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.
- Publikační typ
- časopisecké články MeSH
WHAT IS THIS SUMMARY ABOUT?: Patient registries contain anonymous data from people who share the same medical condition. The MSBase registry contains information from over 80,000 people living with multiple sclerosis (MS) across 41 countries. Using information from the MSBase registry, the GLIMPSE (Generating Learnings In MultiPle SclErosis) study looked at real-life outcomes in 3475 people living with MS who were treated with cladribine tablets (Mavenclad®) compared with other oral treatments. WHAT WERE THE RESULTS?: Results showed that people treated with cladribine tablets stayed on treatment for longer than other treatments given by mouth. They also had fewer relapses (also called flare ups of symptoms) than people who received a different oral treatment for their MS. WHAT DO THE RESULTS MEAN?: The results provide evidence that, compared with other oral treatments for MS, cladribine tablets are an effective medicine for people living with MS.
- Klíčová slova
- cladribine tablets, dimethyl fumarate (Tecfidera®), fingolimod (Gilenya®), lay summary, multiple sclerosis, relapses, teriflunomide (Aubagio®), treatment options,
- MeSH
- imunosupresiva terapeutické užití MeSH
- kladribin terapeutické užití MeSH
- lidé MeSH
- registrace MeSH
- relabující-remitující roztroušená skleróza * farmakoterapie MeSH
- roztroušená skleróza * farmakoterapie MeSH
- tablety MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
- Názvy látek
- imunosupresiva MeSH
- kladribin MeSH
- tablety MeSH
BACKGROUND: Exposure to disease-modifying therapy (DMT) during early pregnancy in women with relapsing-remitting MS (RRMS) may be increasing. OBJECTIVE: To retrospectively determine incidence of pregnancy, DMT exposure and pregnancy outcomes in women with RRMS. METHODS: We identified all women with RRMS aged 15-45 years in the MSBase Registry between 2005-2016. Annualised pregnancy incidence rates were calculated using Poisson regression models. DMT exposures and pregnancy outcomes were assessed. RESULTS: Of 9,098 women meeting inclusion criteria, 1,178 (13%) women recorded 1,521 pregnancies. The annualised incidence rate of pregnancy was 0.042 (95% CI 0.040, 0.045). A total of 635 (42%) reported pregnancies were conceived on DMT, increasing from 27% in 2006 to 62% in 2016. The median duration of DMT exposure during pregnancy was 30 days (IQR: 9, 50). There were a higher number of induced abortions on FDA pregnancy class C/D drugs compared with pregnancy class B and no DMT (p = 0.010); but no differences in spontaneous abortions, term or preterm births. CONCLUSIONS: We report low pregnancy incidence rates, with increasing number of pregnancies conceived on DMT over the past 12-years. The median duration of DMT exposure in pregnancy was relatively short at one month.
- Klíčová slova
- Incidence, Multiple sclerosis, Outcomes, Pregnancy, Therapy,
- MeSH
- dospělí MeSH
- imunologické faktory terapeutické užití MeSH
- incidence MeSH
- kohortové studie MeSH
- komplikace těhotenství epidemiologie terapie MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- následné studie MeSH
- registrace MeSH
- relabující-remitující roztroušená skleróza epidemiologie terapie MeSH
- retrospektivní studie MeSH
- těhotenství MeSH
- výsledek těhotenství MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- těhotenství MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- Názvy látek
- imunologické faktory MeSH
OBJECTIVE: To evaluate variability and predictability of disability trajectories in moderately advanced and advanced multiple sclerosis (MS), and their modifiability with immunomodulatory therapy. METHODS: The epochs between Expanded Disability Status Scale (EDSS) steps 3-6, 4-6 and 6-6.5 were analysed. Patients with relapse-onset MS and having reached 6-month confirmed baseline EDSS step (3/4/6) were identified in MSBase, a global observational MS cohort study. We used multivariable survival models to examine the impact of disease-modifying therapy, clinical and demographic factors on progression to the outcome EDSS step (6/6.5). Sensitivity analyses with varying outcome definitions and inclusion criteria were conducted. RESULTS: For the EDSS 3-6, 4-6 and 6-6.5 epochs, 1560, 1504 and 1231 patients were identified, respectively. Disability trajectories showed large coefficients of variance prebaseline (0.92-1.11) and postbaseline (2.15-2.50), with no significant correlations. The probability of reaching the outcome step was not associated with prebaseline variables, but was increased by higher relapse rates during each epoch (HRs 1.58-3.07; p<0.001). A greater proportion of each epoch treated with higher efficacy therapies was associated with lower risk of reaching the outcome disability step (HRs 0.72-0.91 per 25%; p≤0.02). 3 sensitivity analyses confirmed these results. CONCLUSIONS: Disease progression during moderately advanced and advanced MS is highly variable and amnesic to prior disease activity. Lower relapse rates and greater time on higher efficacy immunomodulatory therapy after reaching EDSS steps 3, 4 and 6 are associated with a decreased risk of accumulating further disability. Highly effective immunomodulatory therapy ameliorates accumulation of disability in moderately advanced and advanced relapse-onset MS.
- MeSH
- imunomodulace imunologie MeSH
- kohortové studie MeSH
- lidé MeSH
- postižení * MeSH
- posuzování pracovní neschopnosti MeSH
- progrese nemoci * MeSH
- relabující-remitující roztroušená skleróza farmakoterapie imunologie MeSH
- Check Tag
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- pozorovací studie MeSH