Methods for Inclusive Underwriting of Breast Cancer Risk with Machine Learning and Innovative Algorithms.

INTRODUCTION: -Due to early detection and improved therapies, the prevalence of long-term breast cancer survivors is increasing. This has increased the need for more inclusive underwriting in individuals with a history of breast cancer. Herein, we developed a method using algorithm aiming facilitating the underwriting of multiple parameters in breast cancer survivors. METHODS: -Variables and data were extracted from the SEER database and analyzed using 4 different machine learning based algorithms (Logistic Regression, GA2M, Random Forest, and XGBoost) that were compared with Kaplan Meier survival estimates. The performances of these algorithms have been compared with multiple metrics (Log Loss, AUC, and SMR). In situ (non-invasive) and metastatic breast cancer were excluded from this analysis. RESULTS: -Parameters included the pathological subtype, pTNM staging (T: tumor size, N; number of nodes; M presence or absence of metastases), Scarff-Bloom-Richardson grading, the expression of estrogen and progesterone hormone receptors were selected to predict the individual outcome at any time point from diagnosis. While all models had identical performance in terms of statistical metrics (AUC, Log Loss, and SMR), the logistic regression was the one and only model that respects all business constraints and was intelligible for medical and underwriting users. CONCLUSION: -This study provides insight to develop algorithms to set underwriter-friendly calculators for more accurate risk estimations that can be used to rationalize insurance pricing for breast cancer survivors. This study supports the development of a more inclusive underwriting based on models that can encompass the heterogeneity of several malignancies such as breast cancer.

The relationship between mortality and daily number of steps in type 2 diabetes.

BACKGROUND: Physical activity (PA) is an established modifiable factor for the prevention of cardiovascular disease. Our objective was to assess the association of PA with mortality rates in a national sample of patients with diabetes. METHODS: We analyzed a nationally representative sample from The National Health and Nutrition Examination Survey (NHANES, periods 2003-2004 and 2005-2006) that used PA Monitors. Individuals were matched for BMI, number of steps/per day and age. Three groups were created: subjects with less than 5000/steps per day (low), 5000-7500/steps per day (moderate) and more than 7500/steps per day (high levels of physical activity). All-cause mortality was ascertained through December 2015. RESULTS: A sample of 3072 individuals (1018 with diabetes) was analyzed. Patients with diabetes had 30% increased risk of mortality of all causes (RR: 1.298, 95% CI [1.162-1.451], P<0.001), higher levels of PA (>7500 steps/day) provided similar relative risk for subjects with diabetes compared to their controls (RR:1.256 [95% CI 0.910-1.732]). In a Poisson model adjusted for sex, history of previous cardiovascular event or cancer, ethnicity, Hb1ac, SBP, and total cholesterol to HDL ratio, patients with diabetes and moderate or high PA had an associated 44% to 80% lower risk of all-cause mortality compared to those with low PA. CONCLUSIONS: The subgroup of patients with diabetes and high PA had no excess of mortality compared to the general population. PA can reduce the gap for all-cause mortality, used as an index of cardiovascular fitness and a clinical tool for the assessment of mortality risk.