Retrospective cohort study to devise a treatment decision score predicting adverse 24-month radiological activity in early multiple sclerosis

Alexander Hapfelmeier; Begum Irmak On; Mark Mühlau; Jan S Kirschke; Achim Berthele; Christiane Gasperi; Ulrich Mansmann; Alexander Wuschek; Matthias Bussas; Martin Boeker; Antonios Bayas; Makbule Senel; Joachim Havla; Markus C Kowarik; Klaus Kuhn; Ingrid Gatz; Helmut Spengler; Benedikt Wiestler; Lioba Grundl; Dominik Sepp; Bernhard Hemmer

doi:10.1177/17562864231161892

Retrospective cohort study to devise a treatment decision score predicting adverse 24-month radiological activity in early multiple sclerosis

Ther Adv Neurol Disord. 2023 Mar 24:16:17562864231161892. doi: 10.1177/17562864231161892. eCollection 2023.

Authors

Alexander Hapfelmeier^{1

2

3}, Begum Irmak On^{4

3}, Mark Mühlau⁵, Jan S Kirschke⁶, Achim Berthele⁵, Christiane Gasperi⁵, Ulrich Mansmann^{4

3}, Alexander Wuschek⁵, Matthias Bussas⁵, Martin Boeker^{7

3}, Antonios Bayas^{8

3}, Makbule Senel^{9

3}, Joachim Havla^{10

3}, Markus C Kowarik^{11

3}, Klaus Kuhn^{7

3}, Ingrid Gatz^{7

3}, Helmut Spengler^{7

3}, Benedikt Wiestler⁶, Lioba Grundl⁶, Dominik Sepp⁶, Bernhard Hemmer^{12

3

13}

Affiliations

¹ Institute of AI and Informatics in Medicine, School of Medicine, Technical University of Munich, Ismaninger Str. 22, Munich 81675, Germany.
² Institute of General Practice and Health Services Research, School of Medicine, Technical University of Munich, Orleansstr. 47, Munich 81667, Germany.
³ Data Integration for Future Medicine (DIFUTURE) Consortium, Munich, Germany.
⁴ Institute for Medical Information Processing, Biometry, and Epidemiology, Ludwig-Maximilians-Universität in Munich, Munich, Germany.
⁵ Department of Neurology, Klinikum rechts der Isar School of Medicine, Technical University of Munich, Munich, Germany.
⁶ Department of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany.
⁷ Institute of AI and Informatics in Medicine, School of Medicine, Technical University of Munich, Munich, Germany.
⁸ Department of Neurology, Medical Faculty, University of Augsburg, Augsburg, Germany.
⁹ Department of Neurology, Ulm University Hospital, Ulm, Germany.
¹⁰ Institute of Clinical Neuroimmunology, LMU Hospital, Ludwig-Maximilians-Universität in Munich, Munich, Germany.
¹¹ Department of Neurology & Stroke and Hertie-Institute for Clinical Brain Research, Eberhard-Karls University of Tübingen, Tübingen, Germany.
¹² Department of Neurology, Klinikum rechts der Isar, School of Medicine, Technical University of Munich, Munich, Germany.
¹³ Munich Cluster for Systems Neurology (SyNergy), Munich, Germany.

Abstract

Background: Multiple sclerosis (MS) is a chronic neuroinflammatory disease affecting about 2.8 million people worldwide. Disease course after the most common diagnoses of relapsing-remitting multiple sclerosis (RRMS) and clinically isolated syndrome (CIS) is highly variable and cannot be reliably predicted. This impairs early personalized treatment decisions.

Objectives: The main objective of this study was to algorithmically support clinical decision-making regarding the options of early platform medication or no immediate treatment of patients with early RRMS and CIS.

Design: Retrospective monocentric cohort study within the Data Integration for Future Medicine (DIFUTURE) Consortium.

Methods: Multiple data sources of routine clinical, imaging and laboratory data derived from a large and deeply characterized cohort of patients with MS were integrated to conduct a retrospective study to create and internally validate a treatment decision score [Multiple Sclerosis Treatment Decision Score (MS-TDS)] through model-based random forests (RFs). The MS-TDS predicts the probability of no new or enlarging lesions in cerebral magnetic resonance images (cMRIs) between 6 and 24 months after the first cMRI.

Results: Data from 65 predictors collected for 475 patients between 2008 and 2017 were included. No medication and platform medication were administered to 277 (58.3%) and 198 (41.7%) patients. The MS-TDS predicted individual outcomes with a cross-validated area under the receiver operating characteristics curve (AUROC) of 0.624. The respective RF prediction model provides patient-specific MS-TDS and probabilities of treatment success. The latter may increase by 5-20% for half of the patients if the treatment considered superior by the MS-TDS is used.

Conclusion: Routine clinical data from multiple sources can be successfully integrated to build prediction models to support treatment decision-making. In this study, the resulting MS-TDS estimates individualized treatment success probabilities that can identify patients who benefit from early platform medication. External validation of the MS-TDS is required, and a prospective study is currently being conducted. In addition, the clinical relevance of the MS-TDS needs to be established.

Keywords: machine learning; multiple sclerosis; personalized medicine; predictive factor; predictive model; treatment effect.