一种用于筛查患精神分裂症风险的标志物及其用途
By combining IDH2 protein and total cholesterol or PPARγ protein as biomarkers with machine learning models, this approach addresses the shortcomings in sensitivity and specificity of existing technologies, providing a highly efficient schizophrenia risk screening tool suitable for large-scale population screening.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- THE FIRST AFFILIATED HOSPITAL OF CHONGQING MEDICAL UNIVERSITY
- Filing Date
- 2023-08-04
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack schizophrenia risk screening tools that are highly sensitive, specific, and suitable for large-scale population screening. The detection effect of single biomarkers is poor, leading to frequent misdiagnosis and missed diagnosis.
IDH2 protein, total cholesterol, and/or PPARγ protein were used as joint biomarkers. The expression levels in blood samples were detected by methods such as enzyme-linked immunosorbent assay (ELISA). A random forest model was constructed using machine learning models for risk assessment.
It achieves high detection rate, high sensitivity and good repeatability of schizophrenia risk screening, is simple and easy to perform, and the test results are highly consistent with clinical diagnosis, making it suitable for large-scale population screening.
Smart Images
Figure CN117007822B_ABST