Currently accepted at: JMIR Medical Informatics
Date Submitted: Feb 22, 2026
Open Peer Review Period: Mar 2, 2026 - Apr 27, 2026
Date Accepted: Oct 26, 2026
(closed for review but you can still tweet)
This paper has been accepted and is currently in production.
It will appear shortly on 10.2196/93953
The final accepted version (not copyedited yet) is in this tab.
Modelling Time to Gastrostomy Intervention in Amyotrophic Lateral Sclerosis: A Multi-Cohort Longitudinal Trajectory and Survival Analysis
ABSTRACT
Background:
Harnessing longitudinal data for time to event analysis can provide valuable insights into disease progression and help plan clinical interventions for individual patients, with the goal of improving clinical outcomes and quality of life. However, real-world clinical data is characterised by missingness, inconsistencies and heterogeneity, especially when datasets are aggregated from different sources.
Objective:
To address the challenges of missingness, inconsistency, and heterogeneity in multi-source data of degenerative disease, we propose a framework for explaining time-to-event predictions using multivariate longitudinal trajectories, applied to time-to-gastrostomy in patients with Amyotrophic Lateral Sclerosis (ALS).
Methods:
We analysed data from 8,586 ALS patients using a two-stage analytical approach. Joint latent class growth discrete-time survival analysis was used to identify data-driven reference trajectories of functional decline. New patient markers were mapped to these clusters using Fréchet distances. Two survival models (Cox-PH, Cox XGBoost) and a regression model (XGBoost Pseudo-Observation) using baseline demographics and functional decline features were used to predict time-to-gastrostomy.
Results:
Distinct classes of functional decline revealed that rapid deterioration in bulbar and swallowing functions are the most critical indicators for intervention, reaching a 50% probability of gastrostomy within 16 to 18 months. Bulbar, swallow, and ALFRS-R onset slopes were the primary predictors of time-to-gastrostomy. First, we fitted models using one feature only, determining that bulbar, swallow, and ALSFRS-R early "onset slopes" outperformed any model trained with baseline demographics alone, yielding an increase in concordance index that ranged from 0.002 to 0.050, and decreased pseudo-observed median absolute error by 41-77 days compared to relying on diagnostic delay alone. The XGBoost MAEPO regression model utilizing onset slope was the best overall classifier, achieving a concordance index of 0.760 (IQR, 0.752-0.767) and a pseudo-observed median absolute error of 258 days (IQR, 248-267), which outperformed the clinical standard of identifying patients with >10% weight loss from baseline.
Conclusions:
Our framework addresses clinical data heterogeneity through principled feature extraction and unsupervised trajectory mapping, translating individual predictions into interpretable clinical narratives that support timely gastrostomy decisions, and more generally time-to-intervention in degenerative diseases.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.