Mental Health Repository

Explainable time-to-progression predictions in multiple sclerosis.

Journal: Computer methods and programs in biomedicine

Volume: 263

Issue:

Year of Publication:

Abstract summary

Prognostic machine learning research in multiple sclerosis has been mainly focusing on black-box models predicting whether a patients' disability will progress in a fixed number of years. However, as this is a binary yes/no question, it cannot take individual disease severity into account. Therefore, in this work we propose to model the time to disease progression instead. Additionally, we use explainable machine learning techniques to make the model outputs more interpretable.A preprocessed subset of 29,201 patients of the international data registry MSBase was used. Disability was assessed in terms of the Expanded Disability Status Scale (EDSS). We predict the time to significant and confirmed disability progression using random survival forests, a machine learning model for survival analysis. Performance is evaluated on a time-dependent area under the receiver operating characteristic and the precision-recall curves. Importantly, predictions are then explained using SHAP and Bellatrex, two explainability toolboxes, and lead to both global (population-wide) as well as local (patient visit-specific) insights.On the task of predicting progression in 2 years, the random survival forest achieves state-of-the-art performance, comparable to previous work employing a random forest. However, here the random survival forest has the added advantage of being able to predict progression over a longer time horizon, with AUROC >60% for the first 10 years after baseline. Explainability techniques further validated the model by extracting clinically valid insights from the predictions made by the model. For example, a clear decline in the per-visit probability of progression is observed in more recent years since 2012, likely reflecting globally increasing use of more effective MS therapies.The binary classification models found in the literature can be extended to a time-to-event setting without loss of performance, thus allowing a more comprehensive prediction of patient prognosis. Furthermore, explainability techniques proved to be key to reach a better understanding of the model and increase validation of its behaviour.

Authors & Co-authors: D'hondt Robbe R Dedja Klest K Aerts Sofie S Van Wijmeersch Bart B Kalincik Tomas T Reddel Stephen S Havrdova Eva Kubala EK Lugaresi Alessandra A Weinstock-Guttman Bianca B Mrabet Saloua S Lalive Patrice P Kermode Allan G AG Ozakbas Serkan S Patti Francesco F Prat Alexandre A Tomassini Valentina V Roos Izanne I Alroughani Raed R Gerlach Oliver O Khoury Samia J SJ van Pesch Vincent V Sá Maria José MJ Prevost Julie J Spitaleri Daniele D McCombe Pamela P Solaro Claudio C van der Walt Anneke A Butzkueven Helmut H Laureys Guy G Sánchez-Menoyo José Luis JL de Gans Koen K Al-Asmi Abdullah A Deri Norma N Csepany Tunde T Al-Harbi Talal T Carroll William M WM Rozsa Csilla C Singhal Bhim B Hardy Todd A TA Ramanathan Sudarshini S Peeters Liesbet L Vens Celine C

Study Outcome

Statistics

Citations :
Authors : 43

Identifiers

Doi : 10.1016/j.cmpb.2025.108624
SSN : 1872-7565

Study Population

Male,Female

Mesh Terms

Other Terms

Disability progression;Explainable artificial intelligence;Longitudinal data;Multiple sclerosis;Survival analysis

Explainable time-to-progression predictions in multiple sclerosis.

Statistics

Identifiers

Study Population

Mesh Terms

Other Terms

Study Design

Study Approach

Country of Study

Publication Country