Early Intelligent Identification of Diabetic Complications

By Lina Han, Shuli Guo, Yanan Guo

This book delves into the AI practical application in the association patterns & prediction models of diabetes complications. In view of dataset preprocessing and clustering, a fusion clustering algorithm is proposed in combination with the self-organizing map neural network, and the superiority of the improved algorithm is proved through comparative experiments, overcoming the sensitive clustering centers and uncertain number of clustering categories of the traditional fuzzy c-means algorithm. For designing the association pattern of diabetic complications based on the improved Apriori algorithm, matrix compression parallelization is investigated to improve the mining efficiency of the Apriori algorithm. At the same time, the PS interest degree is improved by combining subjective factors and rule credibility, and the IPSR interest degree measurement is proposed to ensure the effectiveness of the mining results. Then, a diabetes complication prediction model is established based on the improved least squares support vector machine. The sparrow search algorithm is used to optimize the model parameters, the prediction deviation is corrected in combination with the deep belief network to further improve the prediction accuracy, and the particle swarm optimization algorithm is used to realize the adaptive selection of the network structure. At last, an intelligent early warning system using the Vue.js framework and the Flask framework for diabetes complications is designed, which realizes the following functions such as visualization of common diabetes' complication association patterns, prediction of diabetes complications, and query of diabetes patient information.

• Format: Hardcover
• Language: English
• ISBN: 9819248833
• ISBN13: 9789819248834
• Release Date: January 2027
• Publisher: Springer
• Length: 115 Pages