RESUMO
The misdiagnosis of headache disorders is a serious issue, and AI-based headache model diagnoses with external validation are scarce. We previously developed an artificial intelligence (AI)-based headache diagnosis model using a database of 4000 patients' questionnaires in a headache-specializing clinic and herein performed external validation prospectively. The validation cohort of 59 headache patients was prospectively collected from August 2023 to February 2024 at our or collaborating multicenter institutions. The ground truth was specialists' diagnoses based on the initial questionnaire and at least a one-month headache diary after the initial consultation. The diagnostic performance of the AI model was evaluated. The mean age was 42.55 ± 12.74 years, and 51/59 (86.67%) of the patients were female. No missing values were reported. Of the 59 patients, 56 (89.83%) had migraines or medication-overuse headaches, and 3 (5.08%) had tension-type headaches. No one had trigeminal autonomic cephalalgias or other headaches. The models' overall accuracy and kappa for the ground truth were 94.92% and 0.65 (95%CI 0.21-1.00), respectively. The sensitivity, specificity, precision, and F values for migraines were 98.21%, 66.67%, 98.21%, and 98.21%, respectively. There was disagreement between the AI diagnosis and the ground truth by headache specialists in two patients. This is the first external validation of the AI headache diagnosis model. Further data collection and external validation are required to strengthen and improve its performance in real-world settings.
RESUMO
BACKGROUND: Introducing telemedicine in outpatient treatment may improve patient satisfaction and convenience. However, the optimal in-person visit interval for video-based telemedicine among patients with hypertension remains unreported in Japan. OBJECTIVE: We determined the optimal in-person visit interval for video-based telemedicine among patients with hypertension. METHODS: This was a cluster randomized controlled noninferiority trial. The target sites were 8 clinics in Japan that had a telemedicine system, and the target patients were individuals with essential hypertension. Among patients receiving video-based telemedicine, those who underwent in-person visits at 6-month intervals were included in the intervention group, and those who underwent in-person visits at 3-month intervals were included in the control group. The follow-up period of the participants was 6 months. The primary end point of the study was the change in systolic blood pressure, and the secondary end points were the rate of treatment continuation after 6 months, patient satisfaction, health economic evaluation, and safety evaluation. RESULTS: Overall, 64 patients were enrolled. Their mean age was 54.5 (SD 10.3) years, and 60.9% (39/64) of patients were male. For the primary end point, the odds ratio for the estimated difference in the change in systolic blood pressure between the 2 groups was 1.18 (90% CI -3.68 to 6.04). Notably, the criteria for noninferiority were met. Patient satisfaction was higher in the intervention group than in the control group. Furthermore, the indirect costs indicated that lost productivity was significantly lesser in the intervention group than in the control group. Moreover, the treatment continuation rate did not differ between the intervention and control groups, and there were no adverse events in either group. CONCLUSIONS: Blood pressure control status and safety did not differ between the intervention and control groups. In-person visits at 6-month intervals may cause a societal cost reduction and improve patient satisfaction during video-based telemedicine. TRIAL REGISTRATION: UMIN Clinical Trials Registry (UMIN-CTR) UMIN000040953; https://tinyurl.com/2p8devm9.
RESUMO
Background: Coronavirus disease 2019 (COVID-19) has spread rapidly worldwide. In Japan, the spread of COVID-19 was recognized and a state of emergency declared in April 2020. In response, public health interventions, such as discouraging people from leaving their homes unnecessarily, were enacted across the country. Under these circumstances, telemedicine has received a great deal of social attention, and it has become necessary to identify the perceptions of and attitudes toward telemedicine by clinicians and patients and to clarify the problems and advantages. Materials and Methods: Ten clinicians and 10 family members (if the patient was pediatric or elderly, a caregiver was included) were invited to participate in individual private interviews in 2020. All interviews were conducted from October to December 2020 using a semistructured interview guide. All transcripts were coded using thematic content analysis. Results: Four categories from clinicians and five from patients were identified as perceptions of and attitudes toward telemedicine. Both evaluated the usefulness and convenience of telemedicine in the same manner, but there was a large gap in the content under the safety and problem categories. Discussion: It is necessary to disseminate information about the communication techniques unique to telemedicine to doctors and to improve the "operation and introduction" and "communication environment and device settings" when starting or using telemedicine for all patients. Conclusions: The perceptions and attitudes identified in this study will be useful for establishing and developing a telemedicine system in Japan.
