Longitudinal machine learning modeling of MS patient trajectories improves predictions of disability progression. (September 2021)

• Record Type: Journal Article
• Authors: De Brouwer, Edward; Becker, Thijs; Moreau, Yves; Havrdova, Eva Kubala; Trojano, Maria; Eichau, Sara; Ozakbas, Serkan; Onofrj, Marco; Grammond, Pierre; Kuhle, Jens; Kappos, Ludwig; Sola, Patrizia; Cartechini, Elisabetta; Lechner-Scott, Jeannette; Alroughani, Raed; Gerlach, Oliver; Kalincik, Tomas; Granella, Franco; Grand'Maison, Francois; Bergamaschi, Roberto; José Sá, Maria; Van Wijmeersch, Bart; Soysal, Aysun; Sanchez-Menoyo, Jose Luis; Solaro, Claudio; Boz, Cavit; Iuliano, Gerardo; Buzzard, Katherine; Aguera-Morales, Eduardo; Terzi, Murat; Trivio, Tamara Castillo; Spitaleri, Daniele; Van Pesch, Vincent; Shaygannejad, Vahid; Moore, Fraser; Oreja-Guevara, Celia; Maimone, Davide; Gouider, Riadh; Csepany, Tunde; Ramo-Tello, Cristina; Peeters, Liesbet;
• Is Part Of: Computer methods and programs in biomedicine. Volume 208(2021)
• Publication Date: 2021-09
• Subjects: Multiple sclerosis -- Machine learning -- Longitudinal data -- Recurrent neural networks -- Electronic health records -- Disability progression -- Real-world data; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106180
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Temporal neural networks allow to significantly improve the prediction of disability progression in MS patients. Disability progression can be predicted in a 2-year horizon can be predicted with an AUC-ROC of 0.85. Longitudinal clinical history of the patients ranks amongst the most predictive variables for disability progression. Abstract: Background and Objectives: Research in Multiple Sclerosis (MS) has recently focused on extracting knowledge from real-world clinical data sources. This type of data is more abundant than data produced during clinical trials and potentially more informative about real-world clinical practice. However, this comes at the cost of less curated and controlled data sets. In this work we aim to predict disability progression by optimally extracting information from longitudinal patient data in the real-world setting, with a special focus on the sporadic sampling problem. Methods: We use machine learning methods suited for patient trajectories modeling, such as recurrent neural networks and tensor factorization. A subset of 6682 patients from the MSBase registry is used. Results: We can predict disability progression of patients in a two-year horizon with an ROC-AUC of 0.85, which represents a 32% decrease in the ranking pair error (1-AUC) compared to reference methods using static clinical features. Conclusions: Compared to the models available in the literature, this work uses the most complete patient history for MS disease progression prediction and represents a step forward towards AI-assisted precision medicine in MS.