RÉSUMÉ
Objective To evaluate the rationality of the number of configured monitors based on error back propagation(BP)neural network.Methods A BP neural network model was established with the number of the equipment in use as the output result and the average number of inpatients,the average number of operations,the average days of hospitalization,the number of scrapped equipment,the average age of equipment and times of equipment maintenance as the input indicators.The data of 9 internal medicine departments in the whole year of 2020-2021 and the first 2 quarters of 2022 were collected on a quarterly basis as the training set,and the data of the third quarter of 2022 was used as the test set to verify the learning results.The performance of the model was analyzed using the root mean square error,mean absolute error and coefficient of determination.Results The model established behaved well in prediction with the root mean square error between the predicted and expected values of the model being 1.135 7,the mean absolute error being 0.893 72 and the coefficient of determination being 0.958 71.Conclusion The BP neural network-based evaluation is feasible for the number of configured monitors,and guidance is provided for the optimized configuration of the equipment.[Chinese Medical Equipment Journal,2023,44(9):14-18]