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

Jean-Pierre R. Falet (), Joshua Durso-Finley, Brennan Nichyporuk, Julien Schroeter, Francesca Bovis, Maria-Pia Sormani, Doina Precup, Tal Arbel and Douglas Lorne Arnold
Additional contact information
Jean-Pierre R. Falet: McGill University
Joshua Durso-Finley: McGill University
Brennan Nichyporuk: McGill University
Julien Schroeter: McGill University
Francesca Bovis: University of Genoa
Maria-Pia Sormani: University of Genoa
Doina Precup: Mila-Quebec AI Institute
Tal Arbel: McGill University
Douglas Lorne Arnold: McGill University

Nature Communications, 2022, vol. 13, issue 1, 1-12

Abstract: 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.

Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-022-33269-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-33269-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-022-33269-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().