RESUMO
Objective: This study examined the proxy use of patient portals for children in a large Federally Qualified Health Centers (FQHC) network in Texas. Methods: We used de-identified individual-level data of patients, 0-18 years, who had 1+ visits between December 2018 and November 2020. Logistic regression was used to examine patient-, clinic-, and geographic-level factors associated with portal usage by an assumed proxy (i.e. parent or guardian). Results: The proxy portal usage rate increased from 28% in the pre-pandemic months (November 2018-February 2020) to 34% in the pandemic months (March-Nov 2020). Compared to patients 0-5 years, patients aged 6 to 18 years had lower odds of portal usage (6-10 OR: 0.77, p < 0.001; 11-14 OR: 0.62, p < 0.001; 15-18 OR: 0.51, p < 0.001). Minoritized groups had significantly lower odds of portal usage when compared to their non-Hispanic White counterparts (non-Hispanic Black OR: 0.78, p < 0.001; Hispanic OR 0.63, p < 0.001; Asian OR: 0.69, p < 0.001). Having one chronic condition was associated with portal usage (OR: 1.57, p < 0.001); however, there were no significant differences in portal usage between those with none or multiple chronic conditions. Portal usage also varied by service lines, with obstetrics and gynecology (OR: 1.84, p < 0.001) and behavioral health (OR 1.82, p < 0.001) having the highest odds of usage when compared to pediatrics. Having a telemedicine visit was the strongest predictor of portal usage (OR: 2.30, p < 0.001), while residence in zip codes with poor broadband internet access was associated with lower odds of portal usage (OR: 0.97, p < 0.001). Conclusion: While others have reported portal usage rates as high as 64% in pediatric settings, our analysis suggests proxy portal usage rates of 30% in pediatric FQHC settings, with race/ethnicity, age group, and chronic disease status being significant drivers of portal non-usage. These findings highlight the need for appropriate and responsive health information technology approaches for vulnerable populations receiving care in low-resource settings.
RESUMO
Social isolation is a well-documented contributor to poor mental and physical health, and interventions promoting social connectedness have been associated with various health benefits. This study examined predictors of participation in a telephone-based social connectedness intervention for socially isolated older adults. Data were obtained from a social-connectedness intervention that paired college students with Houston-area, community-dwelling adults aged 65 years and older and enrolled in Medicare Advantage plans. We combined machine learning and regression techniques to identify significant predictors of program participation. The following machine-learning methods were implemented: (1) k-nearest neighbors, (2) decision tree and ensembles of decision trees, (3) gradient-boosted decision tree, and (4) random forest. The primary outcome was a binary flag indicating participation in the telephone-based social-connectedness intervention. The most predictive variables in the ML models, with scores corresponding to the 90th percentile or greater, were included in the regression analysis. The predictive ability of each model showed high discriminative power, with test accuracies greater than 95%. Our findings suggest that telephone-based social-connectedness interventions appeal to individuals with disabilities, depression, arthritis, and higher risk scores. scores. Recognizing features that predict participation in social-connectedness programs is the first step to increasing reach and fostering patient engagement.