# US 2021/0173679 A1 · Training a machine learning module and updating a rules engine to determine medical best practice recommendations for user entered medical observations

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

- Number: US 2021/0173679 A1
- Document ID: US20210173679A1
- Status: Published application
- Kind: A1
- Application number: 17/180,678
- Filed: 2021-02-19
- Published: 2021-06-10
- Earliest claimed: 2018-06-28
- Assignees: Radiology Partners, Inc.
- Applicants: Radiology Partners, Inc.
- Inventors: Nina KOTTLER; Thomas N. TOBIAS; Jason R. MITSKY; Joyce LIANG; Kelly DENNEY; Kevin CROXALL; Telford BERKEY; Jai SALZWEDEL
- Web page: https://patentgrep.com/patent/US20210173679A1

## CPC

- G06F 9/451: Execution arrangements for user interfaces
- G06F 16/285: {Clustering or classification}
- G06F 16/353: into predefined classes
- G06F 40/174: Form filling; Merging
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/046: Forward inferencing; Production systems
- G06N 20/00: Machine learning
- G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H 40/63: for local operation
- 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
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/025: Extracting rules from data
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Provided are a computer program product, system, and method for determining real-time changes to content entered into a user interface to generate results for the content. In response to determining that entry of first content in a user input field rendered in a user interface is completed, the first content is provided to a classification program to classify into a first machine classification to provide to a rules engine to determine a first machine determined proposition. The first machine determined proposition is rendered in the user interface. A determination is made of second content in the user input field from the user that differs from the first content. The second content is provided to the classification program to classify into a second machine classification to provide to the rules engine to determine a second machine determined proposition rendered in the user interface with the second content.

## Claims

### Claim at position 1

1-22. (canceled)

### Claim 23

A computer program product for determining medical best practice recommendations for user entered medical observations, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that is executable to perform operations, the operations comprising:
receiving a medical observation of a patient from a user;
processing, by a classification program, implementing a machine learning module, the received medical observation to classify into a medical finding based on the received medical observation;
processing, by a rules engine, comprising a data structure that provides best practice recommendations for each of possible medical findings outputted from the classification program, the medical finding to determine a medical best practice recommendation for the medical finding;
transmitting the medical finding and the medical best practice recommendation to render in a user interface;
receiving indication of the user rejecting the medical finding rendered in the user interface; and
training the machine learning module comprising the classification program to output a preferred medical finding, provided to replace the medical finding transmitted to the user interface, based on the medical observations, in response to receiving the user rejecting the medical finding.

### Claim 24 (depends on 23)

The computer program product of claim 23, wherein the operations further comprise:
receiving indication of the user rejecting the medical best practice recommendation; and
updating the rules engine to associate a preferred medical best practice recommendation with the medical finding rendered in the user interface in response to the receiving of the indication of the user rejecting the medical best practice recommendation for the medical finding without rejecting the medical finding, wherein the updated rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding.

### Claim 25 (depends on 24)

The computer program product of claim 24, wherein the operations further comprise:
updating the rules engine to not associate the medical best practice recommendation rendered in the user interface with the medical finding.

### Claim 26 (depends on 23)

The computer program product of claim 23, wherein the operations further comprise:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding and not to output the medical best practice recommendation for the medical finding in response to receiving the indication of the user rejecting the medical finding and rejecting the medical best practice recommendation.

### Claim 27 (depends on 23)

The computer program product of claim 23, wherein the operations further comprise:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding in response to the receiving indication of the user rejecting the medical best practice recommendation and rejecting the medical finding rendered in the user interface.

### Claim 28 (depends on 27)

The computer program product of claim 27, wherein the preferred medical best practice recommendation and the preferred medical finding are received from the user when rejecting the medical best practice recommendation and the medical finding rendered in the user interface.

### Claim 29 (depends on 23)

The computer program product of claim 23, wherein the rules engine uses a decision tree of rules to determine the medical best practice recommendation for the medical finding, wherein the decision tree includes rules to map medical findings from the classification program to medical best practice recommendations to output one of the medical best practice recommendations based on one of the possible medical findings outputted by the classification program.

### Claim 30

A system for determining medical best practice recommendations for user entered medical observations, comprising:
a processor; and
a computer readable storage medium having computer readable program code embodied that when executed by the processor performs operations, the operations comprising: receiving a medical observation of a patient entered into a user interface;
receiving a medical observation of a patient from a user;
processing, by a classification program, implementing a machine learning module, the received medical observation to classify into a medical finding based on the received medical observation;
processing, by a rules engine, comprising a data structure that provides best practice recommendations for each of possible medical findings outputted from the classification program, the medical finding to determine a medical best practice recommendation for the medical finding;
transmitting the medical finding and the medical best practice recommendation to render in the user interface;
receiving indication of the user rejecting the medical finding rendered in the user interface; and
training the machine learning module comprising the classification program to output a preferred medical finding, provided to replace the medical finding transmitted to the user interface, based on the medical observations, in response to receiving the user rejecting the medical finding.

### Claim 31 (depends on 30)

The system of claim 30, wherein the operations further comprise:
receiving indication of the user rejecting the medical best practice recommendation; and
updating the rules engine to associate a preferred medical best practice recommendation with the medical finding rendered in the user interface in response to the receiving the indication of the user rejecting the medical best practice recommendation for the medical finding without rejecting the medical finding, wherein the updated rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding.

### Claim 32 (depends on 31)

The system of claim 31, wherein the operations further comprise:
updating the rules engine to not associate the medical best practice recommendation rendered in the user interface with the medical finding.

### Claim 33 (depends on 30)

The system of claim 30, wherein the operations further comprise:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding and not to output the medical best practice recommendation for the medical finding in response to receiving the indication of the user rejecting the medical finding and rejecting the medical best practice recommendation.

### Claim 34 (depends on 30)

The system of claim 30, wherein the operations further comprise:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding in response to the receiving indication of the user rejecting the medical best practice recommendation and rejecting the medical finding rendered in the user interface.

### Claim 35 (depends on 34)

The system of claim 34, wherein the preferred medical best practice recommendation and the preferred medical finding are received from the user when rejecting the medical best practice recommendation and the medical finding rendered in the user interface.

### Claim 36 (depends on 30)

The system of claim 30, wherein the rules engine uses a decision tree of rules to determine the medical best practice recommendation for the medical finding, wherein the decision tree includes rules to map medical findings from the classification program to medical best practice recommendations to output one of the medical best practice recommendations based on one of the possible medical findings outputted by the classification program.

### Claim 37

A computer implemented method for determining medical best practice recommendations for user entered medical observations, comprising:
receiving a medical observation of a patient from a user;
processing, by a classification program, implementing a machine learning module, the received medical observation to classify into a medical finding based on the received medical observation;
processing, by a rules engine, comprising a data structure that provides best practice recommendations for each of possible medical findings outputted from the classification program, the medical finding to determine a medical best practice recommendation for the medical finding;
transmitting the medical finding and the medical best practice recommendation to render in a user interface;
receiving indication of the user rejecting the medical finding rendered in the user interface; and
training the machine learning module comprising the classification program to output a preferred medical finding, provided to replace the medical finding transmitted to the user interface, based on the medical observations, in response to receiving the user rejecting the medical finding.

### Claim 38 (depends on 37)

The method of claim 37, further comprising:
receiving indication of the user rejecting the medical best practice recommendation; and
updating the rules engine to associate a preferred medical best practice recommendation with the medical finding rendered in the user interface in response to the receiving the indication of the user rejecting the medical best practice recommendation for the medical finding without rejecting the medical finding, wherein the updated rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding.

### Claim 39 (depends on 38)

The method of claim 38, further comprising:
updating the rules engine to not associate the medical best practice recommendation rendered in the user interface with the medical finding.

### Claim 40 (depends on 37)

The method of claim 37, further comprising:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding and not to output the medical best practice recommendation for the medical finding in response to receiving the indication of the user rejecting the medical finding and rejecting the medical best practice recommendation.

### Claim 41 (depends on 37)

The method of claim 37, further comprising:
updating the rules engine to provide a preferred medical best practice recommendation for the preferred medical finding in response to the receiving indication of the user rejecting the medical best practice recommendation and rejecting the medical finding rendered in the user interface.

### Claim 42 (depends on 38)

The method of claim 38, wherein the preferred medical best practice recommendation and the preferred medical finding are received from the user when rejecting the medical best practice recommendation and the medical finding rendered in the user interface.