Combining randomized and non-randomized data to predict heterogeneous effects of competing treatments.

Some patients benefit from a treatment while others may do so less or do not benefit at all. We have previously developed a two-stage network meta-regression prediction model that synthesized randomized trials and evaluates how treatment effects vary across patient characteristics. In this article, we extended this model to combine different sources of types in different formats: aggregate data (AD) and individual participant data (IPD) from randomized and non-randomized evidence. In the first stage, a prognostic model is developed to predict the baseline risk of the outcome using a large cohort study. In the second stage, we recalibrated this prognostic model to improve our predictions for patients enrolled in randomized trials. In the third stage, we used the baseline risk as effect modifier in a network meta-regression model combining AD, IPD randomized clinical trial to estimate heterogeneous treatment effects. We illustrated the approach in the re-analysis of a network of studies comparing three drugs for relapsing-remitting multiple sclerosis. Several patient characteristics influence the baseline risk of relapse, which in turn modifies the effect of the drugs. The proposed model makes personalized predictions for health outcomes under several treatment options and encompasses all relevant randomized and non-randomized evidence.

Visualizing the target estimand in comparative effectiveness studies with multiple treatments.

Aim: Comparative effectiveness research using real-world data often involves pairwise propensity score matching to adjust for confounding bias. We show that corresponding treatment effect estimates may have limited external validity, and propose two visualization tools to clarify the target estimand. Materials & methods: We conduct a simulation study to demonstrate, with bivariate ellipses and joy plots, that differences in covariate distributions across treatment groups may affect the external validity of treatment effect estimates. We showcase how these visualization tools can facilitate the interpretation of target estimands in a case study comparing the effectiveness of teriflunomide (TERI), dimethyl fumarate (DMF) and natalizumab (NAT) on manual dexterity in patients with multiple sclerosis. Results: In the simulation study, estimates of the treatment effect greatly differed depending on the target population. For example, when comparing treatment B with C, the estimated treatment effect (and respective standard error) varied from -0.27 (0.03) to -0.37 (0.04) in the type of patients initially receiving treatment B and C, respectively. Visualization of the matched samples revealed that covariate distributions vary for each comparison and cannot be used to target one common treatment effect for the three treatment comparisons. In the case study, the bivariate distribution of age and disease duration varied across the population of patients receiving TERI, DMF or NAT. Although results suggest that DMF and NAT improve manual dexterity at 1 year compared with TERI, the effectiveness of DMF versus NAT differs depending on which target estimand is used. Conclusion: Visualization tools may help to clarify the target population in comparative effectiveness studies and resolve ambiguity about the interpretation of estimated treatment effects.

Overall and patient-specific comparative effectiveness of dimethyl fumarate versus teriflunomide: A novel approach to precision medicine applied to the German NeuroTrans Data Multiple Sclerosis Registry.

Background: Multiple sclerosis (MS) comparative effectiveness research needs to go beyond average treatment effects (ATEs) and post-host subgroup analyses. Objective: This retrospective study assessed overall and patient-specific effects of dimethyl fumarate (DMF) versus teriflunomide (TERI) in patients with relapsing-remitting MS. Methods: A novel precision medicine (PM) scoring approach leverages advanced machine learning methods and adjusts for imbalances in baseline characteristics between patients receiving different treatments. Using the German NeuroTransData registry, we implemented and internally validated different scoring systems to distinguish patient-specific effects of DMF relative to TERI based on annualized relapse rates, time to first relapse, and time to confirmed disease progression. Results: Among 2791 patients, there was superior ATE of DMF versus TERI for the two relapse-related endpoints (p = 0.037 and 0.018). Low to moderate signals of treatment effect heterogeneity were detected according to individualized scores. A MS patient subgroup was identified for whom DMF was more effective than TERI (p = 0.013): older (45 versus 38 years), longer MS duration (110 versus 50 months), not newly diagnosed (74% versus 40%), and no prior glatiramer acetate usage (35% versus 5%). Conclusion: The implemented approach can disentangle prognostic differences from treatment effect heterogeneity and provide unbiased patient-specific profiling of comparative effectiveness based on real-world data.

Methods for comparative effectiveness based on time to confirmed disability progression with irregular observations in multiple sclerosis.

Real-world data sources offer opportunities to compare the effectiveness of treatments in practical clinical settings. However, relevant outcomes are often recorded selectively and collected at irregular measurement times. It is therefore common to convert the available visits to a standardized schedule with equally spaced visits. Although more advanced imputation methods exist, they are not designed to recover longitudinal outcome trajectories and typically assume that missingness is non-informative. We, therefore, propose an extension of multilevel multiple imputation methods to facilitate the analysis of real-world outcome data that is collected at irregular observation times. We illustrate multilevel multiple imputation in a case study evaluating two disease-modifying therapies for multiple sclerosis in terms of time to confirmed disability progression. This survival outcome is derived from repeated measurements of the Expanded Disability Status Scale, which is collected when patients come to the healthcare center for a clinical visit and for which longitudinal trajectories can be estimated. Subsequently, we perform a simulation study to compare the performance of multilevel multiple imputation to commonly used single imputation methods. Results indicate that multilevel multiple imputation leads to less biased treatment effect estimates and improves the coverage of confidence intervals, even when outcomes are missing not at random.

Synthesizing cross-design evidence and cross-format data using network meta-regression.

In network meta-analysis (NMA), we synthesize all relevant evidence about health outcomes with competing treatments. The evidence may come from randomized clinical trials (RCT) or non-randomized studies (NRS) as individual participant data (IPD) or as aggregate data (AD). We present a suite of Bayesian NMA and network meta-regression (NMR) models allowing for cross-design and cross-format synthesis. The models integrate a three-level hierarchical model for synthesizing IPD and AD into four approaches. The four approaches account for differences in the design and risk of bias (RoB) in the RCT and NRS evidence. These four approaches variously ignoring differences in RoB, using NRS to construct penalized treatment effect priors and bias-adjustment models that control the contribution of information from high RoB studies in two different ways. We illustrate the methods in a network of three pharmacological interventions and placebo for patients with relapsing-remitting multiple sclerosis. The estimated relative treatment effects do not change much when we accounted for differences in design and RoB. Conducting network meta-regression showed that intervention efficacy decreases with increasing participant age. We also re-analysed a network of 431 RCT comparing 21 antidepressants, and we did not observe material changes in intervention efficacy when adjusting for studies' high RoB. We re-analysed both case studies accounting for different study RoB. In summary, the described suite of NMA/NMR models enables the inclusion of all relevant evidence while incorporating information on the within-study bias in both observational and experimental data and enabling estimation of individualized treatment effects through the inclusion of participant characteristics.

Decision Curve Analysis for Personalized Treatment Choice between Multiple Options.

BACKGROUND: Decision curve analysis can be used to determine whether a personalized model for treatment benefit would lead to better clinical decisions. Decision curve analysis methods have been described to estimate treatment benefit using data from a single randomized controlled trial. OBJECTIVES: Our main objective is to extend the decision curve analysis methodology to the scenario in which several treatment options exist and evidence about their effects comes from a set of trials, synthesized using network meta-analysis (NMA). METHODS: We describe the steps needed to estimate the net benefit of a prediction model using evidence from studies synthesized in an NMA. We show how to compare personalized versus one-size-fit-all treatment decision-making strategies, such as "treat none" or "treat all patients with a specific treatment" strategies. First, threshold values for each included treatment need to be defined (i.e., the minimum risk difference compared with control that renders a treatment worth taking). The net benefit per strategy can then be plotted for a plausible range of threshold values to reveal the most clinically useful strategy. We applied our methodology to an NMA prediction model for relapsing-remitting multiple sclerosis, which can be used to choose between natalizumab, dimethyl fumarate, glatiramer acetate, and placebo. RESULTS: We illustrated the extended decision curve analysis methodology using several threshold value combinations for each available treatment. For the examined threshold values, the "treat patients according to the prediction model" strategy performs either better than or close to the one-size-fit-all treatment strategies. However, even small differences may be important in clinical decision making. As the advantage of the personalized model was not consistent across all thresholds, improving the existing model (by including, for example, predictors that will increase discrimination) is needed before advocating its clinical usefulness. CONCLUSIONS: This novel extension of decision curve analysis can be applied to NMA-based prediction models to evaluate their use to aid treatment decision making. HIGHLIGHTS: Decision curve analysis is extended into a (network) meta-analysis framework.Personalized models predicting treatment benefit are evaluated when several treatment options are available and evidence about their effects comes from a set of trials.Detailed steps to compare personalized versus one-size-fit-all treatment decision-making strategies are outlined.This extension of decision curve analysis can be applied to (network) meta-analysis-based prediction models to evaluate their use to aid treatment decision making.

Heterogeneity on long-term disability trajectories in patients with secondary progressive MS: a latent class analysis from Big MS Data network.

BACKGROUND: Over the decades, several natural history studies on patients with primary (PPMS) or secondary progressive multiple sclerosis (SPMS) were reported from international registries. In PPMS, a consistent heterogeneity on long-term disability trajectories was demonstrated. The aim of this study was to identify subgroups of patients with SPMS with similar longitudinal trajectories of disability over time. METHODS: All patients with MS collected within Big MS registries who received an SPMS diagnosis from physicians (cohort 1) or satisfied the Lorscheider criteria (cohort 2) were considered. Longitudinal Expanded Disability Status Scale (EDSS) scores were modelled by a latent class growth analysis (LCGA), using a non-linear function of time from the first EDSS visit in the range 3-4. RESULTS: A total of 3613 patients with SPMS were included in the cohort 1. LCGA detected three different subgroups of patients with a mild (n=1297; 35.9%), a moderate (n=1936; 53.6%) and a severe (n=380; 10.5%) disability trajectory. Median time to EDSS 6 was 12.1, 5.0 and 1.7 years, for the three groups, respectively; the probability to reach EDSS 6 at 8 years was 14.4%, 78.4% and 98.3%, respectively. Similar results were found among 7613 patients satisfying the Lorscheider criteria. CONCLUSIONS: Contrary to previous interpretations, patients with SPMS progress at greatly different rates. Our identification of distinct trajectories can guide better patient selection in future phase 3 SPMS clinical trials. Additionally, distinct trajectories could reflect heterogeneous pathological mechanisms of progression.

Predictors of treatment switching in the Big Multiple Sclerosis Data Network.

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.

Overall and patient-level comparative effectiveness of dimethyl fumarate and fingolimod: A precision medicine application to the Observatoire Français de la Sclérose en Plaques registry.

Background: Comparing real-world effectiveness and tolerability of therapies for relapsing-remitting multiple sclerosis is increasingly important, though average treatment effects fail to capture possible treatment effect heterogeneity. With the clinical course of the disease being highly heterogeneous across patients, precision medicine methods enable treatment response heterogeneity investigations. Objective: To compare real-world effectiveness and discontinuation profiles between dimethyl fumarate and fingolimod while investigating treatment effect heterogeneity with precision medicine methods. Methods: Adults initiating dimethyl fumarate or fingolimod as a second-line therapy were selected from a French registry. The primary outcome was annualized relapse rate at 12 months. Seven secondary outcomes relative to discontinuation and disease progression were considered. A precision medicine framework was used to characterize treatment effect heterogeneity. Results: Annualized relapse rates at 12 months were similar for dimethyl fumarate and fingolimod. The odd of treatment persistence was 47% lower for patients treated with dimethyl fumarate relative to those treated with fingolimod (odds ratio: 0.53, 95% confidence interval: 0.39, 0.70). None of the five precision medicine scoring approaches identified treatment heterogeneity. Conclusion: These findings substantiated the similar effectiveness and different discontinuation profiles for dimethyl fumarate and fingolimod as a second-line therapy for relapsing-remitting multiple sclerosis, with no significant effect heterogeneity observed.

Recommendations for the use of propensity score methods in multiple sclerosis research.

BACKGROUND: With many disease-modifying therapies currently approved for the management of multiple sclerosis, there is a growing need to evaluate the comparative effectiveness and safety of those therapies from real-world data sources. Propensity score methods have recently gained popularity in multiple sclerosis research to generate real-world evidence. Recent evidence suggests, however, that the conduct and reporting of propensity score analyses are often suboptimal in multiple sclerosis studies. OBJECTIVES: To provide practical guidance to clinicians and researchers on the use of propensity score methods within the context of multiple sclerosis research. METHODS: We summarize recommendations on the use of propensity score matching and weighting based on the current methodological literature, and provide examples of good practice. RESULTS: Step-by-step recommendations are presented, starting with covariate selection and propensity score estimation, followed by guidance on the assessment of covariate balance and implementation of propensity score matching and weighting. Finally, we focus on treatment effect estimation and sensitivity analyses. CONCLUSION: This comprehensive set of recommendations highlights key elements that require careful attention when using propensity score methods.

The use and quality of reporting of propensity score methods in multiple sclerosis literature: A review.

BACKGROUND: Propensity score (PS) analyses are increasingly used in multiple sclerosis (MS) research, largely owing to the greater availability of large observational cohorts and registry databases. OBJECTIVE: To evaluate the use and quality of reporting of PS methods in the recent MS literature. METHODS: We searched the PubMed database for articles published between January 2013 and July 2019. We restricted the search to comparative effectiveness studies of two disease-modifying therapies. RESULTS: Thirty-nine studies were included in the review, with most studies (62%) published within the past 3 years. All studies reported the list of covariates used for the PS model, but only 21% of studies mentioned how those covariates were selected. Most studies used PS matching (72%), followed by PS adjustment (18%), weighting (15%), and stratification (3%), with some overlap. Most studies using matching or weighting reported checking post-PS covariate imbalance (91%), although about 45% of these studies relied on p values from various statistical tests. Only 25% of studies using matching reported calculating robust standard errors for the PS analyses. CONCLUSIONS: The quality of reporting of PS methods in the MS literature is sub-optimal in general, and in some cases, inappropriate methods are used.

A two-stage prediction model for heterogeneous effects of treatments.

Treatment effects vary across different patients, and estimation of this variability is essential for clinical decision-making. We aimed to develop a model estimating the benefit of alternative treatment options for individual patients, extending a risk modeling approach in a network meta-analysis framework. We propose a two-stage prediction model for heterogeneous treatment effects by combining prognosis research and network meta-analysis methods where individual patient data are available. In the first stage, a prognostic model to predict the baseline risk of the outcome. In the second stage, we use the baseline risk score from the first stage as a single prognostic factor and effect modifier in a network meta-regression model. We apply the approach to a network meta-analysis of three randomized clinical trials comparing the relapses in Natalizumab, Glatiramer Acetate, and Dimethyl Fumarate, including 3590 patients diagnosed with relapsing-remitting multiple sclerosis. We find that the baseline risk score modifies the relative and absolute treatment effects. Several patient characteristics, such as age and disability status, impact the baseline risk of relapse, which in turn moderates the benefit expected for each of the treatments. For high-risk patients, the treatment that minimizes the risk of relapse in 2 years is Natalizumab, whereas Dimethyl Fumarate might be a better option for low-risk patients. Our approach can be easily extended to all outcomes of interest and has the potential to inform a personalized treatment approach.

Treatment Switching and Discontinuation Over 20 Years in the Big Multiple Sclerosis Data Network.

Background: Although over a dozen disease modifying treatments (DMTs) are available for relapsing forms of multiple sclerosis (MS), treatment interruption, switching and discontinuation are common challenges. The objective of this study was to describe treatment interruption and discontinuation in the Big MS data network. Methods: We merged information on 269,822 treatment episodes in 110,326 patients from 1997 to 2016 from five clinical registries in this cohort study. Treatment stop was defined as a clinician recorded DMT end for any reason and included treatment interruptions, switching to alternate DMTs and long-term or permanent discontinuations. Results: The incidence of DMT stopping cross the full observation period was lowest in FTY (19.7 per 100 person-years (PY) of treatment; 95% CI 19.2-20.1), followed by NAT (22.6/100 PY; 95% CI 22.2-23.0), IFNß (23.3/100 PY; 95% CI 23.2-23.5). Of the 184,013 observed DMT stops, 159,309 (86.6%) switched to an alternate DMT within 6 months. Reasons for stopping a drug were stable during the observation period with lack of efficacy being the most common reason followed by lack of tolerance and side effects. The proportion of patients continuing on most DMTs were similarly stable until 2014 and 2015 when drop from 83 to 75% was noted. Conclusions: DMT stopping reasons and rates were mostly stable over time with a slight increase in recent years, with the availability of more DMTs. The overall results suggest that discontinuation of MS DMTs is mostly due to DMT properties and to a lesser extent to risk management and a competitive market.

Early treatment delays long-term disability accrual in RRMS: Results from the BMSD network.

BACKGROUND: The optimal timing of treatment starts for achieving the best control on the long-term disability accumulation in multiple sclerosis (MS) is still to be defined. OBJECTIVE: The aim of this study was to estimate the optimal time to start disease-modifying therapies (DMTs) to prevent the long-term disability accumulation in MS, using a pooled dataset from the Big Multiple Sclerosis Data (BMSD) network. METHODS: Multivariable Cox regression models adjusted for the time to first treatment start from disease onset (in quintiles) were used. To mitigate the impact of potential biases, a set of pairwise propensity score (PS)-matched analyses were performed. The first quintile, including patients treated within 1.2 years from onset, was used as reference. RESULTS: A cohort of 11,871 patients (median follow-up after treatment start: 13.2 years) was analyzed. A 3- and 12-month confirmed disability worsening event and irreversible Expanded Disability Status Scale (EDSS) 4.0 and 6.0 scores were reached by 7062 (59.5%), 4138 (34.9%), 3209 (31.1%), and 1909 (16.5%) patients, respectively. The risk of reaching all the disability outcomes was significantly lower (p < 0.0004) for the first quintile patients' group. CONCLUSION: Real-world data from the BMSD demonstrate that DMTs should be commenced within 1.2 years from the disease onset to reduce the risk of disability accumulation over the long term.

Estimation and Validation of Ratio-based Conditional Average Treatment Effects Using Observational Data.

While sample sizes in randomized clinical trials are large enough to estimate the average treatment effect well, they are often insufficient for estimation of treatment-covariate interactions critical to studying data-driven precision medicine. Observational data from real world practice may play an important role in alleviating this problem. One common approach in trials is to predict the outcome of interest with separate regression models in each treatment arm, and estimate the treatment effect based on the contrast of the predictions. Unfortunately, this simple approach may induce spurious treatment-covariate interaction in observational studies when the regression model is misspecified. Motivated by the need of modeling the number of relapses in multiple sclerosis patients, where the ratio of relapse rates is a natural choice of the treatment effect, we propose to estimate the conditional average treatment effect (CATE) as the ratio of expected potential outcomes, and derive a doubly robust estimator of this CATE in a semiparametric model of treatment-covariate interactions. We also provide a validation procedure to check the quality of the estimator on an independent sample. We conduct simulations to demonstrate the finite sample performance of the proposed methods, and illustrate their advantages on real data by examining the treatment effect of dimethyl fumarate compared to teriflunomide in multiple sclerosis patients.

Harnessing Real-World Data to Inform Decision-Making: Multiple Sclerosis Partners Advancing Technology and Health Solutions (MS PATHS).

Background: Multiple Sclerosis Partners Advancing Technology and Health Solutions (MS PATHS) is the first example of a learning health system in multiple sclerosis (MS). This paper describes the initial implementation of MS PATHS and initial patient characteristics. Methods: MS PATHS is an ongoing initiative conducted in 10 healthcare institutions in three countries, each contributing standardized information acquired during routine care. Institutional participation required the following: active MS patient census of ≥500, at least one Siemens 3T magnetic resonance imaging scanner, and willingness to standardize patient assessments, share standardized data for research, and offer universal enrolment to capture a representative sample. The eligible participants have diagnosis of MS, including clinically isolated syndrome, and consent for sharing pseudonymized data for research. MS PATHS incorporates a self-administered patient assessment tool, the Multiple Sclerosis Performance Test, to collect a structured history, patient-reported outcomes, and quantitative testing of cognition, vision, dexterity, and walking speed. Brain magnetic resonance imaging is acquired using standardized acquisition sequences on Siemens 3T scanners. Quantitative measures of brain volume and lesion load are obtained. Using a separate consent, the patients contribute DNA, RNA, and serum for future research. The clinicians retain complete autonomy in using MS PATHS data in patient care. A shared governance model ensures transparent data and sample access for research. Results: As of August 5, 2019, MS PATHS enrolment included participants (n = 16,568) with broad ranges of disease subtypes, duration, and severity. Overall, 14,643 (88.4%) participants contributed data at one or more time points. The average patient contributed 15.6 person-months of follow-up (95% CI: 15.5-15.8); overall, 166,158 person-months of follow-up have been accumulated. Those with relapsing-remitting MS demonstrated more demographic heterogeneity than the participants in six randomized phase 3 MS treatment trials. Across sites, a significant variation was observed in the follow-up frequency and the patterns of disease-modifying therapy use. Conclusions: Through digital health technology, it is feasible to collect standardized, quantitative, and interpretable data from each patient in busy MS practices, facilitating the merger of research and patient care. This approach holds promise for data-driven clinical decisions and accelerated systematic learning.

On the aggregation of published prognostic scores for causal inference in observational studies.

As real world evidence on drug efficacy involves nonrandomized studies, statistical methods adjusting for confounding are needed. In this context, prognostic score (PGS) analysis has recently been proposed as a method for causal inference. It aims to restore balance across the different treatment groups by identifying subjects with a similar prognosis for a given reference exposure ("control"). This requires the development of a multivariable prognostic model in the control arm of the study sample, which is then extrapolated to the different treatment arms. Unfortunately, large cohorts for developing prognostic models are not always available. Prognostic models are therefore subject to a dilemma between overfitting and parsimony; the latter being prone to a violation of the assumption of no unmeasured confounders when important covariates are ignored. Although it is possible to limit overfitting by using penalization strategies, an alternative approach is to adopt evidence synthesis. Aggregating previously published prognostic models may improve the generalizability of PGS, while taking account of a large set of covariates-even when limited individual participant data are available. In this article, we extend a method for prediction model aggregation to PGS analysis in nonrandomized studies. We conduct extensive simulations to assess the validity of model aggregation, compared with other methods of PGS analysis for estimating marginal treatment effects. We show that aggregating existing PGS into a "meta-score" is robust to misspecification, even when elementary scores wrongfully omit confounders or focus on different outcomes. We illustrate our methods in a setting of treatments for asthma.

A proof-of-concept application of a novel scoring approach for personalized medicine in multiple sclerosis.

BACKGROUND: Stratified medicine methodologies based on subgroup analyses are often insufficiently powered. More powerful personalized medicine approaches are based on continuous scores. OBJECTIVE: We deployed a patient-specific continuous score predicting treatment response in patients with relapsing-remitting multiple sclerosis (RRMS). METHODS: Data from two independent randomized controlled trials (RCTs) were used to build and validate an individual treatment response (ITR) score, regressing annualized relapse rates (ARRs) on a set of baseline predictors. RESULTS: The ITR score for the combined treatment groups versus placebo detected differential clinical response in both RCTs. High responders in one RCT had a cross-validated ARR ratio of 0.29 (95% confidence interval (CI) = 0.13-0.55) versus 0.62 (95% CI = 0.47-0.83) for all other responders (heterogeneity p = 0.038) and were validated in the other RCT, with the corresponding ARR ratios of 0.31 (95% CI = 0.18-0.56) and 0.61 (95% CI = 0.47-0.79; heterogeneity p = 0.036). The strongest treatment effect modifiers were the Short Form-36 Physical Component Summary, age, Visual Function Test 2.5%, prior MS treatment and Expanded Disability Status Scale. CONCLUSION: Our modelling strategy detects and validates an ITR score and opens up avenues for building treatment response calculators that are also applicable in routine clinical practice.

Predicting disability progression in multiple sclerosis: Insights from advanced statistical modeling.

BACKGROUND: There is an unmet need for precise methods estimating disease prognosis in multiple sclerosis (MS). OBJECTIVE: Using advanced statistical modeling, we assessed the prognostic value of various clinical measures for disability progression. METHODS: Advanced models to assess baseline prognostic factors for disability progression over 2 years were applied to a pooled sample of patients from placebo arms in four different phase III clinical trials. least absolute shrinkage and selection operator (LASSO) and ridge regression, elastic nets, support vector machines, and unconditional and conditional random forests were applied to model time to clinical disability progression confirmed at 24 weeks. Sensitivity analyses for different definitions of a combined endpoint were carried out, and bootstrap was used to assess prediction model performance. RESULTS: A total of 1582 patients were included, of which 434 (27.4%) had disability progression in a combined endpoint over 2 years. Overall model discrimination performance was relatively poor (all C-indices ⩽ 0.65) across all models and across different definitions of progression. CONCLUSION: Inconsistency of prognostic factor importance ranking confirmed the relatively poor prediction ability of baseline factors in modeling disease progression in MS. Our findings underline the importance to explore alternative predictors as well as alternative definitions of commonly used endpoints.