CPC G16H 50/20 (2018.01) [G06N 20/00 (2019.01); G16H 70/20 (2018.01)] | 18 Claims |
1. A method for intelligent collaborative generation or enhancement of useful medical actions by a processor, comprising:
receiving medical and non-medical data associated with both a user and similar users;
executing machine learning logic to train a recommendation model with the medical and non-medical data;
recommending one or more useful medical actions, with evidence in support thereof, for impacting a health state of the user according to the recommendation model;
in conjunction with the recommending, enabling one or more domain experts to vote on a degree of applicability, a degree of effectiveness, or a combination thereof of the one or more useful medical actions for the user, wherein the voting is used as feedback to progressively refine the recommendation model;
matching the one or more useful medical actions to one or more selected portions of clinical practice guidelines (CPGs); and
adding the one or more useful medical actions as an additional CPG or as an enhancement according to the matching.
|