RESUMO

According to the Pan American Health Organization, cardiovascular disease is the leading cause of death worldwide, claiming an estimated 17.9 million lives each year. This paper presents a systematic review to highlight the use of IoT, IoMT, and machine learning to detect, predict, or monitor cardiovascular disease. We had a final sample of 164 high-impact journal papers, focusing on two categories: cardiovascular disease detection using IoT/IoMT technologies and cardiovascular disease using machine learning techniques. For the first category, we found 82 proposals, while for the second, we found 85 proposals. The research highlights list of IoT/IoMT technologies, machine learning techniques, datasets, and the most discussed cardiovascular diseases. Neural networks have been popularly used, achieving an accuracy of over 90%, followed by random forest, XGBoost, k-NN, and SVM. Based on the results, we conclude that IoT/IoMT technologies can predict cardiovascular diseases in real time, ensemble techniques obtained one of the best performances in the accuracy metric, and hypertension and arrhythmia were the most discussed diseases. Finally, we identified the lack of public data as one of the main obstacles for machine learning approaches for cardiovascular disease prediction.

RESUMO

BACKGROUND: Around 15 million premature babies are born annually, requiring specialized care. Incubators are vital for maintaining their body temperature, which is crucial for their well-being. Ensuring optimal conditions in incubators, including constant temperature, oxygen control, and comfort, is essential for improving the care and survival rates of these infants. METHODS: To address this, an IoT-based monitoring system was developed in a hospital setting. The system comprised hardware components such as sensors and a microcontroller, along with software components including a database and a web application. The microcontroller collected data from the sensors, which was then transmitted to a broker via WiFi using the MQTT protocol. The broker validated and stored the data in the database, while the web application provided real-time access, alerts, and event recording. RESULTS: Two certified devices were created, employing high quality components. The system was successfully implemented and tested in both the biomedical engineering laboratory and the neonatology service of the hospital. The results of the pilot test supported the concept of IoT-based technology, demonstrating satisfactory responses in temperature, humidity, and sound variables within the incubators. CONCLUSIONS: The monitoring system facilitated efficient record traceability, allowing access to data over various timeframes. It also captured event records (alerts) related to variable problems, providing information on duration, date, hour, and minutes. Overall, the system offered valuable insights and enhanced monitoring capabilities for neonatal care.

Assuntos

RESUMO

Pervasive healthcare services have undergone a great evolution in recent years. The technological development of communication networks, including the Internet, sensor networks, and M2M (Machine-to-Machine) have given rise to new architectures, applications, and standards related to addressing almost all current e-health challenges. Among the standards, the importance of OpenEHR has been recognized, since it enables the separation of medical semantics from data representation of electronic health records. However, it does not meet the requirements related to interoperability of e-health devices in M2M networks, or in the Internet of Things (IoT) scenarios. Moreover, the lack of interoperability hampers the application of new data-processing techniques, such as data mining and online analytical processing, due to the heterogeneity of the data and the sources. This article proposes an Internet of Medical Things (IoMT) platform for pervasive healthcare that ensures interoperability, quality of the detection process, and scalability in an M2M-based architecture, and provides functionalities for the processing of high volumes of data, knowledge extraction, and common healthcare services. The platform uses the semantics described in OpenEHR for both data quality evaluation and standardization of healthcare data stored by the association of IoMT devices and observations defined in OpenEHR. Moreover, it enables the application of big data techniques and online analytic processing (OLAP) through Hadoop Map/Reduce and content-sharing through fast healthcare interoperability resource (FHIR) application programming interfaces (APIs).

Assuntos