Dataset Information

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning.

ABSTRACT: Disability progression in multiple sclerosis remains resistant to treatment. The absence of a suitable biomarker to allow for phase 2 clinical trials presents a high barrier for drug development. We propose to enable short proof-of-concept trials by increasing statistical power using a deep-learning predictive enrichment strategy. Specifically, a multi-headed multilayer perceptron is used to estimate the conditional average treatment effect (CATE) using baseline clinical and imaging features, and patients predicted to be most responsive are preferentially randomized into a trial. Leveraging data from six randomized clinical trials (n = 3,830), we first pre-trained the model on the subset of relapsing-remitting MS patients (n = 2,520), then fine-tuned it on a subset of primary progressive MS (PPMS) patients (n = 695). In a separate held-out test set of PPMS patients randomized to anti-CD20 antibodies or placebo (n = 297), the average treatment effect was larger for the 50% (HR, 0.492; 95% CI, 0.266-0.912; p = 0.0218) and 30% (HR, 0.361; 95% CI, 0.165-0.79; p = 0.008) predicted to be most responsive, compared to 0.743 (95% CI, 0.482-1.15; p = 0.179) for the entire group. The same model could also identify responders to laquinimod in another held-out test set of PPMS patients (n = 318). Finally, we show that using this model for predictive enrichment results in important increases in power.

SUBMITTER: Falet JR

PROVIDER: S-EPMC9512913 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning.

Falet Jean-Pierre R JR Durso-Finley Joshua J Nichyporuk Brennan B Schroeter Julien J Bovis Francesca F Sormani Maria-Pia MP Precup Doina D Arbel Tal T Arnold Douglas Lorne DL

Nature communications 20220926 1

Disability progression in multiple sclerosis remains resistant to treatment. The absence of a suitable biomarker to allow for phase 2 clinical trials presents a high barrier for drug development. We propose to enable short proof-of-concept trials by increasing statistical power using a deep-learning predictive enrichment strategy. Specifically, a multi-headed multilayer perceptron is used to estimate the conditional average treatment effect (CATE) using baseline clinical and imaging features, an ...[more]

PMID: 36163349

Similar Datasets

Project description:IntroductionMultiple sclerosis (MS) is a chronic disease of the central nervous system. Estimates of MS natural history (NH) disability progression speed from clinical observations vary worldwide. This may reflect, in part, variance in censoring-bias) (missing observations) and assumptions about when irreversible disability progression events occurred. We test whether estimates of progression speed which assume midpoint survival time at irreversible disability endpoints are significantly faster than estimates which assume maximum survival time, and are more stable across study groups and time periods.MethodsOur Nova Scotia NH study population includes 2,240 definite relapsing-onset multiple sclerosis (R-MS) natural history patients with 18,078 Expanded Disability Status Scale (EDSS) clinical observations in study period 1979-2010. Progression speed is measured by rate-of-change in range EDSS 0-6 and by survival time at irreversible endpoints EDSS 1-9. Midpoint censoring-bias-reduction methods are applied to clinical observations.FindingsTypical EDSS increase per year in range EDSS 0-6, assuming midpoint survival time, is estimated to be 0.168 for all R-MS, 0.204 for eventually-DMD-treated patients and 0.155 for never-DMD-treated patients. Estimates assuming midpoint rather than maximum survival time are significantly faster: 16% faster for all R-MS natural history patients, 6% faster for eventually-DMD-treated patients, and 21% faster for never-DMD-treated patients. The variability of estimates across study groups and time periods decreased when midpoint survival time was assumed.ConclusionsEstimates of typical disease progression speed from 1979-2010 Nova Scotia clinical observations are sensitive to censoring-bias and to analysts' survival time assumptions. Censoring-bias-adjusted estimates of typical natural history disability progression speed in relapsing-onset multiple sclerosis patients are significantly faster, and less variable within and across study groups and time periods, than unadjusted estimates, and are, arguably, more relevant for various stakeholders. The application of censoring-bias-reduction methods to other multiple sclerosis clinical databases may reduce variability in estimates of disability progression speed worldwide.

Project description:ImportanceTherapeutic options for patients with secondary progressive multiple sclerosis (SPMS) are limited.ObjectiveTo analyze disability progression in patients with SPMS treated with rituximab compared with matched control patients never treated with rituximab.Design, setting, and participantsThis retrospective cohort study analyzed data obtained from patients with SPMS at 3 multiple sclerosis centers located in Basel and Lugano, Switzerland, and Amsterdam, the Netherlands, from 2004 to 2017. Patients were included for analysis if they had received a diagnosis of SPMS, were treated (57 eligible; 54 included) or never treated (504 eligible; 59 included) with rituximab, and had at least 1 follow-up visit. The variables used for propensity score matching were sex, age, Expanded Disability Status Scale (EDSS) score, and disease duration. Follow-up duration was up to 10 years, with a mean (SD) of 3.5 (2.6) years for rituximab-treated patients and 5.4 (2.4) years for controls in the total cohort and a mean (SD) of 3.5 (2.7) years for rituximab-treated patients and 4.8 (2.2) years for controls in the matched cohort.ExposuresComparing EDSS score progression in patients with SPMS (treated with rituximab vs not treated with rituximab) using propensity score matching.Main outcomes and measuresThe primary end point was progression of EDSS score after baseline, and the secondary end point was time to confirmed disability progression.ResultsAfter 1:1 propensity score matching, 44 matched pairs (88 patients) were included in the analysis. At baseline, patients treated with rituximab had a mean (SD) age of 49.7 (10.0) years, mean (SD) disease duration of 18.2 (9.4) years, and mean (SD) EDSS score of 5.9 (1.4), and 26 (59%) were women, whereas controls had a mean (SD) age of 51.3 (7.4) years, mean (SD) disease duration of 19.4 (8.7) years, and mean (SD) EDSS score of 5.70 (1.29), and 27 (61%) were women. In the covariate-adjusted analysis of the matched set, patients with SPMS who were treated with rituximab had a significantly lower EDSS score during a mean (SD) follow-up of 3.5 (2.7) years (mean difference, -0.52; 95% CI, -0.79 to -0.26; P < .001). Time to confirmed disability progression was significantly delayed in the rituximab-treated group (hazard ratio, 0.49; 95% CI, 0.26-0.93; P = .03).Conclusions and relevanceIn this study, patients with SPMS treated with rituximab had a significantly lower EDSS score for up to 10 years of follow-up and a significantly delayed confirmed progression compared with matched controls, suggesting that B-cell depletion by rituximab may be therapeutically beneficial in these patients. A prospective randomized clinical trial with a better level of evidence is needed to confirm the efficacy of rituximab in such patients.

Project description:BACKGROUND:Evoked potentials (EPs) are a measure of the conductivity of the central nervous system. They are used to monitor disease progression of multiple sclerosis patients. Previous studies only extracted a few variables from the EPs, which are often further condensed into a single variable: the EP score. We perform a machine learning analysis of motor EP that uses the whole time series, instead of a few variables, to predict disability progression after two years. Obtaining realistic performance estimates of this task has been difficult because of small data set sizes. We recently extracted a dataset of EPs from the Rehabiliation & MS Center in Overpelt, Belgium. Our data set is large enough to obtain, for the first time, a performance estimate on an independent test set containing different patients. METHODS:We extracted a large number of time series features from the motor EPs with the highly comparative time series analysis software package. Mutual information with the target and the Boruta method are used to find features which contain information not included in the features studied in the literature. We use random forests (RF) and logistic regression (LR) classifiers to predict disability progression after two years. Statistical significance of the performance increase when adding extra features is checked. RESULTS:Including extra time series features in motor EPs leads to a statistically significant improvement compared to using only the known features, although the effect is limited in magnitude (ΔAUC = 0.02 for RF and ΔAUC = 0.05 for LR). RF with extra time series features obtains the best performance (AUC = 0.75±0.07 (mean and standard deviation)), which is good considering the limited number of biomarkers in the model. RF (a nonlinear classifier) outperforms LR (a linear classifier). CONCLUSIONS:Using machine learning methods on EPs shows promising predictive performance. Using additional EP time series features beyond those already in use leads to a modest increase in performance. Larger datasets, preferably multi-center, are needed for further research. Given a large enough dataset, these models may be used to support clinicians in their decision making process regarding future treatment.

Dataset Information

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning.

Publications

Estimating individual treatment effect on disability progression in multiple sclerosis using deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets