Savitz, Samuel

Background: Telemedicine use has expanded rapidly across ambulatory care. Satisfaction with telemedicine services has been associated with social determinants of health (SDOH) such as socioeconomic status, ethnicity, and employment status. However, little is known about gender-specific patterns in patient experience. This study examined how demographic and SDOH are associated with telehealth satisfaction among women. Methods: A cross-sectional analysis was conducted using data from female patients who completed standardized post-telehealth surveys within the Mayo Clinic Health Care System between March 2020 and December 15, 2023. Logistic regression was used to evaluate the association between patient satisfaction and the following demographics and SDOH: age, race, ethnicity, marital status, Elixhauser score, mental health diagnosis, stress risk, financial risk, transportation risk, food insecurity risk, primary language, and physical activity risk. Results: Among 51,512 female patients, higher age was associated with less satisfaction with “ease of scheduling appointment” and “ease of contacting clinic,” but was associated with significantly higher satisfaction for other measures, including “care practitioners’ efforts to include” and “recommending healthcare office.” A high Elixhauser score was associated with lower satisfaction with “how well the audio and video connections worked.” Conclusion and Action Steps: A higher Elixhauser score and older age emerged as key factors associated with telehealth satisfaction among women. Targeted efforts to support patients with complex health needs and those requiring enhanced care coordination may improve satisfaction and equity in ambulatory telemedicine.

ABSTRACT Introduction Community health workers (CHWs) help patients navigate community resources. CHW programs can improve health outcomes and reduce healthcare utilization, but identifying eligible patients is challenging. We developed an electronic health record (EHR)‐based algorithm trained to predict referrals to a CHW program. Our objective was to evaluate whether an algorithm trained on historical referrals identifies a subgroup of patients that differs from the subgroup identified through questionnaire‐based health‐related social needs (HRSN) screening alone. Methods This analysis used data from Mayo Clinic primary care patients in Southeast Minnesota. We developed a gradient boosted time‐to‐event model that incorporated demographics, diagnoses, HRSN questionnaire responses, and HRSNs derived from clinical notes using natural language processing. We compared the characteristics of algorithm‐identified patients with those identified through questionnaires and assessed the variable importance of model features. Results The algorithm had AUC: 0.87 in the training and 0.92 in the hold out set. Patients flagged by the algorithm tended to use interpreter services more commonly (12.6% vs. 1.3%), have a non‐English preferred language (14.1% vs. 2.3%), and have more instances of health literacy documented (5.36 vs. 1.29) compared to patients identified by the HRSN questionnaire. Only 47.0% of patients flagged by the algorithm had responded to the HRSN questionnaire within 2 years. Variable importance was highest for health literacy and financial strain from unstructured notes. Conclusions The algorithm is a chart‐review prioritization tool for referral to the CHW program for patients that may overcome challenges to identifying patients with HRSNs, especially when questionnaire data is incomplete.