Univariate Logistic Regression: Walking Cadence and Mobility Outcomes in Older Adults

Data from 213 participants in the Program to Improve Mobility in Aging (PRIMA) cohort trial, used to evaluate whether changes in walking cadence can identify responders to mobility interventions. Logistic regression models assessed the ability of cadence changes to predict clinically important improvements in gait speed and 6-minute walk test distance. The dataset was authored by Daniel S. Rubin and last updated on 2026-05-29.

Use Cases

• Training logistic regression models to predict mobility improvement based on walking cadence changes.
• Validating digitally measurable outcomes like cadence against established clinical tests such as the 6-minute walk test.
• Identifying optimal thresholds (e.g., ≥3 steps/min) for classifying intervention responders in aging populations.

Strengths

• Includes data from 213 participants in a prospective cohort trial.
• Reports specific model performance metrics, including an AUC of 0.90 for predicting gait speed improvement.
• Defines a clear optimal threshold (≥3 steps/min) with reported sensitivity and specificity values.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

Secondary analysis of the prospective Program to Improve Mobility in Aging (PRIMA) cohort trial.

Collection Method

Cadence was measured during usual-pace gait speed testing and the 6-minute walk test.

Freshness

Last updated 2026-05-29 17:29:19; freshness should be verified.