A machine learning approach to predicting clinical trajectories in bipolar disorder
Clinical Snapshot
PICO Framework
| P — Population | 203 patients with bipolar disorder from dual-site African cohort |
| I — Intervention | Machine learning models (Random Forest, Weighted Logistic Regression, XGBoost) for clinical trajectory prediction |
| C — Comparator | Statistical modelling and survival analysis methods |
| O — Outcomes | Age of onset timing (early/late), illness severity, diagnostic delay, patient phenotype clusters |
Bottom Line
This cross-sectional study developed machine learning models to predict clinical trajectories in 203 bipolar disorder patients from an African cohort. Weighted logistic regression achieved moderate predictive performance (AUC 0.733) for age of onset timing. Three distinct patient phenotypes were identified through clustering. However, the study has significant methodological limitations including small sample size, cross-sectional design preventing true trajectory assessment, lack of external validation, and insufficient reporting of model development details. The finding that diagnostic delay was independent of clinical severity (p=0.34) suggests current risk stratification approaches may be inadequate. While the concept of using machine learning for bipolar disorder trajectory prediction is promising, this study provides insufficient evidence to support clinical implementation. Australian clinicians should await larger, longitudinal studies with external validation before considering such approaches in practice.
Key Findings
P Value: Log-Rank p = 0.34 for diagnostic delay analysis
Effect Size: AUC 0.733 (Weighted Logistic Regression), AUC 0.729 (XGBoost)
Primary Outcome: Age of onset timing prediction (early vs late onset)
Nnt Or Sensitivity: Sensitivity and specificity values not reported for optimal cut-points
Confidence Interval: Not reported
Clinical Application
Requires access to comprehensive clinical datasets and machine learning infrastructure; limited by model complexity Limited applicability due to different healthcare pathways, cultural factors, and population genetics compared to African cohort. Would require local validation before implementation in Australian mental health services Patients with established bipolar disorder diagnosis in specialist mental health settings
Abstract
BACKGROUND: Bipolar disorder (BD) is characterized by significant heterogeneity in clinical presentation, age of onset, and diagnostic delays. Identifying clinical trajectories and subtypes is a central aim of precision psychiatry, with the goal of improving risk stratification and characterization of illness courses, enabling early recognition of high-risk patients and facilitating timely interventions that improve long-term outcomes. METHODS: This is a dual-site retrospective cross-sectional secondary analysis of 203 clinical datasets from BD patients to develop machine learning models: Random Forest, Weighted Logistic Regression (LR), and XGBoost, supplemented by statistical modelling, to predict age of onset timing (early/late onset) and illness severity. Survival analysis (Kaplan-Meier and Cox proportional hazards) investigated factors influencing diagnostic delay, while clustering identified patient subtypes. RESULTS: Single-split Weighted LR (AUC = 0.733) and nested cross-validation XGBoost (AUC = 0.729) achieved superior performance in predicting onset timing. Cluster analysis identified three distinct phenotypes: baseline low complexity, late-onset familial-severe, and an early-onset comorbid group. Survival analysis revealed that the time to diagnosis was independent of clinical risk profiles (Log-Rank p = 0.34), with the most severe cases experiencing significant diagnostic latency. CONCLUSIONS: Machine learning accurately predicts BD clinical trajectories using routinely collected data in an African cohort. Diagnostic delay did not differ significantly across clinical risk or severity strata, indicating that the measured variables did not explain variation in time to diagnosis.
References
- 1.Ejiohuo, O., Adiukwu, F. N., Bamgboye, A. O., Folami, S., Essien, E. A., Osagiede, G., & Olaleye, O. O. (2026). A machine learning approach to predicting clinical trajectories in bipolar disorder. Psychiatry Research, 117009. https://doi.org/10.1016/j.psychres.2026.117009
Related Research
Journal of psychiatric research
Systematic review of machine learning and deep learning models for EEG-based detection of depression.
2 Aug 2026
Sleep medicine reviews
Artificial intelligence in sleep medicine I: Diagnosis, treatment, care, and research
2 Aug 2026
International journal of yoga therapy
Randomized Controlled Trial on the Effect of Yoga on Anxiety Severity, Quality of Life, and Biomarkers in Individuals with Anxiety Disorder
31 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service