A new cloud-based method for composition of healthcare services using deep reinforcement learning and Kalman filtering.

Healthcare has significantly contributed to the well-being of individuals around the globe; nevertheless, further benefits could be derived from a more streamlined healthcare system without incurring additional costs. Recently, the main attributes of cloud computing, such as on-demand service, high scalability, and virtualization, have brought many benefits across many areas, especially in medical services. It is considered an important element in healthcare services, enhancing the performance and efficacy of the services. The current state of the healthcare industry requires the supply of healthcare products and services, increasing its viability for everyone involved. Developing new approaches for discovering and selecting healthcare services in the cloud has become more critical due to the rising popularity of these kinds of services. As a result of the diverse array of healthcare services, service composition enables the execution of intricate operations by integrating multiple services' functionalities into a single procedure. However, many methods in this field encounter several issues, such as high energy consumption, cost, and response time. This article introduces a novel layered method for selecting and evaluating healthcare services to find optimal service selection and composition solutions based on Deep Reinforcement Learning (Deep RL), Kalman filtering, and repeated training, addressing the aforementioned issues. The results revealed that the proposed method has achieved acceptable results in terms of availability, reliability, energy consumption, and response time when compared to other methods.

Independent and joint effects of sleep duration and sleep quality on suboptimal self-rated health in medical students: A cross-sectional study.

Objective: Studies on the association between sleep behavior and health often ignored the confounding effects of biorhythm-related factors. This study aims to explore the independent and joint effects of sleep duration and sleep quality on suboptimal self-rated health (SRH) in medical students. Methods: Cross-sectional study. Proportional stratified cluster sampling was used to randomly recruit students from various medical specialties at a medical university in eastern China. Our questionnaire mainly included information on basic demographic characteristics, SRH, sleep behavior, and biorhythm-related factors. The independent and joint effects of sleep duration and sleep quality on suboptimal SRH were assessed by logistic regression after controlling for potential confounders. Results: Of 1,524 medical students (mean age = 19.9 years, SD = 1.2 years; 59.1% female), 652 (42.8%) had suboptimal SRH. Most medical students (51.5%) slept for 7 h/night, followed by ≥8 (29.1%) and ≤ 6 h (19.4%). After adjusting for basic demographic characteristics and biorhythm-related factors, compared with students who slept for ≥8 h/night, the adjusted ORs (95%CI) for those who slept 7 and ≤ 6 h/night were 1.36 (1.03, 1.81) and 2.28 (1.60, 3.26), respectively (P < 0.001 for trend); compared with those who had good sleep quality, the adjusted ORs (95%CI) for those who had fair and poor sleep quality were 4.12 (3.11, 5.45) and 11.60 (6.57, 20.46), respectively (P < 0.001 for trend). Further, compared with those who slept for ≥8 h/night and good sleep quality, those who slept ≤ 6 h and poor sleep quality had the highest odds of suboptimal SRH (OR 24.25, 95%CI 8.73, 67.34). Conclusions: Short sleep and poor sleep quality were independently and jointly associated with higher odds of suboptimal SRH among medical students.