I recently heard Stan Huff, CMIO at Intermountain, talk at the Healthcare IT Transformation Assembly about the Healthcare Services Platform Consortium. As he presented what they’re working on he highlighted so well the challenges that I’ve been seeing in healthcare IT. I’ve long be asking people how healthcare IT innovations that happen in one hospital or practice are going to get shared with all of healthcare. Turns out, Stan has been thinking a lot about this problem as well.
In his presentation, Stan framed the discussion perfectly when he said, “No matter what you do, you can’t teach people to be perfect information processors.” I’d also mentioned in a previous post that the human mind can’t detect the difference between something that causes errors 3 in 100 versus 4 in 100. However, with the right data, computers can tell the difference. Plus, computers can assist humans in the information processing.
These points illustrate why building and sharing clinical decision support is so important. The human mind is incredible, but medicine is so complex it’s impossible for the human mind to process it all. Ideally all of the work that Stan Huff and his team at Intermountain are doing on clinical decision support should be “plug n play interoperable” with the rest of the healthcare system. That seems to be the goal of the Healthcare Services Platform Consortium.
Many might wonder why Intermountain would want to share all the work they’ve been doing with the rest of healthcare. Isn’t that their proprietary intellectual property? It’s actually easy to see why. Stan described that Intermountain has implemented or is currently working on ~150 decision support rules or modules. Given their organization’s budget and staff constraints he could see how those 150 could be expanded to 300 or so, but likely not more. That sounds great until you think that there could be 5000+ decision support rules or modules if there was enough time and budget.
The problem is that there was no path for Intermountain to go from 150 to 5000 decision support rules or modules on their own. The only way to get where they need to go is for everyone in healthcare to work together and share their findings and workflows.
Stan and the Healthcare Services Platform Consortium are building the framework for creating and sharing interoperable clinical decision support apps on the back of FHIR and Smart Apps. This diagram illustrates what they have in mind:
I think that Stan is spot on in his assessment of what needs to be done to get where we need to go with clinical decision support in health care. However, there are also plenty of reasons for being cautiously optimistic.
As Stan told us at the event, “If everyone says that their workflow is the only way, we won’t get very far.” Then Stan passionately argued for why physician independence allows the opportunity for doctors to take improper care of patients. “If we allow physicians to do whatever they want, we’re allowing them the right to take improper care of patients.”
Obviously Stan isn’t saying that there shouldn’t be rigorous debate about the best treatment. By putting these algorithms out to other organizations he’s actually inviting criticism and discussion of the work they’re doing. Plus, I have no doubt Stan understands where health care is an art and where it’s a science. However, I believe he rightly argues that where the science is clear, proclaiming the art of medicine is a poor excuse for doing something different.
In my mind, the Healthcare Services Platform Consortium should be focused on making the science of health care easily shareable and usable for all of health care regardless of EHR system. That’s a vision we should all get behind.