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

A Systematic Review of Artificial Intelligence Models for Time-to-Event Outcome Applied in Cardiovascular Disease Risk Prediction

Artificial intelligence (AI) based predictive models for early detection of cardiovascular disease (CVD) risk are increasingly being utilised. However, AI based risk prediction models that account for right-censored data have been overlooked. This systematic review (PROSPERO protocol CRD42023492655) includes 33 studies that utilised machine learning (ML) and deep learning (DL) models for survival outcome in CVD prediction. We provided details on the employed ML and DL models, eXplainable AI (XAI) techniques, and type of included variables, with a focus on social determinants of health (SDoH) and gender-stratification. Approximately half of the studies were published in 2023 with the majority from the United States. Random Survival Forest (RSF), Survival Gradient Boosting models, and Penalised Cox models were the most frequently employed ML models. DeepSurv was the most frequently employed DL model. DL models were better at predicting CVD outcomes than ML models. Permutation-based feature importance and Shapley values were the most utilised XAI methods for explaining AI models. Moreover, only one in five studies performed gender-stratification analysis and very few incorporate the wide range of SDoH factors in their prediction model. In conclusion, the evidence indicates that RSF and DeepSurv models are currently the optimal models for predicting CVD outcomes. This study also highlights the better predictive ability of DL survival models, compared to ML models. Future research should ensure the appropriate interpretation of AI models, accounting for SDoH, and gender stratification, as gender plays a significant role in CVD occurrence.

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

BACKGROUND

Cardiovascular disease and cancer share a common risk factor: chronic stress/allostatic load (AL). A 1-point increase in AL is linked to up to a 30% higher risk of major cardiac events (MACE) in patients with prostate cancer. However, AL's role in MACE in breast cancer, lung cancer, or colorectal cancer remains unknown.

METHODS AND RESULTS

Patients ≥18 years of age diagnosed with the mentioned 3 cancers of interest (2010-2019) and followed up at a large, hybrid academic-community practice were included in this retrospective cohort study. AL was modeled as an ordinal measure (0-11). Adjusted Fine-Gray competing risks regressions estimated the impact of AL precancer diagnosis on 2-year MACE (a composite of heart failure, ischemic stroke, acute coronary syndrome, and atrial fibrillation). The effect of AL changes over time on MACE was calculated via piecewise Cox regression (before, and 2 months, 6 months, and 1 year after cancer diagnosis). Among 16 467 patients, 50.5% had breast cancer, 27.9% had lung cancer, and 21.4% had colorectal cancer. A 1-point elevation in AL before breast cancer diagnosis corresponded to a 10% heightened associated risk of MACE (adjusted hazard ratio, 1.10 [95% CI, 1.06-1.13]). Similar findings were noted in lung cancer (adjusted hazard ratio, 1.16 [95% CI, 1.12-1.20]) and colorectal cancer (adjusted hazard ratio, 1.13 [95% CI, 1.08-1.19]). When considering AL as a time-varying exposure, the peak associated MACE risk occurred with a 1-point AL rise between 6 and 12 months post- breast cancer, lung cancer, and colorectal cancer diagnosis.

CONCLUSIONS

AL warrants investigation as a potential marker in these patients to identify those at elevated cardiovascular risk and intervene accordingly.

Reducing racial and ethnic disparities in cardiovascular outcomes among cancer survivors

PURPOSE OF REVIEW

Analyze current evidence on racial/ethnic disparities in cardiovascular outcomes among cancer survivors, identifying factors and proposing measures to address health inequities.

RECENT FINDINGS

Existing literature indicates that the Black population experiences worse cardiovascular outcomes following the diagnosis of both initial primary cancer and second primary cancer, with a notably higher prevalence of cardio-toxic events, particularly among breast cancer survivors. Contributing socioeconomic factors to these disparities include unfavorable social determinants of health, inadequate insurance coverage, and structural racism within the healthcare system. Additionally, proinflammatory epigenetic modification is hypothesized to be a contributing genetic variation factor. Addressing these disparities requires a multiperspective approach, encompassing efforts to address racial disparities and social determinants of health within the healthcare system, refine healthcare policies and access, and integrate historically stigmatized racial groups into clinical research. Racial and ethnic disparities persist in cardiovascular outcomes among cancer survivors, driven by multifactorial causes, predominantly associated with social determinants of health. Addressing these healthcare inequities is imperative, and timely efforts must be implemented to narrow the existing gap effectively.

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

BACKGROUND

Area-level social determinants of health (SDOH) based on patients' ZIP codes or census tracts have been commonly used in research instead of individual SDOHs. To our knowledge, whether machine learning (ML) could be used to derive individual SDOH measures, specifically individual educational attainment, is unknown.

METHODS

This is a retrospective study using data from the Mount Sinai BioMe Biobank. We included participants that completed a validated questionnaire on educational attainment and had home addresses in New York City. ZIP code-level education was derived from the American Community Survey matched for the participant's gender and race/ethnicity. We tested several algorithms to predict individual educational attainment from routinely collected clinical and demographic data. To evaluate how using different measures of educational attainment will impact model performance, we developed three distinct models for predicting cardiovascular (CVD) hospitalization. Educational attainment was imputed into models as either survey-derived, ZIP code-derived, or ML-predicted educational attainment.

RESULTS

A total of 20,805 participants met inclusion criteria. Concordance between survey and ZIP code-derived education was 47%, while the concordance between survey and ML model-predicted education was 67%. A total of 13,715 patients from the cohort were included into our CVD hospitalization prediction models, of which 1,538 (11.2%) had a history of CVD hospitalization. The AUROC of the model predicting CVD hospitalization using survey-derived education was significantly higher than the model using ZIP code-level education (0.77 versus 0.72; p < 0.001) and the model using ML model-predicted education (0.77 versus 0.75; p < 0.001). The AUROC for the model using ML model-predicted education was also significantly higher than that using ZIP code-level education (p = 0.003).

CONCLUSION

The concordance of survey and ZIP code-level educational attainment in NYC was low. As expected, the model utilizing survey-derived education achieved the highest performance. The model incorporating our ML model-predicted education outperformed the model relying on ZIP code-derived education. Implementing ML techniques can improve the accuracy of SDOH data and consequently increase the predictive performance of outcome models.