The purpose of this study was to develop and evaluate the performance of deep learning methods based on convolutional neural networks (CNN) to detect and identify specific hip arthroplasty models. In this study, we propose a novel deep learning-based approach to identify hip arthroplasty implants’ design using anterior–posterior images of both the stem and the cup. We harness the pre-trained ResNet50 CNN model and employ transfer learning methods to adapt the model for the implants identification task using a total of 714 radiographs of 4 different hip arthroplasty implant designs. Performance was compared with the operative notes and crosschecked with implant sheets. We also evaluate the difference in performance of models trained with the images of the stem, the cup or both. The training and validation data sets were comprised of 357 stem images and 357 cup radiographs across 313 patients and included 4 hip arthroplasty implants from 4 leading implant manufacturers. After 1000 training epochs the model classified 4 implant models with very high accuracy. Our results showed that jointly using stem images and cup images did not improve the classification accuracy of the CNN model. CNN can accurately distinguish between specific hip arthroplasty designs. This technology could offer a useful adjunct to the surgeon in preoperative identification of the prior implant. Using stem images or cup images to train the CNN can both achieve effective identification accuracy, with the accuracy of the stem images being higher. Using stem images and cup images together is not more effective than using images from only one perspective.

No abstract

Background COVID-19 has brought greater workload pressures to the medical field, such as medical staff being required to wear personal protective equipment (PPE). While PPE can protect the safety of staff during the pandemic, it can also accelerate the accumulation of fatigue among operators. Objective This study explores the influence of different protection states on the mental fatigue of nurses. Methods In this study, 10 participants (5 males and 5 females) were randomly selected among applicants to monitor mental fatigue during the nurses’ daily work in four different PPE states (low temperature and low protection; low temperature and high protection; high temperature and low protection; high temperature and high protection). The NASA subjective mental fatigue scale was used for subjective evaluation. Reaction time, attention concentration, attention distribution, memory, and main task completion time were used for objective evaluation. Results The results demonstrated a significant difference in the effects of different protection states on mental fatigue. The state of high temperature and high protection had the greatest influence on mental fatigue, the state of low temperature and low protection had the least, and states of high (low) temperature and low (high) protection had intermediate effects on mental fatigue. Furthermore, the correlation between the subjective and objective fatigue indices was analyzed using a multiple regression model. Conclusion This study clarified the influence of different protection states on the mental fatigue of nurses, and verified that nurses require more time and energy to complete the same work as before under high protection states. It provides a basis for evaluating the mental fatigue of nurses in the unique period of the COVID-19 pandemic and specific ideas for optimizing the nursing process.

Medication administration errors account for a relatively high proportion of medical errors, with more than 50% occurring at the nursing administration stage. Nursing is characterized by a large amount of work, rigid working hours, high information cognitive intensity, and frequent information updates. The high workload of nurses is a significant cause of medication administration errors. In this study, a literature analysis was used to determine the elements of the system dynamics model, and the causal loop diagram was used to draw the relationship framework among the elements. Vensim personal learning edition and interview surveys were then used for model validation and simulation. First, 302 case analyses of medication administration errors collected from the three metropolitan area hospitals were used to construct the causal loop diagram, the stock and flow map of the medication administration error system, and the dynamics model; second, the model was tested from theoretical and historical data simulation perspectives; finally, the system dynamics model proposed in this study was used to simulate a medical institution from overtime and policy perspectives. Through system dynamics modeling, the inducing mechanism of workload on medication administration errors in nursing operations was elucidated, and corresponding suggestions for prevention were provided. In addition, ideas and basis for optimizing the medication administration process, improving workload, and preventing medication administration errors considering workload were provided.