Interpretable deep learning for depression detection in neurological patients using EEG signals
Parisa Khaleghi, Duygu Cakir, Ali Hamidoğlu, Omer Melih Gul, Seifedine Kadry · 2025
Read Interpretable deep learning for depression detection in neurological patients using EEG signals by Parisa Khaleghi, Duygu Cakir, Ali Hamidoğlu, Omer Melih Gul, Seifedine Kadry (2025) 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-12720302.txt.
Description
Parisa Khaleghi and co-authors built a clear-box deep learning tool to detect depression from brain waves in 2025. Depression affects over 280 million people, and patients with brain disorders face extra risk from medicines. Standard diagnosis leans on subjective judgment, which varies between clinicians.
Their model trained on EEG records from 232 neurological patients and reached 98 percent accuracy. An explanation method, called SHAP, named the signals that drove each call. Ratios and band powers that clinicians know well ranked high. The tool fits standard EEG setups, which eases clinic uptake. The authors frame it as support for, not a swap for, clinical judgment.
Catalog record
| CREATOR | Parisa Khaleghi, Duygu Cakir, Ali Hamidoğlu, Omer Melih Gul, Seifedine Kadry |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |