# US 2020/0286627 A1 · Systems and methods for treatment-effect analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0286627 A1
- Document ID: US20200286627A1
- Status: Published application
- Kind: A1
- Application number: 16/295,796
- Filed: 2019-03-07
- Published: 2020-09-10
- Earliest claimed: 2019-03-07
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Hyuna Yang
- Web page: https://patentgrep.com/patent/US20200286627A1

## CPC

- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 20/20: Ensemble learning
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 70/00: ICT specially adapted for the handling or processing of medical references
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and computer-implemented methods for analysis of medical literature to assemble synthetic cohorts are provided. In various embodiments, a plurality of literature sources relating to a medical condition are retrieved. The plurality of literature sources comprise published observational studies. A first plurality of features is extracted from the plurality of literature sources. A subpopulation is defined based on the first plurality of features. An effectiveness of a treatment within the subpopulation is predicted based on the plurality of features. A plurality of electronic medical records is retrieved. The effectiveness of the treatment is validated against the plurality of electronic medical records.

## Claims

### Claim 1

A computer-implemented method comprising:
retrieving a plurality of literature sources relating to a medical condition, the plurality of literature sources comprising published observational studies;
extracting a first plurality of features from the plurality of literature sources;
defining a subpopulation based on the first plurality of features;
predicting an effectiveness of a treatment within the subpopulation based on the plurality of features;
retrieving a plurality of electronic medical records;
validating the effectiveness of the treatment against the plurality of electronic medical records.

### Claim 2 (depends on 1)

The method of claim 1, wherein the electronic medical records comprise health data, insurance claim data, or registry data.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first plurality of features comprises disease definition, condition definition, outcome, standard of care, treatment, effectiveness, cohort definition, inclusion criteria, exclusion criteria, primary endpoint, secondary endpoint, potential modifier, one or more confounders, minimum sample size, or study duration.

### Claim 4 (depends on 1)

The method of claim 1, wherein predicting the effectiveness comprises applying a trained model to features of the subpopulation.

### Claim 5 (depends on 4)

The method of claim 4, wherein the model comprises an ensemble model.

### Claim 6 (depends on 1)

The method of claim 1, wherein extracting the first plurality of features comprises applying natural language processing to the plurality of literature sources.

### Claim 7 (depends on 1)

The method of claim 1, wherein validating the effectiveness of the treatment comprises determining a second plurality of features of the plurality of electronic medical records and comparing the effectiveness against those of the plurality of electronic medical records correlated with the first plurality of features.

### Claim 8

A system comprising:
a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:
retrieving a plurality of literature sources relating to a medical condition, the plurality of literature sources comprising published observational studies;
extracting a first plurality of features from the plurality of literature sources;
defining a subpopulation based on the first plurality of features;
predicting an effectiveness of a treatment within the subpopulation based on the plurality of features;
retrieving a plurality of electronic medical records;
validating the effectiveness of the treatment against the plurality of electronic medical records.

### Claim 9 (depends on 8)

The system of claim 8, wherein the electronic medical records comprise health data, insurance claim data, or registry data.

### Claim 10 (depends on 8)

The system of claim 8, wherein the first plurality of features comprises disease definition, condition definition, outcome, standard of care, treatment, effectiveness, cohort definition, inclusion criteria, exclusion criteria, primary endpoint, secondary endpoint, potential modifier, one or more confounders, minimum sample size, or study duration.

### Claim 11 (depends on 8)

The system of claim 8, wherein predicting the effectiveness comprises applying a trained model to features of the subpopulation.

### Claim 12 (depends on 11)

The system of claim 11, wherein the model comprises an ensemble model.

### Claim 13 (depends on 8)

The system of claim 8, wherein extracting the first plurality of features comprises applying natural language processing to the plurality of literature sources.

### Claim 14 (depends on 8)

The system of claim 8, wherein validating the effectiveness of the treatment comprises determining a second plurality of features of the plurality of electronic medical records and comparing the effectiveness against those of the plurality of electronic medical records correlated with the first plurality of features.

### Claim 15

A computer program product for treatment-effect analysis, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
retrieving a plurality of literature sources relating to a medical condition, the plurality of literature sources comprising published observational studies;
extracting a first plurality of features from the plurality of literature sources;
defining a subpopulation based on the first plurality of features;
predicting an effectiveness of a treatment within the subpopulation based on the plurality of features;
retrieving a plurality of electronic medical records;
validating the effectiveness of the treatment against the plurality of electronic medical records.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the electronic medical records comprise health data, insurance claim data, or registry data.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the first plurality of features comprises disease definition, condition definition, outcome, standard of care, treatment, effectiveness, cohort definition, inclusion criteria, exclusion criteria, primary endpoint, secondary endpoint, potential modifier, one or more confounders, minimum sample size, or study duration.

### Claim 18 (depends on 15)

The computer program product of claim 15, wherein predicting the effectiveness comprises applying a trained model to features of the subpopulation.

### Claim 19 (depends on 18)

The computer program product of claim 18, wherein the model comprises an ensemble model.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein validating the effectiveness of the treatment comprises determining a second plurality of features of the plurality of electronic medical records and comparing the effectiveness against those of the plurality of electronic medical records correlated with the first plurality of features.
