DATA

Our Data Resources

We bring together longitudinal clinical records, molecular testing, imaging, and laboratory data to support cancer research and AI development. Our current data resources include the ROOT HEALTH NSCLC cohort at Samsung Medical Center.

Cohort definition: 38,154 patients with NSCLC, who received anticancer treatment (Systemic therapy, surgery, radio therapy and clinical trials etc.) at Samsung Medical Center. Data cutoff: September 18, 2026.

Data at a Glance

Key data volumes currently available in the ROOT HEALTH NSCLC cohort.

38,154
NSCLC Patients

Excluding stage 0; patients received cancer-directed treatment at SMC.

692,312
Imaging Examinations

Chest CT 500,919 · Brain MRI 117,756 · PET 73,637

1,298,103
OPD Visits

38,154 patients with OPD follow-up · mean 34.0 visits/patient

16,649,133
Laboratory Tests

Tests performed after NSCLC diagnosis; 37,920 patients · mean 439.1 tests/patient

Explore Our Data

Explore our clinical, molecular, imaging, and longitudinal follow-up data. Select a category to view detailed variables and counts.

Clinical Variables

Registry/common information, demographics, clinical trial participation, cohort classification, visits and follow-up, body measurements, vital status, recurrence, metastasis, survival outcomes, medical history, ECOG performance status, diagnosis, TNM staging, molecular examinations, and treatment history.

View clinical variables

Genomic & Biomarker Data

Testing coverage and test volumes for EGFR, ALK, PD-L1, BRAF V600E, RAS, ROS1, NTRK, HER2, MET exon 14 skipping, HER2 IHC, MET IHC/FISH, and overall NGS testing.

View biomarker data

Annual Biomarker Testing

Diagnosis-year-specific testing trends from 2008 through 2026, including the number and percentage of patients tested for EGFR, ALK, PD-L1, and NGS.

View annual testing data

Imaging, Follow-up & Laboratory Data

Imaging volumes for Chest CT, Brain MRI, and PET; outpatient follow-up metrics; and 25 laboratory test types including blood counts, chemistry, coagulation, inflammatory markers, CEA, and renal-function measurements.

View imaging, follow-up & lab data

Data cutoff: September 18, 2026.