Background: Although the COVID-19 pandemic has accelerated the adoption of telemedicine and virtual consultations worldwide, complex factors that may affect the use of virtual clinics are still unclear. Objective: This study aims to identify factors associated with the utilization of virtual clinics in the experience of virtual clinic service implementation in Taiwan. Methods: We retrospectively analyzed a total of 187,742 outpatient visits (176,815, 94.2%, in-person visits and 10,927, 5.8%, virtual visits) completed at a large general hospital in Taipei City from May 19 to July 31, 2021, after rapid implementation of virtual outpatient clinic visits due to the COVID-19 pandemic. Data of patients’ demographic characteristics, disease type, physicians’ features, and specialties/departments were collected, and physicians’ opinions regarding virtual clinics were surveyed and evaluated using a 5-point Likert scale. Multilevel analysis was conducted to determine the factors associated with the utilization of virtual clinics. Results: Patient-/visit-, physician-, and department-level factors accounted for 67.5%, 11.1%, and 21.4% of the total variance in the utilization of virtual clinics, respectively. Female sex (odds ratio [OR] 1.27, 95% CI 1.22-1.33, P<.001); residing at a greater distance away from the hospital (OR 2.36, 95% CI 2.15-2.58 if distance>50 km, P<.001; OR 3.95, 95% CI 3.11-5.02 if extensive travel required, P<.001); reimbursement by the National Health Insurance (NHI; OR 7.29, 95% CI 5.71-9.30, P<.001); seeking care for a major chronic disease (OR 1.33, 95% CI 1.24-1.42, P<.001); the physician’s positive attitude toward virtual clinics (OR 1.50, 95% CI 1.16-1.93, P=.002); and visits within certain departments, including the heart center, psychiatry, and internal medicine (OR 2.55, 95% CI 1.46-4.46, P=.004), were positively associated with the utilization of virtual clinics. The patient’s age, the physician’s age, and the physician’s sex were not associated with the utilization of virtual clinics in our study. Conclusions: Our results show that in addition to previously demonstrated patient-level factors that may influence telemedicine use, including the patient’s sex and distance from the hospital, factors at the visit level (insurance type, disease type), physician level (physician’s attitude toward virtual clinics), and department level also contribute to the utilization of virtual clinics. Although there was a more than 300-fold increase in the number of virtual visits during the pandemic compared with the prepandemic period, the majority (176,815/187,742, 94.2%) of the outpatient visits were still in-person visits during the study period. Therefore, it is of great importance to understand the factors impacting the utilization of virtual clinics to accelerate the implementation of telemedicine. The findings of our study may help direct policymaking for expanding the use of virtual clinics, especially in countries struggling with the development and promotion of telemedicine virtual clinic services.

Early detection of aortic dilatation is clinically important for preventing progression to serious aortic disease and enabling timely intervention. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired contrast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensitivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based workflow enables highly sensitive automated aortic quantification in both contrast-enhanced and non-contrast CT scans, supporting broader clinical applicability across different imaging conditions.

Artificial intelligence (AI) advancements have enabled automated aortic quantification in computed tomography (CT) imaging. We aimed to develop an AI method for quantifying the aorta in both contrast-enhanced and non-contrast CT scans, assisting early detection of aortic dilation. A total of 190 patient cases were analyzed, each having paired con-trast-enhanced and non-contrast CT scans acquired in the same session, resulting in 380 scans. Our approach, based on open-source tools, demonstrated strong agreement with manual annotations, particularly in the ascending aorta. For contrast-enhanced CT, the AI achieved a correlation coefficient of 0.987 and intraclass correlation coefficient (ICC) of 0.986; for non-contrast CT, both were 0.945. Compared with clinical records, the sensi-tivity of AI detection was 97% for contrast-enhanced CT and 94% for non-contrast CT. This AI-based approach offers highly sensitive, automated aortic quantification across contrast conditions, supporting physicians in early identification of aortic abnormalities.