期刊名称：International Journal of Database Management Systems
印刷版ISSN：0975-5985
电子版ISSN：0975-5705
出版年度：2019
卷号：11
期号：1
页码：19-35
DOI：10.5121/ijdms.2019.11102
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：With the continuous development of medical information construction, the potential value of a large amount of medical information has not been exploited. Excavate a large number of medical records of outpatients, and train to generate disease prediction models to assist doctors in diagnosis and improve work efficiency.This paper proposes a disease prediction method based on k-nearest neighbor improvement algorithm from the perspective of patient similarity analysis. The method draws on the idea of clustering, extracts the samples near the center point generated by the clustering, applies these samples as a new training sample set in the K-nearest neighbor algorithm; based on the maximum entropy The K-nearest neighbor algorithm is improved to overcome the influence of the weight coefficient in the traditional algorithm and improve the accuracy of the algorithm. The real experimental data proves that the proposed k-nearest neighbor improvement algorithm has better accuracy and operational efficiency.
