Triclustering-based classification of longitudinal data for prognostic prediction: targeting relevant clinical endpoints in amyotrophic lateral sclerosis

Abstract

This work proposes a new class of explainable prognostic models for longitudinal data classification using triclusters. A new temporally constrained triclustering algorithm, termed TCtriCluster, is proposed to comprehensively find informative temporal patterns common to a subset of patients in a subset of features (triclusters), and use them as discriminative features within a state-of-the-art classifier with guarantees of interpretability. The proposed approach further enhances prediction with the potentialities of model explainability by revealing clinically relevant disease progression patterns underlying prognostics, describing features used for classification. The proposed methodology is used in the Amyotrophic Lateral Sclerosis (ALS) Portuguese cohort (N = 1321), providing the first comprehensive assessment of the prognostic limits of five notable clinical endpoints: need for non-invasive ventilation (NIV); need for an auxiliary communication device; need for percutaneous endoscopic gastrostomy (PEG); need for a caregiver; and need for a wheelchair. Triclustering-based predictors outperform state-of-the-art alternatives, being able to predict the need for auxiliary communication device (within 180 days) and the need for PEG (within 90 days) with an AUC above 90%. The approach was validated in clinical practice, supporting healthcare professionals in understanding the link between the highly heterogeneous patterns of ALS disease progression and the prognosis.

Temporal stratification of amyotrophic lateral sclerosis patients using disease progression patterns

“…In the particular case of ClusTric, we employ the TCtriCluster 26 algorithm to find temporally coherent and contiguous triclusters. This algorithm is an extension of triCluster 35 , a quasi-exhaustive approach, able to mine arbitrarily positioned and overlapping triclusters with constant, scaling, and shifting patterns from three-way data.…”

“…Soares et al 23 proposed BicTric, a classifier able to learn predictive models from static and temporal data using discriminative patterns 24 obtained using biclustering and triclustering 25 . Recently, Soares et al 26 enhanced BicTric with TCtriCluster, a triclustering algorithm incorporating temporal contiguity constraints. All these approaches used temporal preprocessing using snapshots and the time windows approach proposed by Carreiro et al 27 and were used to learn predictive models for different clinically relevant ALS endpoints.…”