Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Nov 1, 2024
Date Accepted: Aug 12, 2025
Forecasting Waitlist Trajectories for Patients with Metabolic Dysfunction-Associated Steatohepatitis Cirrhosis Using Neural Network Competing Risk Analysis
ABSTRACT
Background:
The Model for End-Stage Liver Disease (MELD)-based liver allocation system has suboptimal concordance in predicting waitlist mortality for patients with Metabolic Dysfunction-Associated Steatohepatitis (MASH) cirrhosis and does not capture competing outcomes of death and transplantation on the liver transplant waitlist.
Objective:
A competing risk analysis using deep learning was conducted to forecast waitlist trajectories of MASH patients using data available at the time of waitlisting.
Methods:
A deep learning competing risk model was constructed using data from 17,551 waitlisted MASH cirrhosis patients in the Scientific Registry of Transplant Recipients (SRTR) based on the DeepHit model framework. Its performance was evaluated and compared to single-risk Cox Proportional Hazards (CoxPH) and Random Survival Forests (RSF) models in predicting death or transplant, using the Concordance index (C-index) and Brier scores. Additionally, a novel performance metric, the competing event coherence (CEC) score, was developed to evaluate model performance in the setting of competing risks. Features associated with death and transplant in the DeepHit model were identified using permutation importance. Models were externally validated.
Results:
In a competing risk scenario, DeepHit achieved the best CEC scores at one, three, six, and 12 months on the waitlist. The RSF model showed the highest C-indices for most individual events, except for death at 3 months and transplant at 1 month, and lower Brier scores except for transplant at 12 months. These results were consistent on external validation. MELD at listing along with its components as well as functional status, age, and blood type, were associated with both death and transplant on the waitlist.
Conclusions:
A deep learning competing risk analysis can be used to forecast the risks of both death and transplant in MASH patients on waitlist, helping to inform clinical decisions by identifying the most impactful covariates for each outcome.
Citation
Per the author's request the PDF is not available.
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.