- Title
- Longitudinal machine learning modeling of MS patient trajectories improves predictions of disability progression
- Creator
- De Brouwer, Edward; Becker, Thijs; Kappos, Ludwig; Sola, Patrizia; Cartechini, Elisabetta; Lechner-Scott, Jeannette; Alroughani, Raed; Gerlach, Oliver; Kalincik, Tomas; Granella, Franco; Grand'Maison, Francois; Bergamaschi, Roberto; Moreau, Yves; José Sá, M; Van Wijmeersch, B; Soysal, A; Sanchez-Menoyo, JL; Solaro, C; Boz, C; Iuliano, G; Buzzard, K; Aguera-Morales, E; Terzi, M; Havrdova, Eva Kubala; Trivio, TC; Spitaleri, D; Van Pesch, V; Shaygannejad, V; Moore, F; Oreja-Guevara, C; Maimone, D; Gouider, R; Csepany, T; Ramo-Tello, C; Trojano, Maria; Peeters, L; Eichau, Sara; Ozakbas, Serkan; Onofrj, Marco; Grammond, Pierre; Kuhle, Jens
- Relation
- Computer Methods and Programs in Biomedicine Vol. 208, Issue September 2021, no. 106180
- Publisher Link
- http://dx.doi.org/10.1016/j.cmpb.2021.106180
- Publisher
- Elsevier
- Resource Type
- journal article
- Date
- 2021
- Description
- 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.
- Subject
- multiple sclerosis; machine learning; longitudinal data; recurrent neural networks; electronic health records; disability progression
- Identifier
- http://hdl.handle.net/1959.13/1459395
- Identifier
- uon:45667
- Identifier
- ISSN:0169-2607
- Language
- eng
- Reviewed
- Hits: 6947
- Visitors: 6940
- Downloads: 0