Preventive maintenance is a core function of clinical engineering, and it is essential to guarantee the correct functioning of the equipment. The management and control of maintenance activities are equally important to perform maintenance. As the variety of medical equipment increases, accordingly the size of maintenance activities increases, the need for better management and control become essential. This paper aims to develop a new model for preventive maintenance priority of medical equipment using quality function deployment as a new concept in maintenance of medical equipment. We developed a three-domain framework model consisting of requirement, function, and concept. The requirement domain is the house of quality matrix. The second domain is the design matrix. Finally, the concept domain generates a prioritization index for preventive maintenance considering the weights of critical criteria. According to the final scores of those criteria, the prioritization action of medical equipment is carried out. Our model proposes five levels of priority for preventive maintenance. The model was tested on 200 pieces of medical equipment belonging to 17 different departments of two hospitals in Piedmont province, Italy. The dataset includes 70 different types of equipment. The results show a high correlation between risk-based criteria and the prioritization list.

One of the primary concerns of computer‐aided diagnosis is the detection of retinal disorders. The study aims to categorize the patients into choroidal neovascularization, diabetic macular edema, drusen, and normal by using optical coherence tomography (OCT) images. For the first time, two novel transfer learning‐based techniques were used for retinal disorder classification: SqueezeNet and the Inception V3 Net. Two SqueezeNet scenarios were used to compare the performance of the original SqueezeNet and the improved one. A dataset of 11 200 OCT images was used for data partitioning of SqueezeNet and, meanwhile, 18 000 images for Inception V3 Net. The modified SqueezeNet achieved 98% accuracy, a 1.2% improvement over the original. The Inception V3 Net classifier improved its classification accuracy to 98.4%. When compared to other classifiers and a human expert, the transfer learning approach demonstrated its robustness in the challenge of retinal disorders classification with a large dataset.

No abstract

No abstract