EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Multimodal Machine Learning Prediction of 12‐Month Suicide Attempts in Bipolar Disorder

Alessandro Pigoni iD, Isidora Tesic, Cecilia Pini, Paolo Enrico, Lorena Di Consoli, Francesca Siri, Guido Nosari, Adele Ferro, Letizia Squarcina, Giuseppe Delvecchio, Paolo Brambilla

Bipolar Disorders · 2025-05 · 27 (3) · 217-231

DOI: 10.1111/bdi.70011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bipolar Disorders, online erschienen am 07.03.2025. Verfasst von Alessandro Pigoni und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurosciences and Mental Health, Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Milan, Italy. Hauptthemen laut MEDLINE: Bipolar Disorder, Suicide, Attempted, Machine Learning, Brain. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 123 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Fondazione Cariplo, Ministero dell'Università e della Ricerca, Ministero della Salute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Bipolar disorder (BD) patients present an increased risk of suicide attempts. Most current machine learning (ML) studies predicting suicide attempts are cross‐sectional, do not employ time‐dependent variables, and do not assess more than one modality. Therefore, we aimed to predict 12‐month suicide attempts in a sample of BD patients, using clinical and brain imaging data.

Methods

A sample of 163 BD patients were recruited and followed up for 12 months. Gray matter volumes and cortical thickness were extracted from the T1‐weighted images. Based on previous literature, we extracted 56 clinical and demographic features from digital health records. Support Vector Machine was used to differentiate BD subjects who attempted suicide. First, we explored single modality prediction (clinical features, GM, and thickness). Second, we implemented a multimodal stacking‐based data fusion framework.

Results

During the 12 months, 6.13% of patients attempted suicide. The unimodal classifier based on clinical data reached an area under the curve (AUC) of 0.83 and balanced accuracy (BAC) of 72.7%. The model based on GM reached an AUC of 0.86 and BAC of 76.4%. The multimodal classifier (clinical + GM) reached an AUC of 0.88 and BAC of 83.4%, significantly increasing the sensitivity. The most important features were related to suicide attempts history, medications, comorbidities, and depressive polarity. In the GM model, the most relevant features mapped in the frontal, temporal, and cerebellar regions.

Conclusions

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bipolar DisorderSuicide, AttemptedMachine LearningBrainHumansMaleFemaleAdultMagnetic Resonance ImagingMiddle AgedSupport Vector MachineGray MatterYoung Adult

Stichwörter der Autor:innen

bipolar disordermachine learningpredictionsuicide

Autor:innen und Institutionen

  • Department of Neurosciences and Mental Health, Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico, Milan, Italy.
  • Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy.

ORCID-Profile: Alessandro Pigoni

Förderung

  • Fondazione Cariplo
  • Ministero dell'Università e della Ricerca
  • Ministero della Salute

Zitieren

APA

Pigoni, A., Tesic, I., Pini, C., Enrico, P., Di Consoli, L., Siri, F., Nosari, G., Ferro, A., Squarcina, L., Delvecchio, G., & Brambilla, P. (2025). Multimodal Machine Learning Prediction of 12‐Month Suicide Attempts in Bipolar Disorder. Bipolar Disorders, 27(3), 217-231. https://doi.org/10.1111/bdi.70011

Vancouver

Pigoni A, Tesic I, Pini C, Enrico P, Di Consoli L, Siri F, et al. Multimodal Machine Learning Prediction of 12‐Month Suicide Attempts in Bipolar Disorder. Bipolar Disorders. 2025;27(3):217-231. doi:10.1111/bdi.70011

BibTeX
@article{Pigoni2025,
  author = {Pigoni, Alessandro and Tesic, Isidora and Pini, Cecilia and Enrico, Paolo and Di Consoli, Lorena and Siri, Francesca and Nosari, Guido and Ferro, Adele and Squarcina, Letizia and Delvecchio, Giuseppe and Brambilla, Paolo},
  title = {Multimodal Machine Learning Prediction of 12‐Month Suicide Attempts in Bipolar Disorder},
  journal = {Bipolar Disorders},
  year = {2025},
  volume = {27},
  number = {3},
  pages = {217--231},
  doi = {10.1111/bdi.70011}
}
Kostenlos starten →