SUSU scientists together with colleagues from Spain, France and Egypt have developed a model for more effective diagnosis of cardiovascular diseases and diabetes using artificial intelligence and Internet of Things technology. This work was supported by the Russian Ministry of Science and Higher Education. A new model for diagnosing diseases was described in an article published in the highly rated journal IEEE Access (Q1).
Smart applications for Medicine
Senior Researcher of the Department of System Programming, Ph. D. in Machine learning Kumar Sachin, together with scientists from other countries, created a new model for the operation of digital applications and their application in medicine.
Recent advances of the Internet of Things, cloud computing and artificial intelligence have turned the conventional healthcare system into an intelligent one. Healthcare services can be significantly improved using the Internet of Things and artificial intelligence. Now advanced methods and scientific theory generate huge amounts of digital data that can be applied to create clinical applications based on the Android OS.
"Clinical applications are one of the latest information technology products. Smart healthcare is supposed to use simple, elegant and multitasking applications. These applications contribute to the evolution of the clinical model of medicine, that is, the transition from the standard treatment of the disease according to the scheme to the treatment of a specific patient. There should be changes in the development of medical informatization from generalized medical data to regional medical data. Thus, the clinical management of the patient will become more more person-centered rather than medical statistics. Ideally, we should move from treating diseases to a preventive medical system. These changes are aimed at improving the healthcare system, which, in turn, improves knowledge in the field of medicine and implies a transition to intelligent medicine," says Kumar Sachin.
Doctors, patients, clinical and research centers are interested in providing better medical services using the latest technologies. There are many parameters to consider when applying these technologies: disease prevention and surveillance, prognosis and treatment, clinical management, health decision making and medical research.
Mobile Internet, cloud computing, big data, 5G systems, microelectronics and artificial intelligence, as well as intelligent biotechnologies are used at every stage of «smart» healthcare. Portable devices can be used to monitor the health status of patients when necessary. Patients themselves will be able to receive clinical recommendations through virtual support and control devices remotely, and doctors will be able to use intelligent clinical decision-making systems to select and improve the quality of diagnostic procedures.
Collecting information from all devices
Devices that use the Internet of Things surround us in everyday life: these are smart watches, fitness bracelets and smartphones, portable ECG devices, blood pressure monitors, blood glucose meters and thermometers. These gadgets track the level of physical activity, heart rate, blood glucose levels, they are convenient to use and familiar, they do not need to invent a new technology for them.
The scientists' idea is to create a universal application that can collect data from different devices and translate it into a compatible format. Thus, the smartphone processes and organizes them. On the basis of the received complex information, a number of medical recommendations will be built for one specific patient, taking into account his indicators.
"The model we presented includes various stages: data collection, pre-processing, classification and parameter adjustment. Portable IoT devices and sensors allow you to collect data without hindrance, while artificial intelligence methods use them to diagnose diseases. Based on these indicators, it is possible to determine how good the lifestyle of a patient with a particular disease is. The smartphone processes the data received via a Bluetooth connection with low power consumption and classifies it as healthy, within the normal range, or as unhealthy, " the scientist explains.
The effectiveness of the new model was confirmed by the use of health data. During the experiments, the presented model achieved a maximum accuracy of 96.16 % and 97.26 % in the diagnosis of heart disease and diabetes, respectively. Thus, the proposed model can be used as a suitable tool for diagnosing diseases for an intelligent healthcare system.
South Ural State University (SUSU) is a university of digital transformations, where innovative research is conducted in most priority areas of science and technology development. In accordance with the strategy of scientific and technological development of the Russian Federation, the university is focused on the development of large scientific interdisciplinary projects in the field of digital industry, materials science and ecology. In the Year of Science and Technology, SUSU will take part in the competition under the "Priority–2030"program. The university performs the functions of the regional project office of the Ural Interregional World-class Scientific and Educational Center (UMNOC).