AI and predictive medicine: the plans of Clalit


In an interesting interview published in MobiHealthNews, Professor Ran Balicer, Clalit’s Chief Innovation Officer, explains the objectives of this organization for the coming years.

Clalit is one of Israel’s four mutual health insurance funds, which assists about half of the population. It provides primary care, local medicine and hospital care. It has had an electronic longitudinal medical record and a clinical data repository for over 20 years.

Thanks to the availability of an integrated repository, Clalit’s goal, undertaken over a decade ago, is to move from the paradigm of reactive care to predictive, proactive and preventive care.

Ran Balicer, in the interview with MobiHealthNews, explains how Clalit is trying to put predictive medicine into practice both in their GPs’ practice and in their hospital. The aim is to identify those patients who seem to be well and show no symptoms, but their laboratory tests and comorbidities and several other characteristics make them exposed to the risk of a disease or event. The idea is to provide this information directly to the doctor or patient and thus change the course of their treatment in order to avoid the event or disease.

Balicer mentions, for example, chronic kidney diseases which, if identified through symptoms, is too late and therefore the course of events cannot be changed too much. Through AI Clalit is able to identify people destined to become patients with renal failure five years before this happens, at a much lower cost and much fewer adverse events associated with the treatment. With this approach, followed by tens of thousands of people per year over the past eight years, Clalit has been able to stop the increase in new dialysis patients.

Balicer then cited an article published in Nature Medicine that shows how biomarkers of AI processed by CT scans can predict osteoporosis better than the best current models based on classical data.

Speaking then about the obstacles to the large-scale implementation of digital health, Balicer cites the fact that some of these innovations are not driven by the real needs of the medical community, but rather by a technology that seeks implementation and therefore does not solve a critical problem.

Balicer emphasizes how important it is that innovators work with doctors from the beginning to make sure that their idea is really useful to solve a problem. It is also important to consider and evaluate how the solution can be integrated into the clinical staff workflow. “If you expect your gadget or solution to be integrated when the clinician’s workload increases, then you might forget about it: this won’t work.

Finally, consider how and if it is possible to extend the solution on a large scale after the experimental phase. Research projects for their own sake are not useful for a health care organization.

The interview, which you can read here, contains other interesting insights.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s