# US 2026/0088145 A1 · Healthcare management system

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

- Number: US 2026/0088145 A1
- Document ID: US20260088145A1
- Status: Published application
- Kind: A1
- Application number: 19/339,110
- Filed: 2025-09-24
- Published: 2026-03-26
- Earliest claimed: 2024-09-25
- Applicants: Ortho Marketing, LLC
- Inventors: Marc E. Jackson; Jackson M. Neeley
- Web page: https://patentgrep.com/patent/US20260088145A1

## CPC

- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- 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

## Abstract

A computer system for structured analysis of medical reports includes one or more processors and computer-readable media storing instructions that configure the system to process user-supplied text and medical report data. Written text, including linguistic variants and descriptive phrases associated with injury categories, is received and vectorized into a first embedding vector. The text and embedding vector are stored in a hybrid database comprising predefined labels corresponding to injury categories and severity codes, free-form text fields storing linguistic variants and descriptive phrases, and stored vector embeddings generated for the free-form text fields. A medical report is received via an artificial intelligence engine trained to extract a description of a patient injury, and the description is vectorized into a second embedding vector. The second embedding vector is compared against the stored vector embeddings within the hybrid database, one or more injury categories are selected based on the comparison, and a structured result including at least a predefined label is output.

## Claims

### Claim 1

A computer system for structured analysis of medical reports, comprising:
one or more processors; and
one or more computer-readable media having stored thereon executable instructions that when executed by the one or more processors configure the computer system to perform at least the following:
receive written text from a user, wherein the written text comprises linguistic variants and descriptive phrases associated with different injury categories;
vectorize the written text into a first embedding vector, wherein the first embedding vector comprises a numerical representation of the written text, expressed within a multi-dimensional semantic vector space;
store the written text and the first embedding vector within a hybrid database, wherein the hybrid database comprises:
a plurality of predefined labels corresponding to injury categories and severity codes,
free-form text fields storing the linguistic variants and the descriptive phrases associated with the different injury categories, and
stored vector embeddings generated for at least the free-form text fields;
receive a medical report from a user via an artificial intelligence engine, wherein the artificial intelligence engine is trained to extract a description of a patient injury from the medical report;
vectorize the description of the patient injury into a second embedding vector, wherein the second embedding vector comprises a numerical representation of the description of the patient injury, expressed within the multi-dimensional semantic vector space;
compare the second embedding vector from the medical report against the stored vector embeddings within the hybrid database;
select one or more matching injury categories based on the comparison; and
output a structured result comprising at least a predefined label.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the hybrid database stores hierarchical predefined labels organized into parent injury categories and subcategories.

### Claim 3 (depends on 1)

The computer system of claim 1, wherein the hybrid database stores severity codes including at least surgical, physical-therapy, and self-management codes.

### Claim 4 (depends on 1)

The computer system of claim 1, wherein the written text is vectorized using contextual embeddings generated by a transformer-based neural network.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein comparing vectors includes calculating cosine similarity between the second embedding vector and stored embedding vectors.

### Claim 6 (depends on 1)

The computer system of claim 1, wherein selection of a matching injury categories requires that similarity exceed a predefined threshold value.

### Claim 7 (depends on 1)

The computer system of claim 1, wherein the artificial intelligence engine outputs descriptive text that is discarded if no corresponding stored embedding in the hybrid database is identified.

### Claim 8 (depends on 1)

The computer system of claim 1, wherein the hybrid database allows a user to annotate free-form text with severity indicators that are stored alongside embedding vectors.

### Claim 9 (depends on 1)

The computer system of claim 1, wherein the computer system supports iterative user editing of stored free-form text fields, and re-vectorizes the edited text for database storage.

### Claim 10 (depends on 1)

The computer system of claim 1, wherein multiple matching injury categories are ranked according to similarity scores and the structured result presents a highest-ranked category.

### Claim 11 (depends on 1)

The computer system of claim 1, wherein the structured result further comprises a recovery timeline retrieved from the hybrid database.

### Claim 12

A computer-implemented method for structured analysis of medical reports, comprising:
receiving written text from a user, wherein the written text comprises linguistic variants and descriptive phrases associated with different injury categories;
vectorizing the written text into a first embedding vector, wherein the first embedding vector comprises a numerical representation of the written text, expressed within a multi-dimensional semantic vector space;
storing the written text and the first embedding vector within a hybrid database, wherein the hybrid database comprises:
a plurality of predefined labels corresponding to injury categories and severity codes,
free-form text fields storing the linguistic variants and the descriptive phrases associated with the different injury categories, and
stored vector embeddings generated for at least the free-form text fields;
receiving a medical report from a user via an artificial intelligence engine, wherein the artificial intelligence engine is trained to extract a description of a patient injury from the medical report;
vectorizing the description of the patient injury into a second embedding vector, wherein the second embedding vector comprises a numerical representation of the description of the patient injury, expressed within the multi-dimensional semantic vector space;
comparing the second embedding vector from the medical report against the stored vector embeddings within the hybrid database;
selecting one or more matching injury categories based on the comparison; and
outputting a structured result comprising at least a predefined label.

### Claim 13 (depends on 12)

The computer-implemented method of claim 12, wherein the hybrid database stores hierarchical predefined labels organized into parent injury categories and subcategories.

### Claim 14 (depends on 12)

The computer-implemented method of claim 12, wherein the hybrid database stores severity codes including at least surgical, physical-therapy, and self-management codes.

### Claim 15 (depends on 12)

Computer-implemented method of claim 12, wherein the written text is vectorized using contextual embeddings generated by a transformer-based neural network.

### Claim 16 (depends on 12)

The computer-implemented method of claim 12, wherein comparing vectors includes calculating cosine similarity between the second embedding vector and stored embedding vectors.

### Claim 17 (depends on 12)

The computer-implemented method of claim 12, wherein selection of a matching injury categories requires that similarity exceed a predefined threshold value.

### Claim 18 (depends on 12)

The computer-implemented method of claim 12, wherein the hybrid database allows a user to annotate free-form text with severity indicators that are stored alongside embedding vectors.

### Claim 19 (depends on 1)

The computer system of claim 1, wherein the computer system supports iterative user editing of stored free-form text fields, and re-vectorizes the edited text for database storage.

### Claim 20

A computer-readable media comprising one or more physical computer-readable storage media having stored thereon computer-executable instructions that, when executed at a processor, cause a computer system to perform a method for structured analysis of medical reports, the method comprising:
receiving written text from a user, wherein the written text comprises linguistic variants and descriptive phrases associated with different injury categories;
vectorizing the written text into a first embedding vector, wherein the first embedding vector comprises a numerical representation of the written text, expressed within a multi-dimensional semantic vector space;
storing the written text and the first embedding vector within a hybrid database, wherein the hybrid database comprises:
a plurality of predefined labels corresponding to injury categories and severity codes,
free-form text fields storing the linguistic variants and the descriptive phrases associated with the different injury categories, and
stored vector embeddings generated for at least the free-form text fields;
receiving a medical report from a user via an artificial intelligence engine, wherein the artificial intelligence engine is trained to extract a description of a patient injury from the medical report;
vectorizing the description of the patient injury into a second embedding vector, wherein the second embedding vector comprises a numerical representation of the description of the patient injury, expressed within the multi-dimensional semantic vector space;
comparing the second embedding vector from the medical report against the stored vector embeddings within the hybrid database;
selecting one or more matching injury categories based on the comparison; and
outputting a structured result comprising at least a predefined label.
