Improved grey‐level correlation feature and neural network model for medical resource requirement prediction

Abstract

Although the country's general practitioner training system is constantly improving, problems such as large requirement gaps, low specialization, unfair resource allocation, and uneven regional distribution still exist. In order to promote the improvement of the general practitioner system, to solve the problems of low accuracy and poor robustness of the existing models for medical resource requirement prediction, this paper proposes a combination of grey‐scale prediction features and back propogation algorithm (BP) neural network medical resource requirement prediction algorithm. The algorithm first uses the principal component analysis algorithm to solve the principal components of the medical resource requirement influencing factors, then extracts the equal‐dimensional dynamic grey‐level optimization model grey prediction features of the principal component score, and finally inputs the features into the BP neural network to complete the medical resource requirement prediction. Subsequently, a large number of comparative experiments were carried out on the algorithm proposed in this paper using the medical resource requirement of a certain province as a data set. The experimental results have shown that the comprehensive improvement model proposed in this paper has the best effect in predicting the requirement of medical resources, which contains strong robustness and stability. The algorithm is suitable for the needs of medical resources at this stage. Predicting on the above has strong practical significance in many scenarios by using the proposed algorithm.