Most cited article - PubMed ID 29050389
Towards personalized therapy for multiple sclerosis: prediction of individual treatment response
Early prediction of disability progression in multiple sclerosis (MS) remains challenging despite its critical importance for therapeutic decision-making. We present the first systematic evaluation of personalized federated learning (PFL) for 2-year MS disability progression prediction, leveraging multi-center real-world data from over 26,000 patients. While conventional federated learning (FL) enables privacy-aware collaborative modeling, it remains vulnerable to institutional data heterogeneity. PFL overcomes this challenge by adapting shared models to local data distributions without compromising privacy. We evaluated two personalization strategies: a novel AdaptiveDualBranchNet architecture with selective parameter sharing, and personalized fine-tuning of global models, benchmarked against centralized and client-specific approaches. Baseline FL underperformed relative to personalized methods, whereas personalization significantly improved performance, with personalized FedProx and FedAVG achieving ROC-AUC scores of 0.8398 ± 0.0019 and 0.8384 ± 0.0014, respectively. These findings establish personalization as critical for scalable, privacy-aware clinical prediction models and highlight its potential to inform earlier intervention strategies in MS and beyond.
- Publication type
- Journal Article MeSH
Multiple sclerosis (MS) is a devastating immune-mediated disorder of the central nervous system resulting in progressive disability accumulation. As there is no cure available yet for MS, the primary therapeutic objective is to reduce relapses and to slow down disability progression as early as possible during the disease to maintain and/or improve health-related quality of life. However, optimizing treatment for people with MS (pwMS) is complex and challenging due to the many factors involved and in particular, the high degree of clinical and sub-clinical heterogeneity in disease progression among pwMS. In this paper, we discuss these many different challenges complicating treatment optimization for pwMS as well as how a shift towards a more pro-active, data-driven and personalized medicine approach could potentially improve patient outcomes for pwMS. We describe how the 'Clinical Impact through AI-assisted MS Care' (CLAIMS) project serves as a recent example of how to realize such a shift towards personalized treatment optimization for pwMS through the development of a platform that offers a holistic view of all relevant patient data and biomarkers, and then using this data to enable AI-supported prognostic modelling.
- Keywords
- AI, data, diagnosis, disease progression, multiple sclerosis, personalized medicine, prognosis,
- MeSH
- Biomarkers MeSH
- Precision Medicine * methods trends MeSH
- Quality of Life MeSH
- Humans MeSH
- Prognosis MeSH
- Disease Progression MeSH
- Multiple Sclerosis * therapy immunology MeSH
- Artificial Intelligence * trends MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Names of Substances
- Biomarkers MeSH
BACKGROUND: Disability progression is a key milestone in the disease evolution of people with multiple sclerosis (PwMS). Prediction models of the probability of disability progression have not yet reached the level of trust needed to be adopted in the clinic. A common benchmark to assess model development in multiple sclerosis is also currently lacking. METHODS: Data of adult PwMS with a follow-up of at least three years from 146 MS centers, spread over 40 countries and collected by the MSBase consortium was used. With basic inclusion criteria for quality requirements, it represents a total of 15, 240 PwMS. External validation was performed and repeated five times to assess the significance of the results. Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) guidelines were followed. Confirmed disability progression after two years was predicted, with a confirmation window of six months. Only routinely collected variables were used such as the expanded disability status scale, treatment, relapse information, and MS course. To learn the probability of disability progression, state-of-the-art machine learning models were investigated. The discrimination performance of the models is evaluated with the area under the receiver operator curve (ROC-AUC) and under the precision recall curve (AUC-PR), and their calibration via the Brier score and the expected calibration error. All our preprocessing and model code are available at https://gitlab.com/edebrouwer/ms_benchmark, making this task an ideal benchmark for predicting disability progression in MS. FINDINGS: Machine learning models achieved a ROC-AUC of 0⋅71 ± 0⋅01, an AUC-PR of 0⋅26 ± 0⋅02, a Brier score of 0⋅1 ± 0⋅01 and an expected calibration error of 0⋅07 ± 0⋅04. The history of disability progression was identified as being more predictive for future disability progression than the treatment or relapses history. CONCLUSIONS: Good discrimination and calibration performance on an external validation set is achieved, using only routinely collected variables. This suggests machine-learning models can reliably inform clinicians about the future occurrence of progression and are mature for a clinical impact study.
- Publication type
- Journal Article MeSH
BACKGROUND: Treatment switching is a common challenge and opportunity in real-world clinical practice. Increasing diversity in disease-modifying treatments (DMTs) has generated interest in the identification of reliable and robust predictors of treatment switching across different countries, DMTs, and time periods. OBJECTIVE: The objective of this retrospective, observational study was to identify independent predictors of treatment switching in a population of relapsing-remitting MS (RRMS) patients in the Big Multiple Sclerosis Data Network of national clinical registries, including the Italian MS registry, the OFSEP of France, the Danish MS registry, the Swedish national MS registry, and the international MSBase Registry. METHODS: In this cohort study, we merged information on 269,822 treatment episodes in 110,326 patients from 1997 to 2018 from five clinical registries. Patients were included in the final pooled analysis set if they had initiated at least one DMT during the relapsing-remitting MS (RRMS) stage. Patients not diagnosed with RRMS or RRMS patients not initiating DMT therapy during the RRMS phase were excluded from the analysis. The primary study outcome was treatment switching. A multilevel mixed-effects shared frailty time-to-event model was used to identify independent predictors of treatment switching. The contributing MS registry was included in the pooled analysis as a random effect. RESULTS: Every one-point increase in the Expanded Disability Status Scale (EDSS) score at treatment start was associated with 1.08 times the rate of subsequent switching, adjusting for age, sex, and calendar year (adjusted hazard ratio [aHR] 1.08; 95% CI 1.07-1.08). Women were associated with 1.11 times the rate of switching relative to men (95% CI 1.08-1.14), whilst older age was also associated with an increased rate of treatment switching. DMTs started between 2007 and 2012 were associated with 2.48 times the rate of switching relative to DMTs that began between 1996 and 2006 (aHR 2.48; 95% CI 2.48-2.56). DMTs started from 2013 onwards were more likely to switch relative to the earlier treatment epoch (aHR 8.09; 95% CI 7.79-8.41; reference = 1996-2006). CONCLUSION: Switching between DMTs is associated with female sex, age, and disability at baseline and has increased in frequency considerably in recent years as more treatment options have become available. Consideration of a patient's individual risk and tolerance profile needs to be taken into account when selecting the most appropriate switch therapy from an expanding array of treatment choices.
- Keywords
- disease modifying treatment (DMT), disease registry, multiple sclerosis, real world evidence (RWE), treatment switching,
- Publication type
- Journal Article MeSH
The clinical course of multiple sclerosis (MS) is highly variable among patients, thus creating important challenges for the neurologist to appropriately treat and monitor patient progress. Despite some patients having apparently similar symptom severity at MS disease onset, their prognoses may differ greatly. To this end, we believe that a proactive disposition on the part of the neurologist to identify prognostic "red flags" early in the disease course can lead to much better long-term outcomes for the patient in terms of reduced disability and improved quality of life. Here, we present a prognosis tool in the form of a checklist of clinical, imaging and biomarker parameters which, based on consensus in the literature and on our own clinical experiences, we have established to be associated with poorer or improved clinical outcomes. The neurologist is encouraged to use this tool to identify the presence or absence of specific variables in individual patients at disease onset and thereby implement sufficiently effective treatment strategies that appropriately address the likely prognosis for each patient.
- Keywords
- biomarkers, clinical parameters, evoked potentials, magnetic resonance imaging (MRI), multiple sclerosis, optical coherence tomography, prognosis, treatment,
- MeSH
- Biomarkers MeSH
- Quality of Life MeSH
- Humans MeSH
- Magnetic Resonance Imaging methods MeSH
- Prognosis MeSH
- Recurrence MeSH
- Multiple Sclerosis * diagnosis MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
- Review MeSH
- Names of Substances
- Biomarkers MeSH
OBJECTIVE: To compare the effectiveness of glatiramer acetate (GA) vs intramuscular interferon beta-1a (IFN-β-1a), we applied a previously published statistical method aimed at identifying patients' profiles associated with efficacy of treatments. METHODS: Data from 2 independent multiple sclerosis datasets, a randomized study (the Combination Therapy in Patients With Relapsing-Remitting Multiple Sclerosis [CombiRx] trial, evaluating GA vs IFN-β-1a) and an observational cohort extracted from MSBase, were used to build and validate a treatment response score, regressing annualized relapse rates (ARRs) on a set of baseline predictors. RESULTS: The overall ARR ratio of GA to IFN-β-1a in the CombiRx trial was 0.72. The response score (made up of a linear combination of age, sex, relapses in the previous year, disease duration, and Expanded Disability Status Scale score) detected differential response of GA vs IFN-β-1a: in the trial, patients with the largest benefit from GA vs IFN-β-1a (lower score quartile) had an ARR ratio of 0.40 (95% confidence interval [CI] 0.25-0.63), those in the 2 middle quartiles of 0.90 (95% CI 0.61-1.34), and those in the upper quartile of 1.14 (95% CI 0.59-2.18) (heterogeneity p = 0.012); this result was validated on MSBase, with the corresponding ARR ratios of 0.58 (95% CI 0.46-0.72), 0.92 (95% CI 0.77-1.09,) and 1.29 (95% CI 0.97-1.71); heterogeneity p < 0.0001). CONCLUSIONS: We demonstrate the possibility of a criterion, based on patients' characteristics, to choose whether to treat with GA or IFN-β-1a. This result, replicated on an independent real-life cohort, may have implications for clinical decisions in everyday clinical practice.
- MeSH
- Adjuvants, Immunologic administration & dosage MeSH
- Databases, Factual trends MeSH
- Adult MeSH
- Glatiramer Acetate administration & dosage MeSH
- Immunosuppressive Agents administration & dosage MeSH
- Injections, Intramuscular MeSH
- Interferon beta-1a administration & dosage MeSH
- Cohort Studies MeSH
- Middle Aged MeSH
- Humans MeSH
- Multiple Sclerosis, Relapsing-Remitting diagnosis drug therapy MeSH
- Treatment Outcome MeSH
- Check Tag
- Adult MeSH
- Middle Aged MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Observational Study MeSH
- Research Support, Non-U.S. Gov't MeSH
- Randomized Controlled Trial MeSH
- Research Support, N.I.H., Extramural MeSH
- Names of Substances
- Adjuvants, Immunologic MeSH
- Glatiramer Acetate MeSH
- Immunosuppressive Agents MeSH
- Interferon beta-1a MeSH