# US 2013/0085980 A1 · Systems and methods of predicting a subject's medical outcome

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

- Number: US 2013/0085980 A1
- Document ID: US20130085980A1
- Status: Published application
- Kind: A1
- Application number: 13/701,816
- Filed: 2011-06-06
- Published: 2013-04-04
- Earliest claimed: 2010-06-04
- Assignees: Georgetown University
- Inventors: Farrokh Alemi
- Web page: https://patentgrep.com/patent/US20130085980A1

## CPC

- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06Q 10/00: Administration; Management
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B 40/20: Supervised data analysis
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

Disclosed are methods of constructing systems for predicting a subject's medical outcome. Also disclosed are methods and systems for predicting a subject's medical outcome. The disclosed methods and systems can include identifying a group of subjects with the same medical condition and classifying this group of subjects into one or more subgroups. The subgroups are classified based on similarity of medical outcome, using classification and regression trees (CART) to generate a classification tree based on the presence of identifying genetic characteristics. Each node in the classification tree describes the presence of a specific genetic marker and each branch in the classification tree describes a genetic profile that predicts a subject's medical outcome.

## Claims

### Claim 1

A method of constructing a system for predicting a subject's medical outcome, comprising:
identifying a group of subjects with the same medical condition;
classifying the group of subjects with the same medical condition into one or more subgroups, wherein the one or more subgroups are classified based on similarity of medical outcome, using classification and regression trees (CART) to generate a classification tree based on the presence of identifying genetic characteristics and wherein each node in the classification tree describes the presence of a specific genetic marker and each branch in the classification tree describes a genetic profile that predicts a subject's medical outcome.

### Claim 2

A method for predicting a subject's medical outcome, comprising:
identifying a subject with a medical condition or at risk of acquiring a medical condition;
predicting the subject's medical outcome by comparing the subject's genetic profile with a set of control genetic profiles, wherein the control genetic profiles are generated from a group of subjects with the same disease using classification and regression trees (CART) based on the presence of identifying genetic characteristics and wherein each node in the classification tree describes the presence of a specific genetic marker and each branch in the classification tree describes a genetic profile into one or more subgroups, wherein the one or more subgroups are classified based on similarity of medical outcome, and wherein matching a subject's genetic profile to a branch in the classification tree predicts the subject's medical outcome.

### Claim 3

A system for predicting a subject's medical outcome, comprising:
identifying a group of subjects with the same disease;
classifying the group of subjects with the same disease into one or more subgroups, wherein the one or more subgroups are classified based on similarity of medical outcome, using classification and regression trees (CART) to generate a classification tree based on the presence of identifying genetic characteristics and wherein each node in the classification tree describes the presence of a specific genetic marker and each branch in the classification tree describes a genetic profile that predicts a subject's medical outcome.

### Claim 4 (depends on 2)

The method of claim 2, wherein CART comprises a 10 fold cross-validation and pruning factor of 1 to all unclassified cases to classify the subgroups into the branches of a tree.

### Claim 5 (depends on 4)

The method of claim 4, wherein CART is halted if none of the subgroups identified have a probability of positive or negative response significantly different from 0.05 (p-value≦0.10).

### Claim 6 (depends on 4)

The method of claim 4, wherein CART is boosted.

### Claim 7 (depends on 2)

The method of claim 2, wherein the method predicts medical outcome with at least about 65% accuracy.

### Claim 8 (depends on 2)

The method of claim 2, wherein the medical outcome is a disease progression.

### Claim 9 (depends on 2)

The method of claim 2, wherein the medical outcome is response to medical treatment.

### Claim 10 (depends on 9)

The method of claim 9, wherein the medical treatment is administration of a therapeutic agent.

### Claim 11 (depends on 10)

The method of claim 10, wherein the therapeutic agent is an antidepressant.

### Claim 12 (depends on 11)

The method of claim 11, wherein the antidepressant is citalopram.

### Claim 13 (depends on 12)

The method of claim 12, wherein the medical condition is depression.

### Claim 14 (depends on 13)

The method of claim 13, wherein the identifying genetic characteristics are the presence of single nucleotide polymorphisms (SNPs) rs7238368 and rs809736 in nucleolar protein 4 (NOL4) and rs10499638 in RAR-related orphan receptor A isoform a (RORA) indicating that the subject will not be responsive to the antidepressant.

### Claim at position 15

15-20. (canceled)

### Claim 21 (depends on 13)

The method of claim 13, wherein the identifying genetic characteristics are the presence of single nucleotide polymorphisms (SNPs) rs2697992 in retinoblastoma protein-binding zinc finger (PRDM2), rs6127921 in bone morphogenetic protein 7 precursor (BMP7), and rs6046805 in open reading frame C20orf26 indicating that the subject will be responsive to the antidepressant.

### Claim at position 17

22-25. (canceled)

### Claim 26 (depends on 3)

The system claim 3, wherein CART comprises a 10 fold cross-validation and pruning factor of 1 to all unclassified cases to classify the subgroups into the branches of a tree.

### Claim 27 (depends on 26)

The system of claim 26, wherein CART is halted if none of the subgroups identified have a probability of positive or negative response significantly different from 0.05 (p-value≦0.10).

### Claim 28 (depends on 27)

The system of claim 27, wherein CART is boosted.

### Claim 29 (depends on 3)

The system of claim 3, wherein the system predicts medical outcome with at least about 65% accuracy.

### Claim 30 (depends on 3)

The system of claim 3, wherein the medical outcome is response to citalopram.
