Targeted use of growth mixture modeling: a learning perspective

• Published in: Statistics in medicine 2017-02, Vol.36 (4), p.671-686
• Main Authors: Jo, Booil, Findling, Robert L., Wang, Chen‐Pin, Hastie, Trevor J., Youngstrom, Eric A., Arnold, L. Eugene, Fristad, Mary A., Horwitz, Sarah McCue
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Bipolar Disorder - diagnosis; Clinical outcomes; early prediction; Generalized method of moments; growth mixture modeling; Growth models; Humans; latent trajectory class; Longitudinal Studies; Machine Learning; Medical prognosis; Models, Statistical; Patient Outcome Assessment; Performance evaluation; Predictions; Prognosis; Reproducibility of Results; sensitivity; specificity; supervised learning; Supervised Machine Learning; unsupervised learning
• ISSN: 0277-6715; 1097-0258
• DOI: 10.1002/sim.7152

From the statistical learning perspective, this paper shows a new direction for the use of growth mixture modeling (GMM), a method of identifying latent subpopulations that manifest heterogeneous outcome trajectories. In the proposed approach, we utilize the benefits of the conventional use of GMM for the purpose of generating potential candidate models based on empirical model fitting, which can be viewed as unsupervised learning. We then evaluate candidate GMM models on the basis of a direct measure of success; how well the trajectory types are predicted by clinically and demographically relevant baseline features, which can be viewed as supervised learning. We examine the proposed approach focusing on a particular utility of latent trajectory classes, as outcomes that can be used as valid prediction targets in clinical prognostic models. Our approach is illustrated using data from the Longitudinal Assessment of Manic Symptoms study. Copyright © 2016 John Wiley & Sons, Ltd.