US 12,381,004 B2
Systems and methods for predicting health outcomes
Naiqian Zhi, Hartford, CT (US); Sarah Wohlman, Hartford, CT (US); Alex Xu, Hartford, CT (US); Ryan Berns, Hartford, CT (US); and Rajiv Bhan, Hartford, CT (US)
Assigned to Aetna Inc., Hartford, CT (US)
Filed by Aetna Inc., Hartford, CT (US)
Filed on Mar. 24, 2022, as Appl. No. 17/703,901.
Prior Publication US 2023/0307127 A1, Sep. 28, 2023
Int. Cl. G16H 50/20 (2018.01); G06F 40/40 (2020.01); G16H 10/60 (2018.01); G16H 40/20 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01)
CPC G16H 50/20 (2018.01) [G06F 40/40 (2020.01); G16H 10/60 (2018.01); G16H 40/20 (2018.01); G16H 40/67 (2018.01); G16H 50/30 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A system for predicting health outcomes, the system comprising:
a memory storing instructions; and
one or more processors that, responsive to executing the instructions, are configured to:
receive monitored parameter data from a wearable device;
obtain embedding data corresponding to a user registered to the wearable device;
process the monitored parameter data and the embedding data by a random forest model comprising a plurality of decision trees to generate a binary classification of the user, wherein each of the plurality of decision trees generates a decision tree classification based on the monitored parameter data and the embedding data, wherein the binary classification is a first classification based on a majority of the decision tree classifications being the first classification, and wherein the binary classification is a second classification based on a majority of the decision tree classifications being the second classification;
based on the user being classified according to the first classification, process the monitored parameter data and the embedding data by a gradient boosting machine (GBM) model to generate an index value indicating a health of the user that is registered to the wearable device;
based on the user being classified according to the second classification, assign the index value a minimum index value; and
perform an operation based on the index value.