Inclusive Trial Designs in Acute Spinal Cord Injuries: Prediction-Based Stratification of Clinical Walking Outcome and Projected Enrolment Frequencies.

Patients were included only if they had the required baseline and outcome data, so the results may not represent people with missing follow-up or different injury severity. Some prediction groups were small, so the exact recovery pattern for each group is less certain. The model was built from assessments done within 15 days after injury, so it may not apply to patients assessed much earlier, such as within 72 hours. The study did not test a rehabilitation or drug intervention, so it cannot show whether treatment changes walking outcome. Validation was internal within the same database, not in an independent external population.

The authors declared no potential conflicts of interest. The work was funded by the European Union's Horizon 2020 programme, the Swiss State Secretariat for Education, Research and Innovation, and the International Foundation for Research in Paraplegia. The funders had no role in study design, data collection, analysis, interpretation, or manuscript writing.

Do not read the seven walking groups as proof that a therapy works. The study only predicted usual recovery after acute cervical spinal cord injury and estimated how many patients could be enrolled in future trials; it did not test an intervention.