To innovate in population health, start with the essentials
Many companies have touted the promise of population health or the ability to influence the health outcomes of a group of people. But the process of getting there, from collecting data to changing individual behaviors, can be tricky.
During a panel at MedCity INVEST Pop Health, executives from two companies discussed how to collect data for population health and implement effective solutions.
Earlier in his career, Innovaccer’s chief innovation officer, Dr Anil Jain, opened his own primary care practice. At first, he mostly thought of each patient one at a time.
“It didn’t get to the point until we started to amass this data from the EHRs that we really started to think about what the overall population looks like? ” he said. âInstead of my one diabetic patient, can we see all 236? “
Of course, viewing patients as a group comes with its own compromises. For example, how do you consolidate health information from multiple people, while keeping it confidential? And at the same time, how do you keep track of who’s who, since there is no unique patient identifier in the United States?
Jain said there are solutions for identity management, like asking patients questions to verify their identity, or creating systems that can help match certain details, but there are still “huge problems. around identity management and a single patient record “.
Beyond the identity of the patient, there are other things that must be verified before the data can be compared. For example, if a doctor wrote “PC” in a note, was that referring to chest pain or cerebral palsy?
âA lot of innovators spend a ridiculous amount of time cleaning up the data and in the same terminologies as another set of data so that they can start to understand the meaning,â he said.
Another piece of the puzzle is actually making this information actionable. Some companies have turned to machine learning as a single approach, but Jain and Patientory CEO Chrissa McFarlane said they need to approach this issue with caution. While many of these tools are used by hospitals and payers, “the challenge with AI that continually arises is the fairness and bias around AI,” McFarlane said.
She added that it’s important to have more diversity of thinking in teams that develop software tools to improve results and to understand when to use that data.
For his part, Jain agreed that caution should be exercised and that AI should primarily be used for simpler tasks, rather than for the complex decision-making that a doctor would do.
Ultimately, “It’s not about data, it’s not even about analysis, it’s about changing people’s behavior,” he said.
Photo credit: elenabs, Getty Images