Social Determinants of Health Data Improve the Prediction of Cardiac Outcomes in Females with Breast Cancer

Abstract

Cardiovascular disease is the leading cause of mortality among breast cancer (BC) patients aged 50 and above. Machine Learning (ML) models are increasingly utilized as prediction tools, and recent evidence suggests that incorporating social determinants of health (SDOH) data can enhance its performance. This study included females ≥ 18 years diagnosed with BC at any stage. The outcomes were the diagnosis and time-to-event of major adverse cardiovascular events (MACEs) within two years following a cancer diagnosis. Covariates encompassed demographics, risk factors, individual and neighborhood-level SDOH, tumor characteristics, and BC treatment. Race-specific and race-agnostic Extreme Gradient Boosting ML models with and without SDOH data were developed and compared based on their C-index. Among 4309 patients, 11.4% experienced a 2-year MACE. The race-agnostic models exhibited a C-index of 0.78 (95% CI 0.76–0.79) and 0.81 (95% CI 0.80–0.82) without and with SDOH data, respectively. In non-Hispanic Black women (NHB; n = 765), models without and with SDOH data achieved a C-index of 0.74 (95% CI 0.72–0.76) and 0.75 (95% CI 0.73–0.78), respectively. Among non-Hispanic White women (n = 3321), models without and with SDOH data yielded a C-index of 0.79 (95% CI 0.77–0.80) and 0.79 (95% CI 0.77–0.80), respectively. In summary, including SDOH data improves the predictive performance of ML models in forecasting 2-year MACE among BC females, particularly within NHB.

Allostatic Load/Chronic Stress and Cardiovascular Outcomes in Patients Diagnosed With Breast, Lung, or Colorectal Cancer

“… 19 , 20 While CVD development is multifactorial, recent evidence suggests that adverse social determinants of health are an important factor in this equation and are linked to a heightened risk of CVD. 21 , 22 , 34 Adverse social determinants of health are also believed to increase chronic stress. 35 Our results support that the association between AL and MACE is also valid for patients diagnosed with BC, LC, or CRC, which are, together with prostate cancer, the top 4 newly diagnosed cancers in the United States.…”

“…The study setting was the UH Seidman Cancer Center (Northeast Ohio, US), a tertiary care center that serves urban, suburban, and rural areas, comprising an integrated network of 23 hospitals, >50 health centers and outpatients facilities, and >200 physicians’ offices in 16 counties throughout the region. 21 , 22 Data were obtained from the UH repository, which consists of an open‐source, web‐based cancer data management system that integrates disparate sources of data. 19 , 21 , 22 , 23 , 24 , 25 , 26 , 27 The information obtained was complemented with electronic health record information captured via the Electronic Medical Record Search Engine.…”

“… 21 , 22 Data were obtained from the UH repository, which consists of an open‐source, web‐based cancer data management system that integrates disparate sources of data. 19 , 21 , 22 , 23 , 24 , 25 , 26 , 27 The information obtained was complemented with electronic health record information captured via the Electronic Medical Record Search Engine. 28 , 29 A waiver of informed consent was granted due to the anonymous nature of the data set.…”

“…The primary end point was 2‐year MACE (a composite of heart failure [HF], acute coronary syndrome [ACS], atrial fibrillation [A‐fib], and ischemic stroke [IS]) following the cancer diagnosis. 19 , 22 …”

Comparison of predicting cardiovascular disease hospitalization using individual, ZIP code-derived, and machine learning model-predicted educational attainment in New York City

“…Prior studies evaluating the impact of including SDOH into predictive model performance have resulted in mixed results [5][6][7][8][9][10][11]. Hammond et al [5] demonstrated that adjusting for SDOH improved the accuracy of cardiovascular hospitalization and mortality regression prediction models.…”