Related Experiment Video
Updated: Jun 23, 2026
A Neonatal Mouse Spinal Cord Compression Injury Model
Published on: March 27, 2016
Exploring synthetic controls in rare diseases with a proof of concept in spinal cord injury
Louis P Lukas1,2, Samuel Håkansson1,2, Miklovana Tuci1,2,3
1Department of Health Sciences and Technology (D-HEST), ETH Zurich, Zurich, Switzerland.
Background:
Successfully completing clinical trials for rare and heterogeneous disorders, like spinal cord injuries (SCI), remains challenging, thereby reducing the ability to test and translate promising preclinical findings. We propose synthetic controls, derived from data-driven predictions of recovery in patients undergoing standard treatments, to mitigate these challenges, in particular related to patient recruitment.
Methods:
Based on data from the European Multicenter Study about Spinal Cord Injury (EMSCI) and the Sygen trial, we construct synthetic controls from personalized predictions of neurological recovery of sequences of segmental motor scores. A total of six architectures (linear, tree, and deep learning models) are compared. We demonstrate the applicability of synthetic controls through a simulation framework modeling the randomization process in a clinical trial and a case study that re-evaluates the recently completed Nogo Inhibition in SCI (NISCI) trial as a single-arm trial post hoc.
Results:
The primary dataset included 4196 patients from EMSCI and 587 patients from the Sygen trial for external validation. We identified a convolutional neural network as the best-performing architecture to predict segmental motor score sequences, achieving a median root mean squared error below the neurological level of injury of 0.55. Our trial simulations demonstrate that synthetic controls are a viable alternative to randomization, as the proposed solution reduces intercohort heterogeneity and leads to no significant differences with randomized controls in our case study reassessing a clinical trial.
Conclusions:
We provide a comprehensive benchmark of data-driven prediction architectures for neurological recovery after SCI. Apart from offering individual patients a specific recovery prediction, these models constitute the basis for synthetic controls. Using real-world data from a completed trial in SCI, we show that synthetic controls could mitigate the challenges of small cohorts and patient recruitment in rare disorders, offering the opportunity to maximize the number of patients receiving an investigative treatment. GITHUB REPOSITORY: https://gitlab.ethz.ch/BMDSlab/publications/sci/sci-in-silico-trials .
Insights
Synthetic controls, generated from patient recovery predictions, offer a solution for rare disease clinical trials. This approach reduces patient recruitment challenges and intercohort heterogeneity in spinal cord injury (SCI) studies.
Area of Science:
- Neurology
- Biostatistics
- Clinical Trial Design
Background:
- Clinical trials for rare and heterogeneous disorders like spinal cord injury (SCI) face significant challenges in patient recruitment and translating preclinical findings.
- Synthetic controls, derived from data-driven recovery predictions, are proposed to mitigate these issues.
Purpose of the Study:
- To benchmark data-driven prediction architectures for neurological recovery after SCI.
- To develop and validate synthetic controls for use in clinical trials for rare diseases.
Main Methods:
- Constructed synthetic controls using personalized predictions of neurological recovery (segmental motor scores) from European Multicenter Study about Spinal Cord Injury (EMSCI) and Sygen trial data.
- Compared six architectures (linear, tree, deep learning) and identified the best-performing model.
- Validated synthetic controls via simulation and a post hoc re-evaluation of the Nogo Inhibition in SCI (NISCI) trial.
Main Results:
- A convolutional neural network achieved the best performance in predicting motor score recovery.
- Trial simulations demonstrated that synthetic controls reduce intercohort heterogeneity compared to traditional randomization.
- The case study showed no significant differences between synthetic and randomized controls.
Conclusions:
- Data-driven prediction models provide individual recovery forecasts and form the basis for synthetic controls.
- Synthetic controls can address challenges of small cohorts and recruitment in rare disease trials, potentially increasing patient access to investigational treatments.
- A comprehensive benchmark of prediction architectures for SCI recovery is provided.
Related Concept Videos
01:14Spinal Cord Injury ll: Pathophysiology
01:25Secondary Spinal Cord Injury llI: Pathophysiology