A non-suicidal self-injury state detection and recognition method based on fNIRS

By combining fNIRS technology and machine learning models with channel-level analysis, the problem of distinguishing between major depressive disorder and non-suicidal self-harm in adolescents has been solved in existing technologies. This achieves high-precision NSSI detection and early identification, making it suitable for neurobiological assessment of adolescents.

CN122096801APending Publication Date: 2026-05-29THE UNIVERSITY-TOWN HOSPITAL AFFILIATED TO CHONGQING MEDICAL UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
THE UNIVERSITY-TOWN HOSPITAL AFFILIATED TO CHONGQING MEDICAL UNIVERSITY
Filing Date
2026-02-24
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies are insufficient to effectively distinguish between major depressive disorder and non-suicidal self-harm in adolescents. Furthermore, functional magnetic resonance imaging (fMRI) in adolescents suffers from high costs, sensitivity to head movements, and limited ecological validity, and there is a lack of suitable neurobiological assessment methods.

Method used

Using functional near-infrared spectroscopy (fNIRS) technology, combined with channel-level analysis and machine learning models, we identified significantly different channels by collecting hemodynamic data from the prefrontal cortex and constructed a logistic regression model for NSSI state classification.

Benefits of technology

It achieves high-precision detection of non-suicidal self-harm in adolescents, provides quantifiable biomarkers, improves the objectivity and compliance of the test, is suitable for routine clinical scenarios, and has the potential to identify high-risk individuals for NSSI at an early stage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122096801A_ABST
    Figure CN122096801A_ABST
Patent Text Reader

Abstract

The application discloses a non-suicidal self-injury state detection and recognition method based on fNIRS, and relates to the technical field of medical detection and neural imaging; comprising the following steps: S1: using an fNIRS device to collect blood flow hemodynamic data of a subject's prefrontal cortex under a cognitive task, wherein the fNIRS device comprises a light source, a detector and a signal processing unit; S2: pre-processing the collected optical density data, including motion artifact correction, band-pass filtering and baseline correction, to obtain a time series of oxygenated hemoglobin HbO concentration changes; the application provides objective neural activation data through fNIRS technology, effectively reducing subjective bias; through channel-level analysis, six significant difference channels are recognized, and the activation patterns of these channels present a gradient trend of MDD> healthy control > NSSI + MDD, thereby providing a quantifiable biomarker for the NSSI state.
Need to check novelty before this filing date? Find Prior Art