# US 2020/0004561 A1 · User interface for determining real-time changes to content entered into the user interface to provide to a classifier program and rules engine to generate results for the content

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

- Number: US 2020/0004561 A1
- Document ID: US20200004561A1
- Status: Published application
- Kind: A1
- Application number: 16/022,581
- Filed: 2018-06-28
- Published: 2020-01-02
- 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/US20200004561A1

## 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 1

A computer program product for processing user entered medical observations in a user interface to obtain a best practice recommendation, 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:
rendering an entry of a first medical observation of a patient in a user input field in a user interface;
storing in a log file a first fingerprint of the first medical observation that uniquely identifies the first medical observation;
in response to determining that the entry of the first medical observation is completed, providing the first medical observation to a classification program, implementing a machine learning module, to classify into a first machine classification comprising a first medical finding based on the first medical observation to provide to a rules engine to apply a series of rules to determine a first medical best practice recommendation for the first machine classification;
rendering the first medical best practice recommendation in the user interface;
determining a second medical observation of the patient in the user input field;
generating a second fingerprint of the second medical observation that uniquely identifies the second medical observation;
determining whether the first fingerprint in the log file differs from the second fingerprint;
providing the second medical observation to the classification program to classify into a second machine classification comprising a second medical finding to provide to the rules engine to apply the series of rules to determine a second medical best practice recommendation for the second machine classification in response to determining that the first fingerprint in the log file differs from the second fingerprint; and
rendering the second medical best practice recommendation in the user interface.

### Claim 2

(canceled)

### Claim 3 (depends on 1)

The computer program product of claim 1, wherein the user input field comprises a first user input field, wherein the determining that the first medical observation is completed comprises detecting user input into a second input field in the user interface.

### Claim 4

(canceled)

### Claim 5 (depends on 1)

The computer program product of claim 1, wherein the user input field comprises a first user input field, and wherein the first and the second medical observations comprise user entered observations, wherein the operations further comprise:
receiving user input indicating a user medical finding of the user entered observations in a second user input field, wherein the classifier program additionally receives the user medical finding in the second user input field with the user entered medical observations in the first user input field to process to determine the first and the second medical findings to provide to the rules engine.

### Claim at position 6

6-9. (canceled)

### Claim 10 (depends on 1)

The computer program product of claim 1, wherein the operations further comprise:
indicating the first fingerprint as a previous fingerprint in the log file and the second fingerprint as a current fingerprint in the log file;
periodically processing the log file by:
indicating the current fingerprint as the previous fingerprint;
storing a medical observation as the current fingerprint
determining whether the current fingerprint calculated matches the previous fingerprint;
and
sending the current fingerprint to the classification program in response to the determining no matching to obtain a new medical best practice recommendation from the rules engine to provide real time updating of the new medical best practice recommendation in the user interface.

### Claim 11

A system, 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:
rendering an entry of a first medical observation of a patient in a user input field in a user interface;
storing in a log file a first fingerprint of the first medical observation that uniquely identifies the first medical observation;
in response to determining that the entry of the first medical observation is completed, providing the first medical observation to a classification program, implementing a machine learning module, to classify into a first machine classification comprising a first medical finding based on the first medical observation to provide to a rules engine to apply a series of rules to determine a first medical best practice recommendation for the first machine classification;
rendering the first medical best practice recommendation in the user interface;
determining a second medical observation of the patient in the user input the user;
generating a second fingerprint of the second medical observation that uniquely identifies the second medical observation;
determining whether the first fingerprint in the log file differs from the second fingerprint;
providing the second medical observation to the classification program to classify into a second machine classification comprising a second medical finding to provide to the rules engine to apply the series of rules to determine a second medical best practice recommendation for the second machine classification in response to determining that the first fingerprint in the log file differs from the second fingerprint; and
rendering the second medical best practice recommendation in the user interface.

### Claim 12

(canceled)

### Claim 13 (depends on 11)

The system of claim 11, wherein the user input field comprises a first user input field, and wherein the first and the second medical observations comprise user entered observations, wherein the operations further comprise:
receiving user input indicating a user medical finding of the user entered medical observations in a second user input field, wherein the classifier program additionally receives the user medical finding in the second user input field with the user entered medical observations in the first user input field to process to determine the first and the second medical findings to provide to the rules engine.

### Claim at position 11

14-16. (canceled)

### Claim 17

A computer implemented method for processing user content entered in a user interface rendered in a computer display to obtain machine determined information, comprising:
rendering an entry of a first medical observation of a patient in a user input field in a user interface;
storing in a log file a first fingerprint of the first medical observation that uniquely identifies the first medical observation;
in response to determining that the entry of the first medical observation is completed, providing the first medical observation to a classification program, implementing a machine learning module, to classify into a first machine classification comprising a first medical finding based on the first medical observation to provide to a rules engine to apply a series of rules to determine a first medical best practice recommendation for the first machine classification;
rendering the first medical best practice recommendation in the user interface;
determining a second medical observation of the patient in the user input field;
generating a second fingerprint of the second medical observation that uniquely identifies the second medical observation;
determining whether the first fingerprint in the log file differs from the second fingerprint;
providing the second medical observation to the classification program to classify into a second machine classification comprising a second medical finding to provide to the rules engine to apply the series of rules to determine a second medical best practice recommendation for the second machine classification in response to determining that the first fingerprint in the log file differs from the second fingerprint; and
rendering the second medical best practice recommendation in the user interface.

### Claim 18

(canceled)

### Claim 19 (depends on 17)

The method of claim 17, wherein the user input field comprises a first user input field, and wherein the first and the second medical observations comprise user entered observations, further comprising:
receiving user input indicating a user medical finding of the user entered medical observations in a second user input field, wherein the classifier program additionally receives the user medical finding in the second user input field with the user entered medical observations in the first user input field to process to determine the first and the second medical findings to provide to the rules engine.

### Claim at position 15

20-22. (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 entered into a user input field in a user interface;
providing the medical observation to a classification program implemented as a machine learning module to classify into a machine classification comprising a medical finding based on the medical observations to provide to a rules engine to apply a series of rules 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 user indication of rejecting at least one of the medical finding from the machine learning module and the rendered best practice recommendation;
receiving at least one of a preferred medical finding for the medical observations and a preferred medical best practice recommendation in response to the user indication of rejecting;
training the machine learning module comprising the classification program to output the preferred medical finding based on the medical observations in response to receiving the preferred medical finding; and
updating the rules engine to associate the preferred medical best practice recommendation for the medical finding rendered in the user interface in response to receiving the preferred medical best practice recommendation for the medical finding, wherein the rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding rendered in the user interface.

### Claim 24 (depends on 23)

The computer program product of claim 23, wherein the receiving at least one of the preferred medical finding and the preferred medical best practice recommendation comprises receiving both the preferred medical finding and the preferred medical best practice recommendations, wherein the operations further comprise:
updating the rules engine to output the preferred medical best practice recommendation for the preferred medical finding rendered in response to receiving the preferred medical best practice recommendation and receiving the preferred medical finding.

### Claim 25 (depends on 23)

The computer program product of claim 23, wherein the medical observation is based on a medical imaging of a patient and the medical finding is related to the medical observation based on the medical imaging.

### Claim 26 (depends on 23)

The computer program product of claim 23, wherein the rules engine associates best practice recommendations with medical findings outputted from the classifier program and provides a medical best practice recommendation for each possible classified clinical medical finding from the classifier program.

### Claim 27 (depends on 23)

The computer program product of claim 23, wherein the received at least one of the preferred medical finding and the preferred medical best practice recommendation are provided by the user providing the received rejection.

### Claim 28

A system, 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 input field in a user interface;
providing the medical observation to a classification program implemented as a machine learning module to classify into a machine classification comprising a medical finding based on the medical observations to provide to a rules engine to apply a series of rules 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 user indication of rejecting at least one of the medical finding from the machine learning module and the rendered best practice recommendation;
receiving at least one of a preferred medical finding for the medical observations and a preferred medical best practice recommendation in response to the user indication of rejecting;
training the machine learning module comprising the classification program to output the preferred medical finding based on the medical observations in response to receiving the preferred medical finding; and
updating the rules engine to associate the preferred medical best practice recommendation for the medical finding rendered in the user interface in response to receiving the preferred medical best practice recommendation for the medical finding, wherein the rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding rendered in the user interface.

### Claim 29 (depends on 28)

The system of claim 28, wherein the receiving at least one of the preferred medical finding and the preferred medical best practice recommendation comprises receiving both the preferred medical finding and the preferred medical best practice recommendations, wherein the operations further comprise:
updating the rules engine to output the preferred medical best practice recommendation for the preferred medical finding rendered in response to receiving the preferred medical best practice recommendation and receiving the preferred medical finding.

### Claim 30 (depends on 28)

The system of claim 28, wherein the medical observation is based on a medical imaging of a patient and the medical finding is related to the medical observation based on the medical imaging.

### Claim 31 (depends on 28)

The system of claim 28, wherein the rules engine associates best practice recommendations with medical findings outputted from the classifier program and provides a medical best practice recommendation for each possible classified clinical medical finding from the classifier program.

### Claim 32 (depends on 28)

The system of claim 28, wherein the received at least one of the preferred medical finding and the preferred medical best practice recommendation are provided by the user providing the received rejection.

### Claim 33

A method for determining medical best practice recommendations for user entered medical observations a processor, comprising:
receiving a medical observation of a patient entered into a user input field in a user interface;
providing the medical observation to a classification program implemented as a machine learning module to classify into a machine classification comprising a medical finding based on the medical observations to provide to a rules engine to apply a series of rules 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 user indication of rejecting at least one of the medical finding from the machine learning module and the rendered best practice recommendation;
receiving at least one of a preferred medical finding for the medical observations and a preferred medical best practice recommendation in response to the user indication of rejecting;
training the machine learning module comprising the classification program to output the preferred medical finding based on the medical observations in response to receiving the preferred medical finding; and
updating the rules engine to associate the preferred medical best practice recommendation for the medical finding rendered in the user interface in response to receiving the preferred medical best practice recommendation for the medical finding, wherein the rules engine outputs the preferred medical best practice recommendation in response to the machine learning module outputting the medical finding rendered in the user interface.

### Claim 34 (depends on 33)

The method of claim 33, wherein the receiving at least one of the preferred medical finding and the preferred medical best practice recommendation comprises receiving both the preferred medical finding and the preferred medical best practice recommendations, further comprising:
updating the rules engine to output the preferred medical best practice recommendation for the preferred medical finding rendered in response to receiving the preferred medical best practice recommendation and receiving the preferred medical finding.

### Claim 35 (depends on 33)

The method of claim 33, wherein the medical observation is based on a medical imaging of a patient and the medical finding is related to the medical observation based on the medical imaging.

### Claim 36 (depends on 33)

The method of claim 33, wherein the rules engine associates best practice recommendations with medical findings outputted from the classifier program and provides a medical best practice recommendation for each possible classified clinical medical finding from the classifier program.

### Claim 37 (depends on 33)

The method of claim 33, wherein the received at least one of the preferred medical finding and the preferred medical best practice recommendation are provided by the user with the received user providing the received rejection.
