complement there for sure. You can also go back a few months and read on his blog a bit more about Clinical Query and with his explanation on how it works. Below is a quick screenshot from the links mentioned.
Now one other point that is made here too is the amount of data as compared to an ATM machine, averages 6 transactions..compare that to 65,000 patient data elements to appreciate what was built here and this was well worth the mention as folks seem to think that healthcare is so far behind, not really as there’s so much more data and privacy implications to work within that is complex. Mapping to SNOMED codes was a project in itself. Great thing too is that “open standards” were used in all of this, no proprietary patents, copyrights, etc. to deal with there.
He also mentions his project of taking commercial EHR systems and connecting the data to download into the hospital records and there are several of them whereby the code is being written to do so. I sometimes think back to the early days of some of the technologies we use today and way back in 2008 we had an MD who called himself Dr. Anonymous who was working with a new web radio format and started his weekly shows and at that time there were only a few of us brave enough or making time to communicate to try it out but Dr. Halamka was there too:)
Again worth mentioning here once more is the hands on knowledge we have and the advancements possible when there are people in “key positions” that have some computer science, coding, IT infrastructure an so on in their background. This is huge and what another wise man, Bill Gates told the graduating class at Berkeley a couple years ago, “the hybrids, people who have more than one area of focus are going to be the people in demand and the ones with recognizing value”….and code and technology are right up at the top of that list. BD
Like all the hospitals affiliated with Harvard Medical School, Beth Israel Deaconess Medical Center aims to be the best of the best. A closer look suggests the hospital is achieving that lofty goal partly by taking shrewdly calculated technology risks.
A centerpiece of BIDMC's IT-based innovation is a new medical informatics platform called Clinical Query. To appreciate its value, you need to understand the current healthcare environment.
Enter Clinical Query. John Halamka, BIDMC's ball-of-fire CIO, refers to it as a clinical trials/clinical research business intelligence system. It's a search engine married to a huge database of patient records that lets hospital employees test hypotheses about what causes a disease, for instance, or test which drug, diet, or lifestyle variables may reduce the risk of developing one.
The repository contains 200 million data points on 2.2 million patients, including medications taken, diagnoses, and lab values.
The query tool is capable of navigating 20,000 medical concepts through the use of Boolean expressions. All the data has been mapped to standard medical language codes. Diagnoses, for instance, have been mapped to ICD-9; medications to RxNorm codes; lab data to Logical Observation Identifiers Names and Codes (LOINC).
So with the help of Clinical Query, a clinician or researcher might search the records to find out how many patients with breast cancer also take ACE inhibitors, a class of drug used to treat high blood pressure. If the results reveal a strong correlation between the drug and the malignancy, the hospital could do a deeper analysis and set up a formal research project to investigate the link. The ultimate goal is to discover a new medical intervention that would improve the survival of the entire population of breast cancer patients.
More cutting edge was the hospital's custom EHR system, called Online Medical Record. Halamka is quick to point out: "We built it ourselves. I wrote part of it. It's Web-based, cloud-hosted, runs on tablets. How many EHRs in the world have those characteristics?"
Clinical Query always throws in a few additional arbitrary patients to the search results, creating just enough ambiguity to keep patients' secrets secret. Normally, a database search is supposed to give precise results, but in this scenario, the researcher's initial goal isn't supposed to be to identify individual patients, but to find correlations between diseases and risk factors.
A major technological obstacle to making Clinical Query fully functional centered on the variable nature of medical terminology. As a matter of contrast, there are only six data elements in the average ATM transaction, but the average patient record contains about 65,000 data elements. Complicating matters further is the fact that different clinicians may define each element differently.