Methods, systems, and computer program products using artificial intelligence for coordinated identification of patients for a clinical trial based on social determinants of health information

Patent metadata

Field	Value
Publication number	US-12555652-B2
Application number	US-202117644687-A
Country	US
Kind code	B2
Filing date	Dec 16, 2021
Priority date	Mar 31, 2021
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

A method includes obtaining patient medical record information from a plurality of providers until a demographic profile of patients associated with the patient medical record information meets a desired demographic profile; querying the patient medical record information using selection criteria to identify a first subset of patients having first characteristics that match first screening requirements for a clinical trial; identifying, using an artificial intelligence engine, ones of the first subset of patients whose medical record information includes second characteristics that match second screening requirements for the clinical trial as clinical trial patient candidates; and communicating identities of the clinical trial patient candidates to ones of the plurality of providers that provide healthcare services to the clinical trial patient candidates, respectively. The plurality of providers are associated with a plurality of different organizational managing entities, respectively.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
obtaining, by one or more processors, patient medical record information from a set of providers until a set of demographic profiles of patients associated with the patient medical record information meets a desired demographic profile, wherein the set of demographic profiles and the desired demographic profile are based on a set of social determinants of health (SDOH) factors including at least one of: income, number of employers, transportation mode used, proximity to polluted air, proximity to polluted water, language competency, literacy status, access to nutritious foods, or access to physical activity opportunities; querying, by the one or more processors, the patient medical record information obtained from the set of providers using one or more selection criteria to determine a first subset of patients having one or more first characteristics that match one or more first screening requirements for a clinical trial; determining, by the one or more processors, using an artificial intelligence engine, a second subset of the first subset of patients associated with medical record information that includes one or more second characteristics that match one or more second screening requirements for the clinical trial as clinical trial patient candidates, wherein a neural network of the artificial intelligence engine is trained based at least in part on the one or more second screening requirements and determines the first subset of patients; and transmitting, via a communication network, identities of the clinical trial patient candidates to a subset of the set of providers, the subset of providers being associated with at least two different organizational managing entities wherein the neural network comprises a set of featurization layers and a set of classification layers, wherein determining, by the one or more processors, the second subset of the first subset of patients associated with medical record information that includes the one or more second characteristics that match the one or more second screening requirements for the clinical trial as the clinical trial patient candidates further comprises:
performing, by the set of featurization layers performing, an encoding technique and an embedding technique to generate, based at least in part on a first subset of the patient medical information associated with the first subset of patients that includes structured data, a categorical value information input vector and a sequence of categorical value information input vector;
concatenating, by the set of featurization layers, the first subset of the patient medical information associated with the first subset of patients with the categorical value information input vector and the sequence of categorical value information input vector to generate a first vector representation;
generating, by the set of classification layers and based at least in part on the first vector representation, a first output;
generating, by the one or more processors and via a content similarity engine performing a natural language processing technique, a second output by comparing a second vector representation of a second subset of the patient medical information that includes unstructured text with the one or more second screening requirements including applying a natural language processing technique to the second subset of the patient medical information to generate segments containing sequences of words, weighting the words based on importance of the words with respect to a respective segment and importance of the words with respect to all of the segments, and performing a weighted comparison of the second vector representation of the second subset of the patient medical information with the one or more second screening requirements;
merging, by the one or more processors, the first output and the second output into a third output; and
determining, by the one or more processors, the second subset of the first subset of patients based on the third output including excluding or refraining from selecting a third subset of the first subset of patients based on the third output.

2 . The computer-implemented method of claim 1 , wherein the desired demographic profile comprises a set of weights corresponding to the set of SDOH factors, respectively, the set of weights representing a relative importance of the set of SDOH factors to each other.

3 . The computer-implemented method of claim 1 , wherein the set of SDOH factors is represented numerically, the computer-implemented method further comprising:
obtaining, by the one or more processors, SDOH factor information for the patients associated with the patient medical record information; receiving, by the one or more processors, desired SDOH factor information; determining, by the one or more processors, a first numeric demographic profile score for the patients associated with the patient medical record information based on the SDOH factor information and a set of weights; determining, by the one or more processors, a second numeric demographic profile score based on the desired SDOH factor information and the set of weights; and comparing, by the one or more processors, the first numeric demographic profile score with the second numeric demographic profile score to determine whether the set of demographic profiles of patients associated with the patient medical record information meets the desired demographic profile.

4 . The computer-implemented method of claim 1 , wherein the one or more first screening requirements define a set of individual thresholds for one or more of the one or more selection criteria and a matching threshold for a subset of the set of individual thresholds that must be met to match, and
wherein at least one of: the one or more first screening requirements indicate a first set of individual thresholds for one or more of the first characteristics and a matching threshold for a subset of the first set of individual thresholds that must be met to match; or the one or more second screening requirements indicate a second set of individual thresholds for one or more of the second characteristics and a matching threshold for a subset of the second set of individual thresholds that must be met to match.

5 . The computer-implemented method of claim 1 , wherein the one or more selection criteria comprise at least one of demographic information, one or more diagnosis codes, laboratory test values, medication names, scores for one or more cognitive tests, medical professional observations, acute condition names, chronic condition names, or allergy names.

6 . The computer-implemented method of claim 1 , wherein the set of providers is a first set of providers, the computer-implemented method further comprising:
receiving, by the one or more processors, patient claim information associated with a second set of providers, a number of the second set of providers being greater than a number of the first set of providers; and querying, by the one or more processors, the patient claim information of the second set of providers using demographic information, one or more diagnosis codes, and/or pharmacy information to identify the first set of providers having patients with third characteristics that match third screening requirements for the clinical trial.

7 . The computer-implemented method of claim 6 , further comprising:
receiving, by the one or more processors, a communication from the first set of providers opting in to participating in the clinical trial.

8 . The computer-implemented method of claim 6 , further comprising:
discarding, by the one or more processors, a second subset of the first set of providers havin

Assignees

• Change Healthcare Holdings Llc

Inventors

• Skees Daniel
• Mondal Sanjoy
• Fidow Mark
• Morris V Scott
• Mushtaq Faisal

Classifications

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H40/20

  for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms · CPC title

• G16H10/20 Primary

  for electronic clinical trials or questionnaires · CPC title