Predicting suicidality in people living with HIV in Uganda

A machine learning approach

Bibliographic Data

ID15525166
AuthorsAnthony B Mutema (Uganda Virus Research Institute, corresponding author), Lillian Linda (Uganda Virus Research Institute), Daudi Jjingo (0000-0003-1685-9234, Makerere University), Segun Fatumo (0000-0003-4525-3362, Uganda Virus Research Institute), Eugene Kinyanda (0000-0001-7068-9294, Uganda Virus Research Institute), Allan Kalungi (0000-0002-2890-0145, Uganda Virus Research Institute, corresponding author)
Year2025
Volume16
Pages1584335-1584335
Publication date2025-08-15
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueFrontiers in Psychiatry (JOURNAL)
Journal identifiersISSN: 1664-0640 • E-ISSN: 1664-0640
PublisherFrontiers Media (PUBLISHER • CH)
DOI10.3389/fpsyt.2025.1584335
PMID40896222
OpenAlexW4413380520
LanguageEN
References cited62

A cost-sensitive AdaBoost model developed using the sociodemographic, psychosocial, and clinical data of PLWH in Uganda can predict suicidality risk, albeit with modest PPV. Incorporating suicidality PRS improved the overall predictive performance of the model. However, larger studies involving more diverse participants are needed to evaluate the potential of PRS in enhancing risk stratification and the clinical utility of the prediction model

AdaBoost · Decision tree · Generalizability theory · Logistic regression · Machine learning · Naive Bayes classifier · Population · Psychiatry · Psychosocial · Random forest · Receiver operating characteristic · Statistics · Support vector machine · Computer Science · Mathematics · Medicine · Mental Health Treatment and Access · Psychosomatic Disorders and Their Treatments · Suicide and Self-Harm Studies · Artificial Intelligence

Tools

Open DOIOpen Access