US 12,278,005 B2
Artificial-intelligence-based facilitation of healthcare delivery
Nancy J. Cossler, Solon, OH (US); Jeffrey Alan Beers, Columbia Station, OH (US); and Steven Mattlin, Cleveland, OH (US)
Assigned to University Hospitals Cleveland Medical Center, Cleveland, OH (US)
Filed by University Hospitals Cleveland Medical Center, Cleveland, OH (US)
Filed on Aug. 2, 2022, as Appl. No. 17/816,867.
Application 17/816,867 is a continuation of application No. 15/900,009, filed on Feb. 20, 2018, granted, now 11,437,125.
Application 15/900,009 is a continuation in part of application No. 14/304,593, filed on Jun. 13, 2014, granted, now 10,529,445, issued on Jan. 7, 2020.
Prior Publication US 2022/0383998 A1, Dec. 1, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G16H 10/60 (2018.01); G06N 20/00 (2019.01); G16H 50/30 (2018.01); G16H 50/50 (2018.01); G16H 50/70 (2018.01)
CPC G16H 10/60 (2018.01) [G16H 50/50 (2018.01); G06N 20/00 (2019.01); G16H 50/30 (2018.01); G16H 50/70 (2018.01)] 18 Claims
OG exemplary drawing
 
1. A system, comprising:
a memory that stores computer executable components;
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a monitoring component that monitors live feedback information received over a current course of care of a patient, wherein the live feedback information comprises physiological information regarding a physiological state of the patient and workflow information regarding medical treatment provided to the patient in association with a defined clinical workflow for the current course of care, wherein the workflow information comprises clinician information regarding one or more clinicians responsible for treating the patient in association with the current course of care, including identities of the one or more clinicians, a current level of fatigue of the one or more clinicians and a current workload of the one or more clinicians;
a model development component that employs one or more machine learning processes to:
analyze historical information comprising previously logged live feedback information for other patients to learn first correlations between historical events and conditions associated with historical courses of care for the other patients and the defined clinical workflow that caused a clinician to perform one or more responses and levels of risk associated with failure to provide the one or more responses, and second correlations between how varying fatigue levels and workloads of respective clinicians that performed the same or similar course of care impact the historical events and conditions, and
train one or more neural network models to classify the historical events or conditions as being significant or not significant based on the first and second correlations;
a significant event/condition identification that employs the one or more neural network models to classify current events or conditions associated with the current course of care as being significant or not significant based on the live feedback information; and
a notification component that generates a notification in response to a determination by the significant event/condition identification component that a current event or condition associated with the current course of care warrants a response based on the one or more neural network models classifying the current event or condition as being significant, the notification comprising information identifying the current event or condition and indicating the current event or condition warrants the response and provides the notification to a device associated with an entity involved with treating the patient in association with the current course of care.