Pulse.

a daily field guide to health research that matters

◆ Console

‹ Wed · 10 Jun 2026
Underserved or high-risk populations

Age-stratified risk profiles for emergency colorectal cancer resection: A machine-learning analysis

Young and older adults need different strategies to prevent emergency colorectal cancer surgery—insurance access matters most for younger patients.

This large US national database analysis (n=510,135) applies CART machine learning to reveal fundamentally different mechanisms driving emergency CRC surgery across age groups — access barriers in younger patients vs clinical complexity in older adults. The findings argue against one-size-fits-all ECCR reduction strategies and support age-tailored interventions addressing insurance coverage gaps.

What the study was

Study design
Retrospective cohort (multivariable logistic regression + CART machine learning)
Population
Adults with colorectal cancer resection admissions in the US National Inpatient Sample (NIS), 2018-2022
Sample size
510135
Category
Public Health
Maturity
Validated
Journal
Journal of Gastrointestinal Surgery

Why it surfaced

Large national cohort with health equity implications. ML-derived age-specific risk phenotypes for emergency CRC surgery provide actionable targets (insurance access in younger adults) and signal that CRC prevention programs should stratify by age and socioeconomic factors, not just clinical risk.

A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.