ObjectiveTo explore the model of sharing appointments between medical inspection resources in medical alliance hospitals in the medical profession, in order to improve the utilization efficiency of medical inspection resources and patient satisfaction, and to promote the effective implementation of intelligent services in medical alliance hospitals. MethodsBy analyzing the medical process of medical inspection appointments, and organizing the inspection appointment resources of each hospital according to the actual business characteristics of each hospital of the medical alliance by the unified medical inspection appointment platform. Through the unified big data platform, the business collaboration between the medical alliance hospitals and the sharing and scheduling of medical inspection resources among the hospitals of the medical alliance are realized. ResultsThe construction and use of the medical alliance unified inspection platform has realized the sharing and utilization of inspection resources between hospitals in the medical alliance, which is convenient for patients to choose their own inspection resources across hospitals when making an appointment for inspection, and further improves patient satisfaction. ConclusionThe unified medical appointment platform unifies the management of the medical alliance's appointment examination resources, which can not only effectively improve the utilization efficiency of medical inspection appointment resources, but also expand the effective scope of patients' choice of medical inspection appointments, and at the same time improve patient satisfaction and promote the construction of hospital intelligent services.
Objective To explore an artificial intelligence (AI)-based method for automated hand hygiene monitoring and to compare the effectiveness of three algorithms (UniFormerV2, TDN, C3D) in recognizing hand hygiene steps in surgical settings, thereby aiding hospital infection control. Methods From April to October 2024, we non-invasively collected 641 video recordings of healthcare staff performing hand hygiene at four-bay scrub sinks in two tertiary hospitals using overhead HD cameras. The dataset was annotated by five trained experts for model training and validation. Results Following training on 385 samples, internal validation (n=119) showed the C3D model achieved 81% accuracy, 87% recall, and an 83% F1-score. The TDN model achieved 93%, 91%, and 92% for the same metrics. The UniFormerV2 model outperformed both, with an accuracy, recall, and F1-score of 93%—an improvement of over 10 percentage points compared to traditional CNNs (TDN, C3D). It also achieved an 84% accuracy in external validation, demonstrating strong generalization. Conclusion The UniFormerV2 model is more accurate than CNN-based models for hand hygiene step recognition and shows robust performance in external validation. It presents a viable tool for healthcare facilities to enhance hand hygiene management, ultimately improving medical quality and patient safety.
