University of Notre Dame computer science professor Nitesh Chawla and doctoral student Darcy Davis are using EHR data as a force for good with their newly developed Collaborative Assessment and Recommendation Engine (CARE), taking digital data and creating personalized patient risk assessment profiles to tailor medical care to the individual.
Data analytics is often seen as the next step in EHR adoption: once information is captured in a standardized, digital manner, it can be widened to create a rich portrait of the health of a whole population, or narrowed as far as predicting the risk of certain types of cancers for a specific person.
“The potential for ‘personalizing’ health care from a disease prevention, disease management and therapeutics perspective is increasing,” Chawla said. “Health care informatics and advanced analytics, or data science, may contribute to this shift from population-based evidence for health care decision-making to the fusion of population and individual based evidence in health care. The key question is: how to leverage health population data to drive patient-centered health care?”
CARE uses a collaborative filtering method to generate predictions based on the outcomes of similar patients. As the collection of deidentified patient records grows, more detailed and accurate predictions can be produced. At the very least, Chawla says, CARE can be used to generate reminders for physicians to investigate diseases that might not immediately come to mind, conduct health screenings, and suggest wellbeing strategies based on risk factors like obesity or smoking.
Used to its full capacity, CARE could also do so much more. “Imagine visiting your physician’s office with a list of concerns and questions,” he said. “What if you could walk out of the office with a personalized assessment of your health, along with a list of personalized and important lifestyle change recommendations based on your predicted health risks? What if your physician was afforded a limitless experience to gauge the impact of your disease toward developing other diseases in the future? What if you could find out that there are other patients similar to you not only with respect to major symptoms, but also with respect to rare issues that have puzzled your doctor? What if you could have the experience of others at your fingertips and fathom the lifestyle changes warranted for mitigating diseases?”
As patients become more engaged with their own care and medicine moves towards a holistic, collaborative, accountable model, CARE and other analytics engines could be valuable tools in the quest to reduce healthcare costs and keep patients healthier for longer. “This system can help bend the cost curve,” Chawla asserts. “We believe that our work can lead to reduced re-admission rates, improved quality of care ratings and can demonstrate meaningful use, impact personal and population health, and push forward the discussion and impact on the patient-centered paradigm.”