Predicting patient responses to multiple modalities of CNS disease interventions
A machine-learning system using EEG data predicts patient responses to CNS treatments, addressing inefficiencies by providing personalized treatment recommendations based on multiple models, thus reducing costs and suffering.
WO2025213015A1 Publication Date: 2025-10-09NEUMARKER INC
9 Cites 0 Cited by
Patent Information
- Application Number
- PCT/US2025/023147
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-04-05
- Filing Date
- 2025-04-04
- Publication Date
- 2025-10-09
AI Technical Summary
Technical Problem
Current treatments for CNS diseases lack effective biomarkers to predict patient responses, leading to lengthy trial-and-error processes, ineffective treatments, patient suffering, and financial burdens due to misdiagnosis and inefficiency.
Method used
A machine-learning system using EEG data to extract features and input them into multiple treatment-specific models to predict responses to different candidate treatments, enabling personalized medicine and efficient treatment decision support.
Benefits of technology
Enables individualized precision medicine, reducing treatment time, healthcare costs, and patient suffering by accurately predicting responses to multiple treatments using a single EEG dataset, thereby optimizing treatment choices.
✦ Generated by Eureka AI based on patent content.
Abstract
An electroencephalography (EEG) system comprises: an EEG device; a display; one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for: receiving measurement data; extracting, from the measurement data, a first set of features and a second set of features; inputting the first set of features and the second set of features into a first treatment-specific machine-learning model and a second treatment-specific machine-learning model, respectively; generating a data structure based on the predicted treatment responses; and rendering, on the display, the generated data structure to provide the predicted treatment responses to the first candidate treatment of the CNS disease and the second candidate treatment of the CNS disease.
Need to check novelty before this filing date? Find Prior Art