BackgroundAs patient communication, engagement, personal health data tracking, and up-to-date information became more efficient through mobile health (mHealth), cardiovascular diseases (CVD) and other diseases that require behavioral improvements in daily life are now capable of being managed and prevented more effectively. However, to increase patient engagement through mHealth, it is important for the initial design to consider functionality and usability factors and accurately assess user demands during the developmental process so that the app can be used continuously.ObjectiveThe purpose of the study was to provide insightful information for developing mHealth service for patients with CVD based on user research to help enhance communication between patients and doctors.MethodsTo drive the mobile functions and services needed to manage diseases in CVD patients, user research was conducted on patients and doctors at a tertiary general university hospital located in the Seoul metropolitan area of South Korea. Interviews and a survey were performed on patients (35 participants) and a focus group interview was conducted with doctors (5 participants). A mock-up mobile app was developed based on the user survey results, and a usability test was then conducted (8 participants) to identify factors that should be considered to improve usability.ResultsThe majority of patients showed a positive response in terms of their interest or intent to use an app for managing CVD. Functional features, such as communication with doctors, self-risk assessment, exercise, tailored education, blood pressure management, and health status recording had a score of 4.0 or higher on a 5-point Likert scale, showing that these functions were perceived to be useful to patients. The results of the mock-up usability test showed that inputting and visualizing blood pressure and other health conditions was required to be easier. The doctors requested a function that offered a comprehensive view of the patient’s daily health status by linking the mHealth app data with the hospital’s electronic health record system.ConclusionsInsights derived from a user study for developing an mHealth tool for CVD management, such as self-assessment and a communication channel between patients and doctors, may be helpful to improve patient engagement in care.

No abstract

Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed machine learning-based prediction algorithms. This study included 222,998 Korean adults aged 40–79 years, naïve to lipid-lowering therapy, had no history of cardiovascular disease. Pre-existing models showed moderate to good discrimination in predicting future cardiovascular events (C-statistics 0.70–0.80). Pooled cohort equation (PCE) specifically showed C-statistics of 0.738. Among other machine learning models such as logistic regression, treebag, random forest, and adaboost, the neural network model showed the greatest C-statistic (0.751), which was significantly higher than that for PCE. It also showed improved agreement between the predicted risk and observed outcomes (Hosmer–Lemeshow χ2 = 86.1, P < 0.001) than PCE for whites did (Hosmer–Lemeshow χ2 = 171.1, P < 0.001). Similar improvements were observed for Framingham risk score, systematic coronary risk evaluation, and QRISK3. This study demonstrated that machine learning-based algorithms could improve performance in cardiovascular risk prediction over contemporary cardiovascular risk models in statin-naïve healthy Korean adults without cardiovascular disease. The model can be easily adopted for risk assessment and clinical decision making.

ObjectivesTo successfully introduce an Internet of Things (IoT) system in the hospital environment, this study aimed to identify issues that should be considered while implementing an IoT based on a user demand survey and practical experiences in implementing IoT environment monitoring systems.MethodsIn a field test, two types of IoT monitoring systems (on-premises and cloud) were used in Department of Laboratory Medicine and tested for approximately 10 months from June 16, 2016 to April 30, 2017. Information was collected regarding the issues that arose during the implementation process.ResultsA total of five issues were identified: sensing and measuring, transmission method, power supply, sensor module shape, and accessibility.ConclusionsIt is expected that, with sufficient consideration of the various issues derived from this study, IoT monitoring systems can be applied to other areas, such as device interconnection, remote patient monitoring, and equipment/environmental monitoring.

In order to detect blood volume changes, we proposed the new magnetic plethysmographic sensor using timevarying magnetic fields, and thereby, measuring the change of impedance of exciting coil. The change of coil impedance was proportional to the change of blood volume passing through a volume-of-interests, which inductively coupled with exciting coil. In order to verify the feasibility of the proposed method, photo-plethysmographic and magneto-plethysmographic (MPG) signals were recorded from the index and middle finger of the left hand simultaneously. Comparison of the proposed sensor signals with ultrasound Doppler blood flow velocity recordings shows the excellent correlation (r = 0.9355, p < 0.01) and the RR intervals derived from electrocardiograph and MPG signals showed a very high degree of correlation (r = 0.9823, p < 0.01).Index Terms-Blood flow, blood volume, magnetic plethysmography, time-varying magnetic fields.