Systematic review of approaches to use of neighborhood-level risk factors with clinical data to predict clinical risk and recommend interventions

•Advances in computing and data enables a big data approach to predict clinical risk.•Neighborhood-Level Risk Factors may serve to proxy social determinants of health.•Most frequently ML was used for dimension reduction; more recently to predict.•Utility of including NLRFs to predict clinical risk often showed now added value.•Future study design must directly test the additive predictive power of NLRFs.