NEC Multi-Modal Disease Risk Prediction Device and Method
Summary
NEC Corporation filed US Patent Application US20260112498A1 on April 23, 2026, covering a risk prediction device and method that integrates multi-modal data using probability distribution in a latent space. The system handles missing modality data by acquiring relevance information between probability distributions of different modalities, then generates integrated probability distribution data for disease risk prediction. The application (19350495) was filed on October 6, 2025, with inventors Chenhui HUANG, Kansuke Wagata, and Fumiyuki Nihey.
“By using the risk estimation device to estimate disease risk, it is possible to support decision making regarding the subject's lifestyle.”
About this source
GovPing monitors USPTO Patent Applications - Health Informatics (G16H) for new healthcare & life sciences regulatory changes. Every update since tracking began is archived, classified, and available as free RSS or email alerts — 137 changes logged to date.
What changed
NEC Corporation filed a patent application for a multi-modal risk prediction system that acquires data from multiple different modalities for a single target subject. The system uses complementing means to handle missing modality data by acquiring relevance information from a storage unit storing relevance information between probability distribution data of each modality, generating probability distribution data for missing modalities. An encoder converts each modality's data into probability distribution data in a latent space, an integration unit merges these into integrated probability distribution data, and a predictor estimates disease risk based on the integrated data. The invention is classified under G16H 50/30, G06N 7/01, and G06N 20/00.
For competitors in health informatics, AI-driven medical devices, and clinical decision support systems, this application indicates NEC's strategic direction toward multi-modal data fusion for diagnostic and prognostic applications. Companies developing similar risk prediction systems using machine learning across heterogeneous health data sources should review their IP portfolios for potential overlap and consider their own defensive filings in this technical space.
Archived snapshot
Apr 23, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
RISK PREDICTION DEVICE, RISK PREDICTION METHOD, AND RECORDING MEDIUM
Application US20260112498A1 Kind: A1 Apr 23, 2026
Assignee
NEC Corporation
Inventors
Chenhui HUANG, Kansuke Wagata, Fumiyuki Nihey
Abstract
In the risk prediction device, the acquisition means acquires data of a plurality of different modalities for a single target. In a case where the data of at least one modality among the data of the plurality of modalities is missing, the complementing means acquires the relevance information from the storage unit that stores the relevance information indicating the relevance between the probability distribution data of each modality, and generates the probability distribution data of the missing modality based on the relevance information. The encoder converts the data of each modality into probability distribution data indicating the probability distribution in the latent space. The integration unit integrates the probability distribution data of each modality to generate integrated probability distribution data. The predictor predicts a risk based on the integrated probability distribution data. By using the risk estimation device to estimate disease risk, it is possible to support decision making regarding the subject's lifestyle.
CPC Classifications
G16H 50/30 G06N 7/01 G06N 20/00
Filing Date
2025-10-06
Application No.
19350495
Parties
Related changes
Get daily alerts for USPTO Patent Applications - Health Informatics (G16H)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Health Informatics (G16H) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.