George Vlachogiannis, Managing Editor of Cancer Control at Sage, shared on LinkedIn about a recent paper by Bingya Ma et al. published on Sage Journals:
“Racial Disparities in Comorbidity Patterns of Early-Onset Liver Cancer: A Machine Learning Analysis
A matched case–control study of early-onset liver cancer patients (18–49) used race/ethnicity-specific machine-learning models on electronic health record data from the University of California Health Data Warehouse to map comorbidities and predict liver cancer risk.
Asian/Pacific Islander (API) risk was dominated by HBV, Hispanic risk clustered around HCV and metabolic disorders, while White patients showed a more diffuse profile (including mental health, asthma/hypothyroidism, cholangitis) – all of which provide actionable patterns for potential precision prevention. Models for API and Hispanic groups performed strongly (AUC ~0.90–0.92), highlighting the value of race/ethnicity-tailored screening and targeted interventions (e.g., HBV vaccination/screening in API communities; expanded HCV/metabolic care for Hispanics).
Study out in Cancer Control.
Title: Racial Disparities in Comorbidity Patterns of Early-Onset Liver Cancer: A Machine Learning Analysis
Authors: Bingya Ma, Kai Zheng, Fa-Chyi Lee, and Yunxia Lu
More posts featuring George Vlachogiannis.