NEC Corporation Patent for AI Assessment Support System

ChangeBridge: Patent Apps - Health Informatics (G16H)

Published December 4th, 2025

Detected March 26th, 2026

Summary

The USPTO has published a patent application by NEC Corporation for an AI assessment support system. The system uses machine learning to predict patient assessment vectors and identify similar patients based on nursing record data.

View original document View source feed page

What changed

This document details a patent application (US20260088178A1) filed by NEC Corporation with the USPTO on December 4, 2025. The patent describes a system designed to support decision-making in healthcare assessments, particularly within nursing records. It utilizes a machine learning-trained model to predict assessment vectors for target patients and calculates the degree of similarity to existing patient records to identify similar cases.

The implications for regulated entities are primarily related to intellectual property and potential future adoption of AI technologies in healthcare. While this is a patent application and not a regulatory mandate, it highlights emerging trends in AI-driven healthcare solutions. Companies developing or utilizing similar AI systems in patient assessment or nursing record analysis should be aware of this patent filing and its potential impact on their intellectual property landscape.

Source document (simplified)

← USPTO Patent Applications

SYSTEM FOR SUPPORTING DECISION-MAKING REGARDING ASSESSMENT USING A MACHINE LEARNING-TRAINED MODEL, ASSESSMENT SUPPORT METHOD, AND RECORDING MEDIUM

Application US20260088178A1 Kind: A1 Mar 26, 2026

Assignee

NEC Corporation

Inventors

Kenji ARAKI, Yutaka UNO, Junichi YAHARA, Kosuke NISHIHARA

Abstract

An assessment support system includes: an assessment prediction unit that predicts, based on patient information about a target patient who is a creation target for an assessment in a nursing record, an assessment vector obtained by vectorizing the assessment of the target patient, as a prediction assessment vector; a degree-of-similarity calculation unit that calculates a degree of similarity of the assessment vector to the prediction assessment vector, based on a relationship between the predicted prediction assessment vector and the assessment vector of a patient having the assessment recorded in the nursing record; and a search unit that searches for and outputs at least one similar patient who is similar to the target patient, based on the degree of similarity.