Stability‐Driven Selection of EEG Connectivity Features for Psychosis Classification: A Network‐Based Machine Learning Approach
Mahdi Naeim, Mohammad Narimani · 2026
Read Stability‐Driven Selection of EEG Connectivity Features for Psychosis Classification: A Network‐Based Machine Learning Approach by Mahdi Naeim, Mohammad Narimani (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13240269.txt.
Description
Mahdi Naeim and Mohammad Narimani built in 2026 a stability-first method for spotting psychosis in brain wave data. EEG connectivity features can classify psychosis, but marker lists often fail to repeat across studies. The team reanalyzed a public dataset of forty-three people, nineteen with psychosis and twenty-four controls. Connectivity and network features were pulled from the recordings across frequency bands.
Models were trained under nested cross-validation with strict subject-wise splits. Feature importance was scored by permutation and explanation methods, then graded for stability across folds. A support vector machine reached about ninety-one percent accuracy. Theta-band links between frontal and parietal areas stood out as the most reliable markers. The authors stress the small, single dataset makes this exploratory. External validation is the clear next step before any clinical screening use.
Catalog record
| CREATOR | Mahdi Naeim, Mohammad Narimani |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |