From the January/February 2016 issue of HealthCare Business News magazine
By: Bipin Thomas
Dear Readers, In 2016 I intend to share fresh perspectives and advise on how technology is shaping the new consumer-driven health information economy. I anticipate you will benefit from this under the new name "Technology Advisor." The face of long-term care for chronically ill patients takes on a new look with each passing year, as digital care management organizations come alongside primary care providers with an extra set of hands and a panoply of technological advances. Such relationships will both take up the slack left by the predicted decrease in the doctor-to-patient ratio and push the envelope of what is possible for care prevention, with efforts extending beyond the clinic. Of particular import with regard to these changes in the health care landscape is the proper implementation of digital technology, devices, and the requisite data analysis, which promise to provide essential and unprecedented patient data. In order to use these data successfully, digital health providers must develop metrics and methods to proactively achieve each individual’s health care goals, not only by tracking, but also predicting patient outcomes.
Medical device data and care management guidelines
As digital care management companies pursue for its patient cohorts, the extant health care standards laid out for each condition, including chronic congestive heart failure, obstructive pulmonary disorder and diabetes, ought to serve as the foundation for predictive metric development. The American Heart Association (AHA), The American Diabetes Association (ADA), and the Global Initiative for Chronic Obstructive Lung Disease (GOLD) publish care management guidelines that include risk assessment metrics and categorization. Each of these patient risk profiles is accompanied by further guidance concerning how to effectively provide care for each patient based on their categorization and the predicted risk for deleterious outcomes.
A staple among the differential diagnoses for each of these stages is the use of medical device data, including blood pressure, exhalation measures and blood glucose. As digital health companies already deploy devices measuring these same biological indicators, differential characterization and monitoring of patients with respect to these guidelines may provide additional insights into the predictive quality of these guidelines. The guidance published by these institutions thus provides an intra-cohort basis for the efficacy of patient risk identification and outcome prediction, against which to test additional metrics. Therefore, the two-part question driving the issue at hand is:
