# US 2020/0005948 A1 · Identifying patients undergoing treatment with a drug who may be misidentified as being at risk for abusing the treatment drug

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

- Number: US 2020/0005948 A1
- Document ID: US20200005948A1
- Status: Published application
- Kind: A1
- Application number: 16/126,537
- Filed: 2018-09-10
- Published: 2020-01-02
- Earliest claimed: 2018-06-29
- Assignees: Health Solutions Research, Inc.
- Applicants: Health Solutions Research, Inc.
- Inventors: Ajay Kumar Gupta; Ramani Peruvemba
- Web page: https://patentgrep.com/patent/US20200005948A1

## CPC

- G16H 70/40: relating to drugs, e.g. their side effects or intended usage
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/50: for simulation or modelling of medical disorders
- G16H 70/20: relating to practices or guidelines
- G16H 70/60: relating to pathologies
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Patients being treated successfully with a drug of abuse and at low risk for abusing the drug nevertheless may be at high risk of being misidentified as a high risk of abuse. These patients may need and benefit from treatment with the drug but restricted or cut off from the treatment altogether due to the misidentification and then abandoned. Evaluating a patient's risk of drug treatment change due to a category misidentification may include developing a model for identifying such abandoned patients, applying the model to data of a patient, and determining a patient risk score for the patient based on a result of applying the model.

## Claims

### Claim 1

A method to evaluate a patient's risk of drug treatment change due to a category misidentification, comprising:
acquiring data of a subject population (X);
identifying patients (Y) as a first subset of the subject population (X) based on at least one criterion;
identifying patients (Z) as a second subset of the subject population (X) based on a model;
determining a correlation between (Y) and (Z);
determining whether the correlation at least meets a predetermined threshold;
if the correlation does not at least meet the threshold, adjusting the model and repeating identifying patients (Z), determining a correlation between (Y) and (Z), and determining whether the correlation at least meets a predetermined threshold in accordance with the adjustment;
if the correlation at least meets the threshold, outputting the model;
applying the model to data of a patient; and
determining a patient risk score for the patient based on a result of the applying.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
incorporating the model in a healthcare records system.

### Claim 3 (depends on 1)

The method of claim 1,
wherein the subject population (X) is victims of drug overdose, attempted suicide, and fatal suicide.

### Claim 4 (depends on 3)

The method of claim 3,
wherein, in accordance with the model, the patients (Z) are identified as individuals in the subject population (X) who are or were undergoing treatment with a drug and at low risk for abuse of the drug.

### Claim 5 (depends on 4)

The method of claim 4,
wherein the risk for abuse of the drug is one or more of drug addiction, diversion of prescribed drugs, and drug overdose.

### Claim 6 (depends on 5)

The method of claim 5, wherein the drug is an opioid.

### Claim 7 (depends on 1)

The method of claim 1,
wherein the model includes structured and unstructured information;
wherein the unstructured information includes health system data; and
wherein outputting the adjusting the model includes feeding the adjusted model back to the clinician's electronic health records system.

### Claim 8 (depends on 1)

The method of claim 1, wherein the at least one criterion includes long-term pain management treatment which was one of tapered off or discontinued.

### Claim 9

A method to evaluate a patient's risk of drug treatment change due to a category misidentification, comprising:
determining a patient's risk of abuse of a painkilling drug based on a model;
determining whether the patient's risk of abuse of the painkilling drug is relatively high or relatively low based on a standard;
if the patient's risk of abuse of the painkilling drug is determined to be relatively low, indicating referral of the patient for treatment with the painkilling drug;
outputting the model;
applying the model to data of a patient; and
determining a patient risk score for the patient based on a result of the applying.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
adjusting the model based on feedback from the treatment.

### Claim 11 (depends on 10)

The method of claim 10,
wherein the model includes structured and unstructured information;
wherein the unstructured information includes a clinician's notes; and
wherein adjusting the model includes feeding the adjusted model back to the clinician's electronic health records system.

### Claim 12 (depends on 9)

The method of claim 9, further comprising:
incorporating the model in a healthcare records system.

### Claim 13 (depends on 9)

The method of claim 9,
wherein the risk of abuse of the drug is one or more of drug addiction, diversion of prescribed drugs, and drug overdose.

### Claim 14 (depends on 13)

The method of claim 13, wherein the drug is an opioid.

### Claim 15

A non-transitory computer-readable medium having computer-readable instructions that, if executed by a computing device, cause the computing device to perform operations comprising:
acquiring data of a population (X);
identifying patients (Y) as a first subset of population (X) based on at least one criterion;
identifying patients (Z) as a second subset of population (X) based on a model;
determining a correlation between (Y) and (Z);
determining whether the correlation at least meets a predetermined threshold;
if the correlation does not at least meet the threshold, adjusting the model and repeat identifying patients (Z), determining a correlation between (Y) and (Z), and determining whether the correlation at least meets a predetermined threshold in accordance with the adjustment;
if the correlation at least meets the threshold, outputting the model;
applying the model to data of a patient; and
determining a patient risk score for the patient based on a result of the applying.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15,
wherein the subject population (X) is victims of drug overdose, attempted suicide, and fatal suicide.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15,
wherein, in accordance with the model, the patients (Z) are identified as individuals in the subject population (X) who are or were undergoing treatment with a drug and at low risk for abuse of the drug.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15,
wherein the risk for abuse of the drug is one or more of drug addiction, diversion of prescribed drugs, and drug overdose.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the drug is an opioid.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15,
wherein the model includes structured and unstructured information;
wherein the unstructured information includes a clinician's notes; and
wherein outputting the adjusting the model includes feeding the adjusted model back to the clinician's electronic health records system.
