# US 2018/0322256 A1 · Cirrhosis Forecasting In Human Subjects

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

- Number: US 2018/0322256 A1
- Document ID: US20180322256A1
- Status: Published application
- Kind: A1
- Application number: 15/587,245
- Filed: 2017-05-04
- Published: 2018-11-08
- Earliest claimed: 2017-05-04
- Assignees: Pinscriptive, Inc.
- Applicants: Pinscriptive, Inc.
- Inventors: Roni H. Amiel; Fuad Rahman
- Web page: https://patentgrep.com/patent/US20180322256A1

## CPC

- G16H 50/50: for simulation or modelling of medical disorders
- G06N 20/00: Machine learning
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- 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

## Abstract

A system for training a cirrhosis forecast model includes a computing platform having a hardware processor and a memory storing a software code for training the cirrhosis forecast model. The hardware processor executes the software code to receive medical data for each of multiple human subjects, assign a subset of the human subjects as a training group for the cirrhosis forecast model, and identify cirrhosis predictive parameters from the medical data for the training group. The hardware processor also executes the software code to generate a cirrhosis forecast model including a weighted combination of the cirrhosis predictive parameters, produce, using the cirrhosis forecast model, a cirrhosis prediction for at least one of the human subjects omitted from the training group, determine an accuracy of the cirrhosis prediction, and adapt the cirrhosis forecast model based on the accuracy of the cirrhosis prediction.

## Claims

### Claim 1

A system for training a cirrhosis forecast model, the system comprising:
a computing platform including a hardware processor and a memory;
a software code for training the cirrhosis forecast model stored in the memory; and
the hardware processor configured to execute the software code to:
receive a medical data for each of a plurality of human subjects;
assign a subset of the human subjects as a training group for the cirrhosis forecast model;
identify a plurality of cirrhosis predictive parameters from the medical data for the training group;
generate a cirrhosis forecast model including a weighted combination of the cirrhosis predictive parameters;
produce, using the cirrhosis forecast model, a cirrhosis prediction for at least one of the human subjects omitted from the training group;
determine an accuracy of the cirrhosis prediction; and
adapt the cirrhosis forecast model based on the accuracy of the cirrhosis prediction.

### Claim 2 (depends on 1)

The system of claim 1, wherein the hardware processor is further configured to execute the software code to adapt the cirrhosis forecast model by modifying at least one of a plurality of weighting factors included in the weighted combination of the cirrhosis predictive parameters.

### Claim 3 (depends on 1)

The system of claim 1, wherein the hardware processor is further configured to execute the software code to display the cirrhosis prediction to a system user.

### Claim 4 (depends on 3)

The system of claim 3, wherein the hardware processor is further configured to execute the software code to determine the accuracy of the cirrhosis prediction by receiving an accuracy evaluation data from the system user.

### Claim 5 (depends on 1)

The system of claim 1, wherein the training group includes cirrhotic subjects and non-cirrhotic subjects.

### Claim 6 (depends on 1)

The system of claim 1, wherein the training group is randomly assigned.

### Claim 7 (depends on 1)

The system of claim 1, wherein training group includes all of the plurality of human subjects except one.

### Claim 8

A method for use by a system for training a cirrhosis forecast model, the system including a computing platform having a hardware processor and a memory storing a software code for training the cirrhosis forecast model, the method comprising:
receiving, using the hardware processor, a medical data for each of a plurality of human subjects;
assigning, using the hardware processor, a subset of the human subjects as a training group for the cirrhosis forecast model;
identifying, using the hardware processor, a plurality of cirrhosis predictive parameters from the medical data for the training group;
generating, using the hardware processor, a cirrhosis forecast model including a weighted combination of the cirrhosis predictive parameters;
producing, using the hardware processor and the cirrhosis forecast model, a cirrhosis prediction for at least one of the human subjects omitted from the training group;
determining, using the hardware processor, an accuracy of the cirrhosis prediction; and
adapting, using the hardware processor, the cirrhosis forecast model based on the accuracy of the cirrhosis prediction.

### Claim 9 (depends on 8)

The method of claim 8, wherein adapting the cirrhosis forecast model comprises modifying at least one of a plurality of weighting factors included in the weighted combination of the cirrhosis predictive parameters.

### Claim 10 (depends on 8)

The method of claim 8, further comprising displaying the cirrhosis prediction to a system user.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining the accuracy of the cirrhosis prediction comprises receiving an accuracy evaluation data from the system user.

### Claim 12 (depends on 8)

The method of claim 8, wherein the training group includes cirrhotic subjects and non-cirrhotic subjects.

### Claim 13 (depends on 8)

The method of claim 8, wherein the training group is randomly assigned.

### Claim 14 (depends on 8)

The method of claim 8, wherein training group includes all of the plurality of human subjects except one.

### Claim 15

A computer-readable non-transitory medium having stored thereon instructions, which when executed by a hardware processor, perform a method comprising:
receiving a medical data for each of a plurality of human subjects;
assigning a subset of the human subjects as a training group for the cirrhosis forecast model;
identifying a plurality of cirrhosis predictive parameters from the medical data for the training group;
generating a cirrhosis forecast model including a weighted combination of the cirrhosis predictive parameters;
producing, using the cirrhosis forecast model, a cirrhosis prediction for at least one of the human subjects omitted from the training group;
determining an accuracy of the cirrhosis prediction; and
adapting the cirrhosis forecast model based on the accuracy of the cirrhosis prediction.

### Claim 16 (depends on 15)

The computer-readable non-transitory medium of claim 15, wherein adapting the cirrhosis forecast model comprises modifying at least one of a plurality of weighting factors included in the weighted combination of the cirrhosis predictive parameters.

### Claim 17 (depends on 15)

The computer-readable non-transitory medium of claim 15, wherein the method further comprises displaying the cirrhosis prediction to a system user.

### Claim 18 (depends on 17)

The computer-readable non-transitory medium of claim 17, wherein determining the accuracy of the cirrhosis prediction comprises receiving an accuracy evaluation data from the system user.

### Claim 19 (depends on 15)

The computer-readable non-transitory medium of claim 15, wherein the training group is randomly assigned.

### Claim 20 (depends on 15)

The computer-readable non-transitory medium of claim 15, wherein training group includes all of the plurality of human subjects except one.