Predicting Suicidality in People Living with HIV in Uganda: A Machine Learning Approach
Mutema, A. B.; Lillian, L.; Jjingo, D.; Fatumo, S.; Kinyanda, E.; Kalungi, A.
Show abstract
BackgroundPeople living with HIV (PLWH) are more likely to experience suicidal thoughts and exhibit suicidal behavior than the general population. However, there are currently no effective methods of predicting who is likely to experience suicidal thoughts and behavior. Machine learning (ML) approaches can be leveraged to develop models that evaluate the complex etiology of suicidal behavior, facilitating the timely identification of at-risk individuals and promoting individualized treatment allocation. Materials and methodsThis retrospective case-control study used longitudinal sociodemographic, psychosocial, and clinical data of 1,126 PLWH from Uganda to evaluate the potential of ML in predicting suicidality. In addition, suicidality polygenic risk scores (PRS) were calculated for a subset of 282 study participants and incorporated as an additional feature in the model to determine if including genomic information improves overall model performance. The models performance was evaluated using the area under the receiver operating characteristics curve (AUC), positive predictive value (PPV), sensitivity, specificity, and Mathews correlation coefficient (MCC). ResultsWe trained and evaluated eight different ML algorithms including logistic regression, support vector machines, Naive Bayes, k-nearest neighbors, decision trees, random forests, AdaBoost, and gradient-boosting classifiers. Cost-sensitive AdaBoost emerged as the best model, achieving an AUC of 0.79 (95% CI: 0.72-0.87), a sensitivity of 0.63, a specificity of 0.74, a PPV of 0.36, and an NPV of 0.89 on unseen baseline data. The model demonstrated good generalizability, predicting prevalent and incident suicidality at 12-month follow-up with an AUC of 0.75 (95% CI: 0.69-0.81) and 0.69 (95% CI: 0.62-0.76) respectively. Incorporating PRS as an additional feature in the model resulted in a 19% and 14% improvement in model sensitivity and PPV respectively, and a 4% reduction in specificity. A positive MDD diagnosis and high stress contributed the most to predicting suicidality risk. ConclusionA cost-sensitive AdaBoost model developed using the sociodemographic, psychosocial, and clinical data of PLWH in Uganda can predict suicidality risk. 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.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Applying machine learning in motor activity time series of depressed bipolar and unipolar patients. 94%
- Psychosocial factors associated with mental health and quality of life during the COVID-19 pandemic among low-income urban dwellers in Peninsular Malaysia 93%
- The effect of body image dissatisfaction on goal-directed decision making in a population marked by negative appearance beliefs and disordered eating 92%
Similar papers in this journal
- Machine Learning Models Predict the Emergence of Depression in Argentinean College Students during Periods of COVID-19 Quarantine 91%
- Longitudinal trends and risk factors for depressed mood among Canadian adults during the first wave of COVID-19 91%
- Sex-differences in determinants of suicide risk preceding psychiatric admission: An electronic medical record study 91%
Similar papers in this journal
- Genetic Factors Associated with Suicidal Behaviors and Alcohol Use Disorders in an American Indian Population 94%
- An Examination of Sustained Versus Transient Distressing Psychotic-Like Experiences Using Adolescent Brain Cognitive Development℠ Study Data 91%
- Correlates of suicidal behaviors and genetic risk among United States veterans with schizophrenia or bipolar I disorder 91%
Similar papers in this journal
- Neurovegetative symptom subtypes in young people with major depressive disorder and their structural brain correlates 92%
- Early identification of postpartum depression using demographic, clinical, and digital phenotyping 92%
- Gene-based polygenic risk scores analysis of alcohol use disorder in African Americans 91%
Similar papers in this journal
- Exploring the Efficacy and Potential of Large Language Models for Depression: A Systematic Review 93%
- The Impact of Psychopathology, Social Adversity and Stress-relevant DNAm on Prospective Risk for Post-traumatic Stress: A Machine Learning Approach 91%
- Individual Deviations from Normative Electroencephalographic Connectivity Predict Antidepressant Response 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.