US 12,462,911 B2
Clinical concept identification, extraction, and prediction system and related methods
Michael Lucas, Chicago, IL (US); Jonathan Ozeran, Chicago, IL (US); Jason Taylor, Chicago, IL (US); and Louis Fernandes, Chicago, IL (US)
Assigned to TEMPUS AI, INC., Chicago, IL (US)
Filed by TEMPUS AI, INC., Chicago, IL (US)
Filed on Mar. 19, 2021, as Appl. No. 17/207,582.
Application 17/207,582 is a continuation of application No. 16/702,510, filed on Dec. 3, 2019, granted, now 10,957,433.
Claims priority of provisional application 62/774,854, filed on Dec. 3, 2018.
Prior Publication US 2021/0210184 A1, Jul. 8, 2021
Int. Cl. G06F 40/30 (2020.01); G06F 40/295 (2020.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 15/00 (2018.01); G16H 70/00 (2018.01)
CPC G16H 15/00 (2018.01) [G06F 40/295 (2020.01); G06F 40/30 (2020.01); G16H 10/20 (2018.01); G16H 10/60 (2018.01); G16H 70/00 (2018.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining whether a subject may be enrolled into a clinical trial, the computer-implemented method comprising:
storing, via one or more processors, a plurality of abstraction categories in a database wherein each abstraction category includes a plurality of fields and each field corresponds to a concept type;
accessing, via one or more processors, a medical record of a subject from an electronic health record system wherein the medical record includes a plurality of text words;
deriving, via one or more processors, a plurality of first concepts from the medical record by:
(i) identifying, via one or more processors, a match to a first concept in the plurality of first concepts, the plurality of first concepts not designated as a predetermined authority and including two or more tiers of concepts;
(ii) referencing, via one or more processors, the first concept with an entity in a database of related concepts;
(iii) identifying, via one or more processors, a match from the entity to a second concept in a second list of concepts designated in the predetermined authority, wherein the second concept is included in one of the two or more tiers of concepts, and wherein the predetermined authority is not directly linked to the plurality of first concepts except by a relationship to the entity;
(iv) retrieving, via one or more processors, a degree of specificity comprising selection criteria identifying one or more tiers of the two or more tiers of concepts, other than the one tier including the second concept; and
(v) normalizing, via one or more processors, the second concept to a third concept, of a plurality of third concepts, included in the one or more tiers of the two or more tiers of concepts, based at least in part on the second concept not satisfying the selection criteria;
comparing, via one or more processors, a list of study criteria associated with the clinical trial to the plurality of third concepts, to indicate if the subject meets the list of study criteria; and
generating, via one or more processors, an indication of eligibility of the subject for enrollment in the clinical trial based on the comparing.