RESUMEN
The aim of this study was to introduce the implemented MEDBIZ platform based on the internet of medical things (IoMT) supporting real-time digital health services for precision medicine. In addition, we demonstrated four empirical studies of the digital health ecosystem that could provide real-time healthcare services based on IoMT using real-world data from in-hospital and out-hospital patients. Implemented MEDBIZ platform based on the IoMT devices and big data to provide digital healthcare services to the enterprise and users. The big data platform is consisting of four main components: IoMT, core, analytics, and services. Among the implemented MEDBIZ platform, we performed four clinical trials that designed monitoring services related to chronic obstructive pulmonary disease, metabolic syndrome, arrhythmia, and diabetes mellitus. Of the four empirical studies on monitoring services, two had been completed and the rest were still in progress. In the metabolic syndrome monitoring service, two studies were reported. One was reported that intervention components, especially wearable devices and mobile apps, made systolic blood pressure, diastolic blood pressure, waist circumference, and glycosylated hemoglobin decrease after 6 months. Another one was presented that increasing high-density lipoprotein cholesterol and triglyceride levels were prevented in participants with the pre-metabolic syndrome. Also, self-care using healthcare devices might help prevent and manage metabolic syndrome. In the arrhythmia monitoring service, during the real-time monitoring of vital signs remotely at the monitoring center, 318 (15.9%) general hikers found abnormal signals, and 296 (93.1%) people were recommended for treatment. We demonstrated the implemented MEDBIZ platform based on IoMT supporting digital healthcare services by acquiring real-world data for getting real-world evidence. And then through this platform, we were developing software as a medical device, digital therapeutics, and digital healthcare services, and contributing to the development of the digital health ecosystem.
RESUMEN
OBJECTIVES: Otitis media is a common infection worldwide. Owing to the limited number of ear specialists and rapid development of telemedicine, several trials have been conducted to develop novel diagnostic strategies to improve the diagnostic accuracy and screening of patients with otologic diseases based on abnormal otoscopic findings. Although these strategies have demonstrated high diagnostic accuracy for the tympanic membrane (TM), the insufficient explainability of these techniques limits their deployment in clinical practice. METHODS: We used a deep convolutional neural network (CNN) model based on the segmentation of a normal TM into five substructures (malleus, umbo, cone of light, pars flaccida, and annulus) to identify abnormalities in otoscopic ear images. The mask R-CNN algorithm learned the labeled images. Subsequently, we evaluated the diagnostic performance of combinations of the five substructures using a three-layer fully connected neural network to determine whether ear disease was present. RESULTS: We obtained the receiver operating characteristic (ROC) curve of the optimal conditions for the presence or absence of eardrum diseases according to each substructure separately or combinations of substructures. The highest area under the curve (0.911) was found for a combination of the malleus, cone of light, and umbo, compared with the corresponding areas under the curve of 0.737-0.873 for each substructure. Thus, an algorithm using these five important normal anatomical structures could prove to be explainable and effective in screening abnormal TMs. CONCLUSION: This automated algorithm can improve diagnostic accuracy by discriminating between normal and abnormal TMs and can facilitate appropriate and timely referral consultations to improve patients' quality of life in the context of primary care.
