Princeton University’s Department of Operations Research and Financial Engineering has teamed up with ODH, a health tech company that provides analytics solutions, to jointly research and develop machine learning techniques focused on the mental and social factors impacting patients.
Princeton, New Jersey-based ODH caters to the needs of health plans by helping them improve outcomes for their members, ODH president and CEO Michael Jarjour explained in a recent phone interview. The company, which is affiliated with Japanese conglomerate Otsuka Group, takes patient population data and pinpoints behaviors that can be modified.
With the Rise of AI, What IP Disputes in Healthcare Are Likely to Emerge?
Munck Wilson Mandala Partner Greg Howison shared his perspective on some of the legal ramifications around AI, IP, connected devices and the data they generate, in response to emailed questions.
Jarjour said the origins of the collaboration with Princeton date back to more or less one year ago. The university was an attractive partner for ODH due to its well-respected capabilities and nearby location.
“We’re taking their expertise in data science and math combined with our expertise in the clinical environment,” Jarjour said.
The ML techniques the organizations are developing will allow payers to examine the mental and social health factors of their members’ conditions and suggest potential interventions.
For example, a patient may show up at her doctor’s office with a swollen abdomen and nausea. She could then receive a diagnosis of liver failure. But that’s only part of the picture. This Princeton-ODH project will take it one step further by identifying other factors impacting the patient, such as whether she has transportation issues, alcohol addiction or other social challenges.
A Personalized Approach to Medication Nonadherence
At the Abarca Forward conference earlier this year, George Van Antwerp, managing director at Deloitte, discussed how social determinants of health and a personalized member experience can improve medication adherence and health outcomes.
The machine learning technique will also give care coordinators recommendations for the most effective interventions, like setting up transportation or referring the patient to a substance abuse treatment program.
Jarjour summarized the project rather simply: It’s about treating the patient holistically.
“Many of these capabilities already exist, but we are trying to significantly enhance them, hence the desire to work with Princeton University,” he said.
In a news release, Samory Kpotufe, assistant professor of operations research and financial engineering, put it this way:
Given the expertise of ODH in healthcare technology, we are looking forward to a fruitful collaboration. Confronting the challenges of machine learning for healthcare is bound to generate a rich set of research questions with potential impact beyond the healthcare domain.
Photo: nambitomo, Getty Images
