# US 2026/0066115 A1 · Machine Learning Based Emergency Healthcare Information Extraction

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

- Number: US 2026/0066115 A1
- Document ID: US20260066115A1
- Status: Published application
- Kind: A1
- Application number: 19/302,235
- Filed: 2025-08-18
- Published: 2026-03-05
- Earliest claimed: 2024-09-05
- Assignees: Cerner Innovation, Inc.
- Applicants: Cerner Innovation, Inc.
- Inventors: Praveen Bhat GURPUR
- Web page: https://patentgrep.com/patent/US20260066115A1

## CPC

- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Embodiments diagnose an emergency room (“ER”) patient. Embodiments receive an identifier of the patient and search and retrieve relevant information factors for the patient from publicly available sources using the identifier using a trained machine learning (“ML”) model. The trained ML model is configured to identify and fetch medically relevant information of the patient in response to the identifier of the patient. Embodiments weight each of the retrieved factors relative to contributing to a diagnoses of the patient and assign a score to each of the retrieved factors and provide the scores and corresponding diagnoses to ER personnel.

## Claims

### Claim 1

A method of diagnosing an emergency room (ER) patient, the method comprising:
receiving an identifier of the patient;
searching and retrieving relevant information factors for the patient from publicly available sources using the identifier using a trained machine learning (ML) model, the trained ML model configured to identify and fetch medically relevant information of the patient in response to the identifier of the patient;
weighting each of the retrieved factors relative to contributing to a diagnoses of the patient; and
assigning a score to each of the retrieved factors and providing the scores and corresponding diagnoses to ER personnel.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
training the ML model with medical information and validating the trained machine learning model using standardized medical examinations.

### Claim 3 (depends on 1)

The method of claim 1, wherein the publicly available sources comprises at least one of social media sources, blogs, video repositories and publications.

### Claim 4 (depends on 1)

The method of claim 1, wherein the identifier comprises at least one of a drivers license, passport, social security number, state identifier, military identifier, alien resident card, or a photograph.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
determining whether the patient is registered in an electronic medical records (EMR) database.

### Claim 6 (depends on 1)

The method of claim 1, the trained ML model further configured to predict medical diagnoses in response to the identifier of the patient.

### Claim 7 (depends on 2)

The method of claim 2, further comprising:
receiving a selection of one of the diagnoses; and
retraining the ML model based on the selection.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
using a cloud infrastructure for the diagnosing, the cloud infrastructure comprising a first virtual cloud network (VCN) comprising a local peering gateway (LPG) communicatively coupled to a secure shell (SSH) VCN via the LPG;
wherein the LPG is contained in a control plane VCN and the SSH VCN is communicatively coupled to a data plane VCN.

### Claim 9

A computer readable medium having instructions stored thereon that, when executed by one or more processors, cause the processors to diagnose an emergency room (ER) patient, the diagnosing comprising:
receiving an identifier of the patient;
searching and retrieving relevant information factors for the patient from publicly available sources using the identifier using a trained machine learning (ML) model, the trained ML model configured to identify and fetch medically relevant information of the patient in response to the identifier of the patient;
weighting each of the retrieved factors relative to contributing to a diagnoses of the patient; and
assigning a score to each of the retrieved factors and providing the scores and corresponding diagnoses to ER personnel.

### Claim 10 (depends on 9)

The computer readable medium of claim 9, the diagnosing further comprising:
training the ML model with medical information and validating the trained machine learning model using standardized medical examinations.

### Claim 11 (depends on 9)

The computer readable medium of claim 9, wherein the publicly available sources comprises at least one of social media sources, blogs, video repositories and publications.

### Claim 12 (depends on 9)

The computer readable medium of claim 9, wherein the identifier comprises at least one of a drivers license, passport, social security number, state identifier, military identifier, alien resident card, or a photograph.

### Claim 13 (depends on 9)

The computer readable medium of claim 9, the diagnosing further comprising:
determining whether the patient is registered in an electronic medical records (EMR) database.

### Claim 14 (depends on 9)

The computer readable medium of claim 9, the trained ML model further configured to predict medical diagnoses in response to the identifier of the patient.

### Claim 15 (depends on 10)

The computer readable medium of claim 10, the diagnosing further comprising:
receiving a selection of one of the diagnoses; and
retraining the ML model based on the selection.

### Claim 16 (depends on 10)

The computer readable medium of claim 10, the diagnosing further comprising:
using a cloud infrastructure for the diagnosing, the cloud infrastructure comprising a first virtual cloud network (VCN) comprising a local peering gateway (LPG) communicatively coupled to a secure shell (SSH) VCN via the LPG;
wherein the LPG is contained in a control plane VCN and the SSH VCN is communicatively coupled to a data plane VCN.

### Claim 17

A cloud based system for diagnosing an emergency room (ER) patient, the system comprising:
a trained machine learning (ML) model;
one or more processors coupled to the trained ML model and configured to:
receive an identifier of the patient;
search and retrieve relevant information factors for the patient from publicly available sources using the identifier using the trained ML model, the trained ML model configured to identify and fetch medically relevant information of the patient in response to the identifier of the patient;
weight each of the retrieved factors relative to contributing to a diagnoses of the patient; and
assign a score to each of the retrieved factors and provide the scores and corresponding diagnoses to ER personnel.

### Claim 18 (depends on 17)

The cloud based system of claim 17, the processors further configured to:
train the ML model with medical information and validate the trained machine learning model using standardized medical examinations.

### Claim 19 (depends on 17)

The cloud based system of claim 17, wherein the publicly available sources comprises at least one of social media sources, blogs, video repositories and publications.

### Claim 20 (depends on 17)

The system of claim 17, wherein the system is executed on a cloud infrastructure, the cloud infrastructure comprising a first virtual cloud network (VCN) comprising a local peering gateway (LPG) communicatively coupled to a secure shell (SSH) VCN via the LPG;
wherein the LPG is contained in a control plane VCN and the SSH VCN is communicatively coupled to a data plane VCN.
