Commodity Data Analytics For Health Care

Predixion service could signal a trend for smaller health facilities.

Analytics are expensive and labor intensive; we need them to be routine and ubiquitous. I complained earlier this year that analytics are hard for health care providers to muster because there’s a shortage of analysts and because every data-driven decision takes huge expertise.

Currently, only major health care institutions such as Geisinger, the Mayo Clinic, and Kaiser Permanente incorporate analytics into day-to-day decisions. Research facilities employ analytics teams for clinical research, but perhaps not so much for day-to-day operations. Large health care providers can afford departments of analysts, but most facilities — including those forming accountable care organizations — cannot.

Imagine that you are running a large hospital and are awake nights worrying about the Medicare penalty for readmitting patients within 30 days of their discharge. Now imagine you have access to analytics that can identify about 40 measures that combine to predict a readmission, and a convenient interface is available to tell clinicians in a simple way which patients are most at risk of readmission. Better still, the interface suggests specific interventions to reduce readmissions risk: giving the patient a 30-day supply of medication, arranging transportation to rehab appointments, etc.

A system of just this type was developed by the Carolinas HealthCare System, based on hundreds of thousands of patient experiences with the help of the analytics vendor Predixion. What’s special is that Predixion is now offering this solution in a generalized way to other health care institutions.

Crucially, the solution is not a canned set of predictions based on old analytics. Although Carolinas HealthCare System uses Cerner to store patient data, the Predixion solution can integrate with whatever EHR its client uses and capture new data to update predictions. (Boston’s readmissions risks differ from those in the Carolinas, and even the risks in the Carolinas differ from what they were two years ago.) Predixion can even host the data provided by the institution and run the analytics on its own cloud or using Salesforce’s Wave analytics platform.

Nish Hartman, director of Healthcare Solutions at Predixion, told me they are working on new telehealth services as well. As they move into new health care markets, they encounter providers who are not as well integrated as Carolinas HealthCare System. Hospitals will need stronger bonds with primary care physicians, nursing homes, and other institutions who bear the responsibility for keeping patients out of the hospital once they are released.

I see this service as not just a lithe business move by Predixion and Salesforce, but a step toward the universal application of analytics that many reformers in the health care field have been waiting for. Medicare’s 30-day rule is a useful prod to get the health care industry more concerned in general about long-term results. When analytics prove their value here, they can start to be applied to other hot spots and high-cost patient populations. Eventually, we could have off-the-shelf tools for all health care providers to manage patients intelligently — or even to provide individuals access to their own patient health records to manage themselves.

Commodity Data Analytics For Health Care was authored by Andy Oram and published in O'Reilly Radar. It is being republished by Open Health News under the terms of the Creative Commons License. The original copy of the article can be found here.