Site Editor
Gregory J. Riely, MD, PhD
Gregory J. Riely, MD, PhD
Posted: Wednesday, April 15, 2026
In a prospective cohort study of patients with metastatic non–small cell lung cancer (NSCLC), wearable device–derived step count outperformed Eastern Cooperative Oncology Group (ECOG) performance status in predicting overall survival. These findings were reported by Roma Bhatia, MD, of Huntsman Cancer Institute, University of Utah, Salt Lake City, and colleagues in JNCCN–Journal of the National Comprehensive Cancer Network.
Daily step count was prospectively collected via wearable device from 102 patients and averaged over the first week of valid wear (> 500 minutes/day within 90 days of enrollment). Using least absolute shrinkage and selection operator (LASSO) regression, predictor selection was performed from 11 demographic, disease, treatment, and functional variables, and 3 Cox models (step count, performance status, and a combined model adjusted for additional LASSO-selected predictors) were fitted. The data were split into training (70%) and testing (30%) sets, and model discrimination was assessed using Harrell’s C-index.
Among participants, 67% were female, 72% were aged at least 60 years, and 82% were ex-smokers or never-smokers. Most patients had adenocarcinoma (83%), a performance status of 0 to 1 (86%), and were enrolled during first-line treatment (80%). At baseline, 62% received chemo and/or immune checkpoint inhibitors and 38% were treated with targeted therapy.
The median number of steps taken per day was 3,289. During the median 1-year follow-up period, 58 patients (57%) died. Using LASSO, daily step count, physician performance status, and targeted therapy were identified as key predictors of survival. The model based on daily step count showed better performance than the performance status–based model (C-index = 0.78 vs 0.72), with no further gain from the full model (0.79 vs 0.78).
“[The results] support the use of wearable-collected activity data to potentially enhance prognostication, guide treatment decisions, and identify at-risk patients for targeted supportive interventions in [metastatic] NSCLC,” the investigators concluded.
Disclosure: For full disclosures of the study authors, visit jnccn.org.
Journal of the National Comprehensive Cancer Network
JNCCN Spotlights
