Search

Epidermal growth factor receptor (EGFR) inhibitors have benefitted cancer patients worldwide, but resistance inevitably develops over time, resulting in treatment failures. An accurate prediction model for acquired resistance (AR) to EGFR inhibitors is critical for early diagnosis and according intervention, but is not yet available due to personal variations and the complex mechanisms of AR. Here, we have developed a novel pipeline to build a meta-analysis-based, multivariate model for personalized pathways in AR to EGFR inhibitors, using sophisticated machine learning algorithms. Surprisingly, the model achieved excellent predictive performance, with a cross-study validation area under curve (AUC) of over 0.9, and generalization performance on independent cohorts of samples, with a perfect AUC score of 1. Furthermore, the model showed excellent transferability across different cancer cell lines and EGFR inhibitors, including gefitinib, erlotinib, afatinib, and cetuximab. In conclusion, our model achieved high predictive accuracy through robust cross study validation, and enabled individualized prediction on newly introduced data. We also discovered common pathway alteration signatures for AR to EGFR inhibitors, which can provide directions for other follow-up studies. [ABSTRACT FROM AUTHOR]

Background/aims: We aimed to evaluate site-specific cancer risk in diabetic patients and to investigate causal and temporal relationships by analyzing organ-specific cancer risk according to the duration of diabetes., Methods: Using a database provided by the Korean National Health Insurance Service, we conducted a retrospective, population-based cohort study of adults aged ≥ 30 years from January 2005 to December 2013. To verify the possibility of detection bias or reverse causation, we compared hazard ratios (HRs) for each cancer according to the following duration of diabetes: less than 6 months, 6 months to 3 years, and more than 3 years., Results: The incidence of overall cancer per 1,000 person-years was higher in patients with diabetes than in those without diabetes (20.36 vs. 10.83). The overall cancer risk according to the duration of diabetes was the highest within the first 6 months after diagnosis (HR, 2.03; 95% confidence interval [CI], 1.99 to 2.07), and the HR decreased with the duration of diabetes, ranging from 1.19 (95% CI, 1.18 to 1.21) between 6 months and 3 years to 1.12 (95% CI, 1.11 to 1.13) after 3 years. Both overall cancer risk and HR remained significantly higher in patients with diabetes than in those without diabetes. The risk for prostate cancer was higher in men with diabetes than in those without diabetes (HR, 1.12; 95% CI, 1.10 to 1.14). In women, the risk for endometrial cancer was significantly higher in patients with diabetes than in those without diabetes throughout the duration of diabetes., Conclusion: The risk for stomach, colorectum, liver, pancreas, and kidney cancer appeared to be higher in patients with diabetes than in those without diabetes regardless of the sex or duration of diabetes.