Background: Racial and socioeconomic disparities in healthcare access are well-documented. Minority and rural populations face barriers and often have limited access to healthcare services and facilities. Digital health solutions can help bridge these gaps. Previous studies examining digital health usage patterns have reported mixed findings, with some showing lower adoption among minority/underserved groups and others finding no significant differences compared to the general population. Hypothesis: Minority and rural patients would participate in the digital health intervention at similar rates as non-minority, affluent patients when provided with equal access to cardiologist and device training. Aims: To analyze the variance in usage of digital health products between underserved and general patient populations. Methods: The 5,000-patient clinic serves a population of underserved minority and affluent non-minority patients. All patients were offered cellular-enabled blood pressure cuffs and weight scales that transmitted data automatically to a physician portal as part of routine care. Patients consented to have their data used for research and were instructed to use these devices > 4 times per week for six months, with periodic reminders from clinic staff. Patient participation was tracked, and digital records were analyzed. Results: Demographic information of enrolled patients (n=18) is reported (Figure 1). There was an overall 90% retention rate throughout the six-month study period, including 90% retention from African American patients, 87.5% from indigent patients, and 100% from both rural and inner-city residents. Conclusion: With a modest sample size, this data suggested that minority and rural populations may participate in digital health and remote patient monitoring interventions at the same rate as the general population of patients. This study supports the growing potential of digital health to improve healthcare access for minority and rural communities.

Introduction: We tested the first novel software application to accurately measure QTc using a machine learning algorithm from a mobile ECG and recommend patient-specific antiarrhythmic drug (AAD) dosing. The software was developed to address disparities in AAD hospitalizations that disproportionately affect minority patients. We evaluated the usability of the software interface using the validated Post-Study System Usability Questionnaire (PSSUQ) and mobile Health App Usability Questionnaire (MAUQ). Methods: Ten medical providers, 16 clinic staff, and 16 patients tested the novel software interface for remote titration of Sotalol and Dofetilide medications, followed by the validated PSSUQ and MAUQ surveys. An observer also evaluated each step of the software for completion and noted any challenges. Results: Providers rated the software interface highly, with an overall mean PSSUQ of 6.9 ± 0.2 and MAUQ of 6.8 ± 0.2, and 100% strongly agree on information quality (PSSUQ questions 7-12). Clinic staff and patients provided the highest ratings for system usefulness, with an overall PSSUQ mean of 6.4 ± 1.2 and MAUQ mean of 6.0 ± 1.2, ease of app use and user satisfaction, mean of 6.3 ± 1.1 and 5.9 ± 1.3 respectively. Eighty percent of users found the system easy to use and were satisfied, with 76% rating the app as an acceptable way to receive healthcare services and felt comfortable communicating with their providers using the app. Conclusion: The novel automated software application, designed to improve access to antiarrhythmic drugs and reduce healthcare disparities, received high usability ratings, indicating feasibility for remote administration of antiarrhythmic drugs.

Background: Atrial fibrillation (AF) is the most common heart rhythm disorder and often requires inpatient monitoring for antiarrhythmic drug (AAD) initiation, specifically for dofetilide and sotalol. No system currently offers safe at-home AAD initiation, which is needed to expand AAD access for low-risk or underserved patients and reduce mortality. Objective: Assess accuracy of AAD dosing using a computer-guided decision tree algorithm compared to physician dosing decisions. Methods: Patients in an all-comer population were instructed to take a mobile ECG (mECG; KardiaMobile 6L, AliveCor). A proprietary ML algorithm (SafeBeat Rx) interpreted QTc for each mECG and recommended a starting dose for each AAD (dofetilide and sotalol), per drug labeling. For sotalol, an initial dose of 80 mg was recommended if QTc ≤ 450 ms and HR > 60 bpm; if baseline ECG criteria were unmet, 0 mg was recommended. For dofetilide, initial 500 mcg dose was recommended if QTc ≤ 440 ms. For software simulation, creatinine clearance was assumed to be normal (>60 mL/min) for all patients. Recommendations were adjusted based on a higher QTc threshold >550 ms if the patient’s baseline ECG showed wide QRS (e.g. artificially paced, bundle branch block). The software recommendations were compared to the gold standard: dosing selected by 2 physicians manually measuring baseline mECG QTc and selecting a theoretical starting dose accordingly, independent from software-generated results. Results: 95 patients were enrolled (40% healthy, 30% outpatients, 30% inpatients). The algorithm was highly accurate in predicting starting dose; agreement with physicians was 94.68% for sotalol and 95.74% for dofetilide. Median heart rate was 84.8 bpm (SD = 17.5) and median QTc interval was 475.5 ms (SD = 106.4). Physicians chose the manufacturer-recommended full starting dose for 85% of patients for sotalol and 86% for dofetilide, compared with 86% for sotalol and 86% for dofetilide recommended by the software. Conclusion: The decision tree model had 95% agreement with physician dose recommendations, demonstrating that the algorithm can accurately guide patient-specific AAD dosing, which helps guide remote physician-directed initiation of AAD, ultimately expanding drug access for AF patients.