Reliability estimation of medical equipment

Abstract

Anomalies or failures in medical equipment may lead to severe consequences. Data-driven prognostic and health management (PHM) approaches can improve maintenance efficiency and reduce maintenance costs at hospitals while protecting patients’ lives. However, currently, the research and application of PHM in medical equipment are still very limited. The development of the Internet of Things (IoT) technology provides new opportunities for PHM, which can safely collect, analyze and store real-time equipment data in hospitals. The data-driven models used in PHM are responsible for predicting anomalies or failures. However, current data-driven models’ performance may be limited due to lack of consideration for the interaction of similar features and the importance of different time steps. Hence, this paper proposes a new deep learning network called similar feature interaction with distance self-attention for the PHM of medical equipment. Firstly, a similar feature interaction module which uses clustering algorithms and causal convolution layers is proposed to consider the interaction of similar features. Secondly, a distance self-attention mechanism is proposed to allocate more attention to important time steps. The experiments on millions of CT equipment operating status instants collected by IoT in the hospital and the public dataset show that the proposed model is superior to existing models. The results show that the Accuracy, Recall, Precision and F1-score of the proposed model on the real CT log data achieve 0.865, 0.682, 0.469 and 0.556, respectively. The proposed PHM model can assist the equipment maintenance team of hospitals in making decisions under the IoT framework.