A meaningful prediction of functional decline in amyotrophic lateral sclerosis based on multi-event survival analysis

TL;DR

A novel method to predict the time until a patient with ALS experiences significant functional impairment (ALSFRS-R ≤ 2) for each of five common functions: speaking, swallowing, handwriting, walking, and breathing is proposed.

Abstract

Amyotrophic lateral sclerosis (ALS) is a degenerative disorder of the motor neurons that causes progressive paralysis in patients. Current treatment options aim to prolong survival and improve quality of life. However, due to the heterogeneity of the disease, it is often difficult to determine the optimal time for potential therapies or medical interventions. In this study, we propose a novel method to predict the time until a patient with ALS experiences significant functional impairment (ALSFRS-R <= 2) for each of five common functions: speaking, swallowing, handwriting, walking, and breathing. We formulate this task as a multi-event survival problem and validate our approach in the PRO-ACT dataset (N = 3220) by training five covariate-based survival models to estimate the probability of each event over the 500 days following the baseline visit. We then predict five event-specific individual survival distributions (ISDs) for a patient, each providing an interpretable estimate of when that event is likely to occur. The results show that covariate-based models are superior to the Kaplan-Meier estimator at predicting time-to-event outcomes in the PRO-ACT dataset. Additionally, our method enables practitioners to make individual counterfactual predictions -- where certain covariates can be changed -- to estimate their effect on the predicted outcome. In this regard, we find that Riluzole has little or no impact on predicted functional decline. However, for patients with bulbar-onset ALS, our model predicts significantly shorter time-to-event estimates for loss of speech and swallowing function compared to patients with limb-onset ALS (log-rank p<0.001, Bonferroni-adjusted alpha=0.01). The proposed method can be applied to current clinical examination data to assess the risk of functional decline and thus allow more personalized treatment planning.

Figures (8)

• Figure 1: Outline of the proposed method. Historical data about ALS patients form a patient dataset $\mathcal{D}$ with $N$ training instances and $d$ covariates, and the time to event (filled dot) or censoring (hollow dot) from a patient's first visit -- the "baseline time". Censoring indicates that the event of interest was not observed for a patient within the study period, so their exact event time remains unknown. We consider five separate but related events, i.e., Speech, Swallowing, Handwriting, Walking, and Dyspnea. We use the recorded covariates (taken at the baseline time) and event information to train a survival model $\mathcal{M}$ that can accurately estimate the individual survival distribution (ISD) of each of these five events, for a novel patient $\bm{x}_{i}$, denoted as $\hat{S}^{(i)}$. These ISDs give the probability of each of these five events occurring after $t$ days after the baseline visit, for all $t>0$. They can also be used to estimate the time to event for this $\bm{x}_{i}$ patient, for example, when the survival curve intersects the dashed horizontal line at 50%, which is called the median survival time, for each of the five events.
• Figure 2: Distribution of uncensored and censored times in the PRO-ACT dataset for the five events.
• Figure 3: The mMAE (in days) as a function of covariate-based models (x-axis) in the PRO-ACT test set, with error bars representing empirical 95% confidence intervals. The horizontal dashed line is the KM estimator. Lower is better.
• Figure 4: Predicted ISDs for Mr. Smith ($i$). The point where the survival curve intersects the dashed horizontal line at 50% indicates the predicted time of event -- so this predicts, for example, Walking at approximately 80 days, Handwriting at 240 days, and Speech at 300 days. The dashed vertical lines are Mr. Smith's actual time of event for the respective events -- so, for example, Speech at approximately 7 days, Handwriting at 35 days, and Walking at 45 days.
• Figure 5: Predicted ISDs for Mr. Smith based on his use of Riluzole.