Identifying time patterns in Huntington's disease trajectories using dynamic time warping-based clustering on multi-modal data.

One of the principal goals of Precision Medicine is to stratify patients by accounting for individual variability. However, extracting meaningful information from Real-World Data, such as Electronic Health Records, still remains challenging due to methodological and computational issues. A Dynamic Time Warping-based unsupervised-clustering methodology is presented in this paper for the clustering of patient trajectories of multi-modal health data on the basis of shared temporal characteristics. Building on an earlier methodology, a new dimension of time-varying clinical and imaging features is incorporated, through an adapted cost-minimization algorithm for clustering on different, possibly overlapping, feature subsets. The model disease chosen is Huntington's disease (HD), characterized by progressive neurodegeneration. From a wide range of examined user-defined parameters, four case examples are highlighted to demonstrate the identified temporal patterns in multi-modal HD trajectories and to study how these differ due to the combined effects of feature weights and granularity threshold. For each identified cluster, polynomial fits that describe the time behavior of the assessed features are provided for an informative comparison, together with their averaged values. The proposed data-mining methodology permits the stratification of distinct time patterns of multi-modal health data in individuals that share a diagnosis, by employing user-customized criteria beyond the current clinical practice. Overall, this work bears implications for better analysis of individual variability in disease progression, opening doors to personalized preventative, diagnostic and therapeutic strategies.