Deep learning algorithm reveals probabilities of stage-specific time to conversion in individuals with neurodegenerative disease LATE

Abstract

Introduction: Limbic-predominant age-related TAR DNA-binding protein 43 (TDP-43) encephalopathy (LATE) is a recently defined neurodegenerative disease. Currently, there is no effective way to make a prognosis of time to stage-specific future conversions at an individual level.

Methods: After using the Kaplan-Meier estimation and log-rank test to confirm the heterogeneity of LATE progression, we developed a deep learning-based approach to assess the stage-specific probabilities of time to LATE conversions for different subjects.

Results: Our approach could accurately estimate the disease incidence and transition to next stages: the concordance index was at least 82% and the integrated Brier score was less than 0.14. Moreover, we identified the top 10 important predictors for each disease conversion scenario to help explain the estimation results, which were clinicopathologically meaningful and most were also statistically significant.

Discussion: Our study has the potential to provide individualized assessment for future time courses of LATE conversions years before their actual occurrence.

Keywords: limbic‐predominant age‐related TAR DNA‐binding protein 43 encephalopathy; machine learning; progression rate; stage‐stratified analysis; survival models; time‐to‐event estimation.

FIGURE 1

Schematic illustration of our workflow for DL‐based stage‐stratified assessment of probabilities of time to LATE conversion. ANOVA, analysis of variance; CDR, Clinical Dementia Rating; CI, concordance index; DL, deep learning; FS, feature ranking and selection; IBS, integrated Brier score; KM, Kaplan–Meier; LATE, limbic‐predominant age‐related TAR DNA‐binding protein 43 encephalopathy; NACC, National Alzheimer's Coordinating Center

FIGURE 2

The comparison of Kaplan–Meier estimations for different scenarios as shown in (A) ‐ (F). The dotted line is a trend curve fitted by a quadratic polynomial. The horizontal axis denotes the time in days, and the vertical axis denotes the probability of staying in the current stage

FIGURE 3

Visualization of the assessments for five randomly chosen patients in different conversion scenarios: (A) {0,0.5}⇝{1}; (B) {1}⇝{2}; (C) {2} ⇝ {3}; (D) {1}⇝{3}. The horizontal axis denotes the time in days, with the origin being the onset of the current stage; the vertical axis denotes the probability of staying in the current stage. The vertical dashed line denotes the actual time when the transition event occurred

FIGURE 4

Comparison of the expression levels of significant variables between the conversion group and the non‐conversion group in different scenarios (A) ‐ (H).