Functional Data Analysis Applications in Medicine: A Systematic Review

ABSTRACT Analysis of longitudinal data in medical research exhibits complexities inherent to the nature of correlated and irregular‐timed observations. Functional data analysis (FDA) offers a robust framework to address these challenges, encompassing elements such as smoothing techniques, clustering adjustments, data reduction, and functional linear modeling. This systematic review was conducted under the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) statement. A comprehensive search strategy in 11 databases was conducted to identify original research manuscripts focused on FDA applications in medicine, published between January 1995 and March 2024. Manuscripts focused on such clinical applications of FDA were excluded. From 1796 potential manuscripts, 93 were selected for qualitative synthesis. Utilization of FDA methods has progressively increased over the last 25 years. Smoothing techniques (76.3%), functional principal component analysis (50.5%), supervised learning models (46.2%), and clustering methods (22.5%) were identified as the most used FDA methods. FDA represents a valuable and robust tool for analyzing longitudinal data in clinical research. Adequate application of FDA methods should improve the understanding and interpretation of subtle variations in time‐trajectories of longitudinal data sets.