Using AI to Improve Individual and Population Health

At the intersection of public health and healthcare delivery, population health management analyzes population level data to identify opportunities to improve the quality, efficiency, and equity of care being provided. Population health management incorporates defining a population of individuals; recognizing the circumstances in which that population is born, grows, lives, works, and ages [1]; understanding the healthcare needs of that population; and offering interventions that are targeted to individuals within that population to optimize health.

Ninety percent of United States (US) healthcare expenditures are on people with chronic health conditions [2]. In 2018, 27.2% of the adult US population had least two of ten common major chronic conditions (arthritis, cancer, chronic obstructive pulmonary disease, current asthma, diabetes, hepatitis, hypertension, stroke, or weak or failing kidneys); 24.6% had one condition; and 48.2% had none; the proportion of those with at least one chronic condition is increasing [3].

These three populations have distinct population health management goals: to keep those without any chronic diseases (the healthy population) disease-free; to manage those with one chronic medical disease (the moderately illness burdened population) so that either they enter the healthy population group, avoid additional chronic medical diseases, or do not develop sequelae of their chronic disease; and to maximize patient functionality, independence, and disease control among those with multiple chronic diseases (the substantially illness burdened population).