Explainable and externally validated machine learning for neurocognitive diagnosis via ECGs
These findings suggest that ECG holds promise as a non-invasive, explainable biomarker for selected neurocognitive disorders. This study demonstrates robust performance across cohorts and lays the groundwork for future clinical applications, including early detection and personalised monitoring.
Authors
- Nils Strodthoff (ORCID: https://orcid.org/0000-0003-4447-0162)
- Ebenezer Oloyede (ORCID: https://orcid.org/0000-0003-1352-4017)
- Wilhelm Haverkamp (ORCID: https://orcid.org/0000-0002-6183-2519)
- Juan Miguel Lopez Alcaraz (ORCID: https://orcid.org/0009-0008-3056-3521)
- David Taylor
Institutions
- Carl von Ossietzky Universität Oldenburg (DE)
- King's College London (GB)
- University of Oxford (GB)
- Maudsley Hospital (GB)
- Deutsches Herzzentrum München (DE)
- Berlin Heart (Germany) (DE)
Publication Details
- Journal
- General Psychiatry
- Published
- 2025-10-01
- DOI
- https://doi.org/10.1136/gpsych-2025-102107
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00