US 12,217,876 B2
Method for recommending continuing education to health professionals based on patient outcomes
Maria Levis, San Juan, PR (US)
Assigned to IMPACTIVO, LLC, San Juan, PR (US)
Filed by IMPACTIVO, LLC, San Juan, PR (US)
Filed on Mar. 18, 2022, as Appl. No. 17/655,515.
Application 17/655,515 is a continuation of application No. 16/282,910, filed on Feb. 22, 2019, granted, now 11,315,691.
Prior Publication US 2022/0215969 A1, Jul. 7, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G16H 70/20 (2018.01); G06Q 10/10 (2023.01); G16H 10/60 (2018.01); G16H 40/20 (2018.01); G16H 50/20 (2018.01); G16H 80/00 (2018.01)
CPC G16H 70/20 (2018.01) [G06Q 10/10 (2013.01); G16H 80/00 (2018.01); G16H 10/60 (2018.01); G16H 40/20 (2018.01); G16H 50/20 (2018.01)] 19 Claims
OG exemplary drawing
 
1. A method for providing continuing education to a health care professional comprising:
continually assessing, electronically, via a system application server, actual clinical performance of the health care professional as recorded in a clinical data system;
automatically creating a set of granules of health care knowledge in a database on a system application server, the set of granules of health care knowledge including information, skills, and aptitudes that are intended to improve performance of the health care provider;
training patient health risk factor machine learning models to generate patient health risk factor scores using social determinants and clinical data that correlate workflow assignment to patient outcomes;
training continuing education machine learning models with data from the trained patient risk factor machine learning models to identify which of the set of granules of health care knowledge is correlated with improved patient outcomes;
defining a set of configurable conditions on the system application server that use data from the clinical data system to trigger granule suggestions to the health care provider, wherein the configurable conditions include data from a specific one of the health care providers and data from one or more care teams to which the health care provider is assigned;
analyzing the actual clinical performance of the healthcare provider continually to determine whether the actual clinical performance falls within the defined configurable conditions;
using the trained continuing education machine learning models to deploy knowledge granules in accordance with the learner's preferences and learning styles; and
electronically delivering the health care knowledge granule based on established preferences of the health care provider automatically.