he MoBEMap algorithm combines data from claims, platform interactions, personal monitors, and social determinants of health to dynamically score each individual’s health risk. By monitoring risk levels in real time, MoBE can immediately react. Upon sensing rising risk, it works with the patient to shift health behaviors and bend back the risk curve, rather than waiting for the next doctor appointment or clinical interaction.
How does MoBE shift behavior? In addition to monitoring risk, the MoBEMap recognizes each person’s individual priorities, motivations, and abilities, calculating their unique behavioral propensities. This allows MoBE to prompt small health actions the patient can take to reduce risk and improve overall health. However, the algorithm is never static. The self-learning AI enhances the MoBEMap each time a patient interacts, refining messaging, delivery, frequency, and interaction to adapt to each individual. The MoBEMap will only trigger health actions that the patient is both willing and able to take. This is the key to precision nudging.
Does this work? The MoBEMap personal health algorithm has been calibrated through RCTs, pilots and deployments at scale– having produced results in real world trials in the US. Some of these results (excluding maternity) were presented at Scientific Sessions of the American Heart Association in 2019.