USPTO Grants Patent for Multimodal Machine Learning Clinical Predictor

ChangeBridge: Patent Grants - Health Informatics (G16H)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted a patent (US12586685B2) to Roche Molecular Systems, Inc. for a multimodal machine learning-based clinical predictor. This technology aims to predict a patient's response to treatment by processing molecular and biopsy image data.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12586685B2 to Roche Molecular Systems, Inc. The patent covers methods and systems for performing clinical predictions using multimodal machine learning. Specifically, the invention processes a patient's molecular data (including gene expressions) and biopsy image data to predict their response to a treatment. The machine learning model is trained on similar data from a plurality of patients.

This patent grant is a non-binding regulatory event for compliance purposes, as it pertains to intellectual property protection for a novel predictive technology. While it does not impose direct compliance obligations on other entities, it signifies innovation in health informatics and AI-driven diagnostics. Companies operating in the pharmaceutical and healthcare sectors, particularly those developing AI-based diagnostic tools or personalized medicine solutions, should be aware of this patent as it may impact their intellectual property landscape and competitive environment.

Source document (simplified)

← USPTO Patent Grants

Multimodal machine learning based clinical predictor

Grant US12586685B2 Kind: B2 Mar 24, 2026

Assignee

Roche Molecular Systems, Inc.

Inventors

Antoaneta Petkova Vladimirova, Yogesh P. Pandit, Vishakha Sharma, Tod M. Klingler, Hari Singhal

Abstract

Methods and systems for performing a clinical prediction are provided. In one example, the method comprises: receiving first molecular data of a patient, the first molecular data including at least gene expressions of the patient; receiving first biopsy image data of the patient; processing, using a machine learning model, the first molecular data and the first biopsy image data to perform a clinical prediction of the patient's response to a treatment, wherein the machine learning model is generated or updated based on second molecular data including at least gene expressions and second biopsy image data of a plurality of patients; and generating an output of the clinical prediction.