No abstract

Introduction The use of telemedicine in orthopaedics can provide high-quality orthopaedic services to patients in remote areas. Tele-orthopaedics is widely acknowledged for decreasing travel, time and cost, increasing accessibility and quality of care. In the absence of a comprehensive review on tele-orthopaedics applications and services, here, we systematically identify and classify the tele-orthopaedic applications and services and provide an overview of the trends in the field. Methods In this study, a systematic mapping was conducted to answer six research questions, we searched the databases Scopus, PubMed, IEEE Digital Library and Web of Science up to 2019. Consequently, 77 papers were screened and selected on the basis of specific inclusion and exclusion criteria. Results We found that mobile-based teleconsultation was mostly asynchronous, while non-mobile teleconsultation was synchronous. The results showed that the physician–patient relationship was more common than other interactions, such as physician–physician and physician–robot interactions. In addition, more than half of the services provided by tele-orthopaedics have been used for orthopaedic diseases/traumas in which joint replacement and fracture reduction have been the most important orthopaedic procedures. It has been noted that more attention has been paid to tele-orthopaedics in developed countries such as the USA, Australia, Canada and Finland. Discussion Telemonitoring (teleconsultation and telemetry) and telesurgery (telerobotics and telementoring) were found to be the two major forms of tele-orthopaedics. Mobile phones were used asynchronously in most of the teleconsultations. The development of different applications may result in the use of multiple smartphones applications in real-time teleconsultation. The use of smartphones is expected to increase in the near future.

No abstract

Nowadays, applications for the Internet of Things (IoT) have been introduced in different fields of medicine to provide more efficient medical services to the patients. A systematic mapping study was conducted to answer ten research questions with the purposes of identifying and classifying the present medical IoT technological features as well as recognizing the opportunities for future developments. We reviewed how cloud, wearable technologies, wireless communication technologies, messaging protocols, security methods, development boards, microcontrollers, mobile/IoT operating systems, and programming languages have been engaged in medical IoT. Based on specific inclusion/exclusion criteria, 89 papers, published between 2000 and 2018, were screened and selected. It was found that IoT studies, with a publication rise between 2015 and 2018, predominantly dealt with the following IoT features: (a) wearable sensor types of chiefly accelerometer and ECG placed on 16 different body parts, especially the wrist (33%) and the chest (21%) or implanted on the bone; (b) wireless communication technologies of Bluetooth, cellular networks, and Wi-Fi; (c) messaging protocols of mostly MQTT; (d) utilizing cloud for both storing and analyzing data; (e) the security methods of encryption, authentication, watermark, and error control; (f) the microcontrollers belonging to Atmel ATmega and ARM Cortex-M3 families; (g) Android as the commonly used mobile operating system and TinyOS and ContikiOS as the commonly used IoT operating systems; (h) Arduino and Raspberry Pi development boards; and finally (i) MATLAB as the most frequently employed programming language in validation research. The identified gaps/opportunities for future exploration are, namely, employment of fog/edge computing in storage and processing big data, the overlooked efficient features of CoAP messaging protocol, the unnoticed advantages of AVR Xmega and Cortex-M microcontroller families, employment of the programming languages of Python for its significant capabilities in evaluation and validation research, development of the applications being supported by the mobile/IoT operating systems in order to provide connection possibility among all IoT devices in medicine, exploiting wireless communication technologies such as BLE, ZigBee, 6LoWPAN, NFC, and 5G to reduce power consumption and costs, and finally uncovering the security methods, usually used in IoT applications, in order to make other applications more trustworthy.

Background. In today’s industrialized world, coronary artery disease (CAD) is one of the leading causes of death, and early detection and timely intervention can prevent many of its complications and eliminate or reduce the resulting mortality. Machine learning (ML) methods as one of the cutting-edge technologies can be used as a suitable solution in diagnosing this disease. Methods. In this study, different ML algorithms’ performances were compared for their effectiveness in developing a model for early CAD diagnosis based on clinical examination features. This applied descriptive study was conducted on 303 records and overall 26 features, of which 26 were selected as the target features with the advice of several clinical experts. In order to provide a diagnostic model for CAD, we ran most of the most critical classification algorithms, including Multilayer Perceptron (MLP), Support Vector Machine (SVM), Logistic Regression (LR), J48, Random Forest (RF), K-Nearest Neighborhood (KNN), and Naive Bayes (NB). Seven different classification algorithms with 26 predictive features were tested to cover all feature space and reduce model error, and the most efficient algorithms were identified by comparison of the results. Results. Based on the compared performance metrics, SVM (AUC = 0.88, F-measure = 0.88, ROC = 0.85), and RF (AUC = 0.87, F-measure = 0.87, ROC = 0.91) were the most effective ML algorithms. Among the algorithms, the KNN algorithm had the lowest efficiency (AUC = 0.81, F-measure = 0.81, ROC = 0.77). In the diagnosis of coronary artery disease, machine learning algorithms have played an important role. Proposed ML models can provide practical, cost-effective, and valuable support to doctors in making decisions according to a good prediction. Discussion. It can become the basis for developing clinical decision support systems. SVM and RF algorithms had the highest efficiency and could diagnose CAD based on patient examination data. It is suggested that further studies be performed using these algorithms to diagnose coronary artery disease to obtain more accurate results.