Wearable computing and artificial intelligence for healthcare applications

Recent Patient Health Monitoring Platforms Incorporating Internet of Things-Enabled Smart Devices

Synergistic integration of the Internet of Things (IoT), cloud computing, and big data technologies in healthcare have led to the notion of "smart health." Smart health is an emerging concept that refers to the provision of healthcare services for prevention, diagnosis, treatment, and follow-up management at any time or any place by connecting information technologies and healthcare. As a significant breakthrough in smart healthcare development, IoT-enabled smart devices allow medical centers to carry out preventive care, diagnosis, and treatment more competently. This review focuses on recently developed patient health monitoring platforms based on IoT-enabled smart devices that can collect real-time patient data and transfer information for assessment by healthcare providers, including doctors, hospitals, and clinics, or for self-management. We aimed to summarize the available information about recently approved devices and state-of-the-art developments through a comprehensive, systematic literature review. In this review, we also discuss possible future directions for the integration of cloud computing and blockchain, which may offer unprecedented breakthroughs in on-demand medical services. The combination of IoT with real-time, remote patient monitoring empowers patients to assert more control over their care, thereby allowing them to actively monitor their particular health conditions.

Digitally enhanced recovery: Investigating the use of digital self-tracking for monitoring leisure time physical activity of cardiovascular disease (CVD) patients undergoing cardiac rehabilitation

Research has shown that physical activity is essential in the prevention and treatment of chronic diseases like cardiovascular disease (CVD). Smart wearables (e.g., smartwatches) are increasingly used to foster and monitor human behaviour, including physical activity. However, despite this increased usage, little evidence is available on the effects of smart wearables in behaviour change. The little research which is available typically focuses on the behaviour of healthy individuals rather than patients. In this study, we investigate the effects of using smart wearables by patients undergoing cardiac rehabilitation. A field experiment involving 29 patients was designed and participants were either assigned to the study group (N = 13 patients who finished the study and used a self-tracking device) or the control group (N = 16 patients who finished the study and did not use a device). For both groups data about physiological performance during cardiac stress test was collected at the beginning (baseline), in the middle (in week 6, at the end of the rehabilitation in the organized rehabilitation setting), and at the end of the study (after 12 weeks, at the end of the rehabilitation, including the organized rehabilitation plus another 6 weeks of self-organized rehabilitation). Comparing the physiological performance of both groups, the data showed significant differences. The participants in the study group not only maintained the same performance level as during the midterm examination in week 6, they improved performance even further during the six weeks that followed. The results presented in this paper provide evidence for positive effects of digital self-tracking by patients undergoing cardiac rehabilitation on performance of the cardiovascular system. In this way, our study provides novel insight about the effects of the use of smart wearables by CVD patients. Our findings have implications for the design of self-management approaches in a patient rehabilitation setting. In essence, the use of smart wearables can prolong the success of the rehabilitation outside of the organized rehabilitation setting.

Body-monitoring and health supervision by means of optical fiber-based sensing systems in medical textiles

Long-term monitoring with optical fibers has moved into the focus of attention due to the applicability for medical measurements. Within this Review, setups of flexible, unobtrusive body-monitoring systems based on optical fibers and the respective measured vital parameters are in focus. Optical principles are discussed as well as the interaction of light with tissue. Optical fiber-based sensors that are already used in first trials are primarily selected for the section on possible applications. These medical textiles include the supervision of respiration, cardiac output, blood pressure, blood flow and its saturation with hemoglobin as well as oxygen, pressure, shear stress, mobility, gait, temperature, and electrolyte balance. The implementation of these sensor concepts prompts the development of wearable smart textiles. Thus, current sensing techniques and possibilities within photonic textiles are reviewed leading to multiparameter designs. Evaluation of these designs should show the great potential of optical fibers for the introduction into textiles especially due to the benefit of immunity to electromagnetic radiation. Still, further improvement of the signal-to-noise ratio is often necessary to develop a commercial monitoring system.

Smartphone-based recognition of states and state changes in bipolar disorder patients

Today's health care is difficult to imagine without the possibility to objectively measure various physiological parameters related to patients' symptoms (from temperature through blood pressure to complex tomographic procedures). Psychiatric care remains a notable exception that heavily relies on patient interviews and self-assessment. This is due to the fact that mental illnesses manifest themselves mainly in the way patients behave throughout their daily life and, until recently there were no "behavior measurement devices." This is now changing with the progress in wearable activity recognition and sensor enabled smartphones. In this paper, we introduce a system, which, based on smartphone-sensing is able to recognize depressive and manic states and detect state changes of patients suffering from bipolar disorder. Drawing upon a real-life dataset of ten patients, recorded over a time period of 12 weeks (in total over 800 days of data tracing 17 state changes) by four different sensing modalities, we could extract features corresponding to all disease-relevant aspects in behavior. Using these features, we gain recognition accuracies of 76% by fusing all sensor modalities and state change detection precision and recall of over 97%. This paper furthermore outlines the applicability of this system in the physician-patient relations in order to facilitate the life and treatment of bipolar patients.