Favorable Neighborhood Walkability is Associated With Lower Burden of Cardiovascular Risk Factors Among Patients Within an Integrated Health System: The Houston Methodist Learning Health System Outpatient Registry.

This is the first study to investigate the relationship between neighborhood walkability and cardiovascular (CV) risk factors in the United States using a large population-based database. Cross-sectional study using data from 1.1 million patients over the age of 18 in the Houston Methodist Learning Health System Outpatient Registry (2016-2022). Using the 2019 WalkScore, patients were assigned to one of the 4 neighborhood walkability categories. The burden of CV risk factors (hypertension, diabetes, obesity, dyslipidemia, and smoking) was defined as poor, average, or optimal (>3, 1-2, 0 risk factors, respectively). We included 887,654 patients, of which 86% resided in the two least walkable neighborhoods. The prevalence of CV risk factors was significantly lower among participants in the most walkable neighborhoods irrespective of ASCVD status. After adjusting for age, sex, race/ethnicity, and socioeconomic factors, we found that adults living in the most walkable neighborhoods were more likely to have optimal CV risk profile than those in the least walkable ones (RRR 2.77, 95% CI 2.64-2.91). We observed an inverse association between neighborhood walkability and the burden of CV risk factors. These findings support multilevel health system stakeholder engagements and investments in walkable neighborhoods as a viable tool for mitigating the growing burden of modifiable CV risk factors.

Subphenotyping depression using machine learning and electronic health records.

OBJECTIVE: To identify depression subphenotypes from Electronic Health Records (EHRs) using machine learning methods, and analyze their characteristics with respect to patient demographics, comorbidities, and medications. MATERIALS AND METHODS: Using EHRs from the INSIGHT Clinical Research Network (CRN) database, multiple machine learning (ML) algorithms were applied to analyze 11 275 patients with depression to discern depression subphenotypes with distinct characteristics. RESULTS: Using the computational approaches, we derived three depression subphenotypes: Phenotype_A (n = 2791; 31.35%) included patients who were the oldest (mean (SD) age, 72.55 (14.93) years), had the most comorbidities, and took the most medications. The most common comorbidities in this cluster of patients were hyperlipidemia, hypertension, and diabetes. Phenotype_B (mean (SD) age, 68.44 (19.09) years) was the largest cluster (n = 4687; 52.65%), and included patients suffering from moderate loss of body function. Asthma, fibromyalgia, and Chronic Pain and Fatigue (CPF) were common comorbidities in this subphenotype. Phenotype_C (n = 1452; 16.31%) included patients who were younger (mean (SD) age, 63.47 (18.81) years), had the fewest comorbidities, and took fewer medications. Anxiety and tobacco use were common comorbidities in this subphenotype. CONCLUSION: Computationally deriving depression subtypes can provide meaningful insights and improve understanding of depression as a heterogeneous disorder. Further investigation is needed to assess the utility of these derived phenotypes to inform clinical trial design and interpretation in routine patient care.