Mixed-Effects Machine Learning

Benefits

Evidence quality

Other

Highlighted claims

• The core modelling approach is longitudinal mixed-effects machine learning using youth-provider relationship as the main predictor. — Common factors and unique pathways for linkages between HIV/STI prevention and syndemic behaviours in high-risk youth: protocol for a secondary analysis of harmonised data from six clinical trials
• Five studies will form the master training dataset, while MAGGIE will be held out as an independent test set. — Common factors and unique pathways for linkages between HIV/STI prevention and syndemic behaviours in high-risk youth: protocol for a secondary analysis of harmonised data from six clinical trials
• Random forest regression will be used for continuous outcomes and random forest classification for binary responder status. — Common factors and unique pathways for linkages between HIV/STI prevention and syndemic behaviours in high-risk youth: protocol for a secondary analysis of harmonised data from six clinical trials
• The approach is intended to capture non-linear patterns, multivariate interactions, longitudinal structure, and clustered data that traditional models may miss. — Common factors and unique pathways for linkages between HIV/STI prevention and syndemic behaviours in high-risk youth: protocol for a secondary analysis of harmonised data from six clinical trials
• Model transparency will be supported through predictor importance plots and Shapley additive explanations. — Common factors and unique pathways for linkages between HIV/STI prevention and syndemic behaviours in high-risk youth: protocol for a secondary analysis of harmonised data from six clinical trials