Key result
A machine learning model using only non-clinical sociodemographic factors predicted uncontrolled hypertension (SBP > 160 mmHg) with an AUC of 74.49%.
Why the study?
Hypertension control remains a critical problem and most existing literature overlooks the role of sociodemographic factors, prompting the need to identify patients with poorly controlled hypertension using demographic and socioeconomic features.
Cohort (n=164,041)
No
Machine learning models using only sociodemographic and social determinants of health factors can predict poorly controlled hypertension, but require careful threshold tuning to mitigate inherent racial biases.
Answers are grounded in this paper and cite their sources.
Sociodemographic ML models for hypertension prediction require bias correction before deployment; leaves open prospective validation in diverse cohorts.
Hypertension control remains a critical problem and most of the existing literature views it from a clinical perspective, overlooking the role of sociodemographic factors. This study aims to identify patients with not well-controlled hypertension using readily available demographic and socioeconomic features and elucidate important predictive variables. In this retrospective cohort study, records from 1/1/2012 to 1/1/2020 at the Boston Medical Center were used. Patients with either a hypertension diagnosis or related records (≥ 130 mmHg systolic or ≥ 90 mmHg diastolic, n = 164,041) were selected. Models were developed to predict which patients had uncontrolled hypertension defined as systolic blood pressure (SBP) records exceeding 160 mmHg. The predictive model of high SBP reached an Area Under the Receiver Operating Characteristic Curve of 74.49% ± 0.23%. Age, race, Social Determinants of Health (SDoH), mental health, and cigarette use were predictive of high SBP. Being Black or having critical social needs led to higher probability of uncontrolled SBP. To mitigate model bias and elucidate differences in predictive variables, two separate models were trained for Black and White patients. Black patients face a 4.7 × higher False Positive Rate (FPR) and a 0.58 × lower False Negative Rate (FNR) compared to White patients. Decision threshold differentiation was implemented to equalize FNR. Race-specific models revealed different sets of social variables predicting high SBP, with Black patients being affected by structural barriers (e.g., food and transportation) and White patients by personal and demographic factors (e.g., marital status). Models using non-clinical factors can predict which patients exhibit poorly controlled hypertension. Racial and SDoH variables are significant predictors but lead to biased predictive models. Race-specific models are not sufficient to resolve such biases and require further decision threshold tuning. A host of structural socioeconomic factors are identified to be targeted to reduce disparities in hypertension control.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2025) conducted a cohort in Hypertension (n=164,041). Sociodemographic predictive model was evaluated on Area Under the Receiver Operating Characteristic Curve (AUC) for predicting SBP > 160 mmHg. A machine learning model using only non-clinical sociodemographic factors predicted uncontrolled hypertension (SBP > 160 mmHg) with an AUC of 74.49%.
Synapse has enriched 10 related papers. Consider them for comparative context: