Multimodal Machine Learning Prediction of 12‐Month Suicide Attempts in Bipolar Disorder
By combining models, we increased the detection of suicide attempts, reaching a sensitivity of 80%. Combining more than one modality proved a valid method to overcome limitations from single-modality models and increasing overall accuracy.
Authors
- Letizia Squarcina (ORCID: https://orcid.org/0000-0001-6209-4629)
- Paolo Enrico (ORCID: https://orcid.org/0000-0002-6497-2699)
- Alessandro Pigoni (ORCID: https://orcid.org/0000-0002-9122-5656)
- Lorena Di Consoli
- Giuseppe Delvecchio (ORCID: https://orcid.org/0000-0003-4750-1980)
- Paolo Brambilla (ORCID: https://orcid.org/0000-0002-4021-8456)
- Francesca Siri
- Adele Ferro (ORCID: https://orcid.org/0000-0003-2399-3626)
- Guido Nosari (ORCID: https://orcid.org/0000-0002-1591-2139)
- Isidora Tesic
- Cecilia Pini
Institutions
- University of Milan (IT)
- Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT)
Publication Details
- Journal
- Bipolar Disorders
- Published
- 2025-03-07
- DOI
- https://doi.org/10.1111/bdi.70011
- Citations
- 8
- Primary Topic
- Bipolar Disorder and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 11.77
Funders
- Fondazione Cariplo
- Ministero della Salute
- Ministero dell'Università e della Ricerca