Machine learning prediction models for clinical management of blood-borne viral infections: a systematic review of current applications and future impact

•Machine learning (ML) prediction models hold promising potential for advancing clinical research and patient care in the management of blood-borne viral infections, including hepatitis B virus (HBV).•The development of ML clinical prediction models is often constrained in resource-limited settings, where patient data and electronic databases are either scarce or non-existent.•Majority of the ML models for blood-borne viral infections were developed in high-income countries. No ML model was available for clinical decision support of HBV in African populations including Nigeria.•In future, ML models should be developed in diverse population settings, including low and middle income countries where representation is currently low.•External validation and explainability of ML models need to be prioritised to enhance safe implementation and adoption in routine clinical workflow. Machine learning (ML) prediction models to support clinical management of blood-borne viral infections are becoming increasingly abundant in medical literature, with a number of competing models being developed for the same outcome or target population. However, evidence on the quality of these ML prediction models are limited. This study aimed to evaluate the development and quality of reporting of ML prediction models that could facilitate timely clinical management of blood-borne viral infections. We conducted narrative evidence synthesis following the synthesis without meta-analysis guidelines. We searched PubMed and Cochrane Central Register of Controlled Trials for all studies applying ML models for predicting clinical outcomes associated with hepatitis B virus (HBV), human immunodeficiency virus (HIV), or hepatitis C virus (HCV). We found 33 unique ML prediction models aiming to support clinical decision making. Overall, 12 (36.4%) focused on HBV, 10 (30.3%) on HCV, 10 on HIV (30.3%) and two (6.1%) on co-infection. Among these, six (18.2%) addressed the diagnosis of infection, 16 (48.5%) the prognosis of infection, eight (24.2%) the prediction of treatment response, two (6.1%) progression through a cascade of care, and one (3.03%) focused on the choice of antiretroviral therapy (ART). Nineteen prediction models (57.6%) were developed using data from high-income countries. Evaluation of prediction models was limited to measures of performance. Detailed information on software code accessibility was often missing. Independent validation on new datasets and/or in other institutions