At present, chronic diseases in internal medicine are becoming increasingly prominent in China, and the amount of data is gradually increasing. Hypertension, as a common chronic disease in internal medicine, consistently ranks among the top in the world in terms of patient numbers. In response to the above issues, this article proposes an intelligent diagnosis cloud platform for chronic diseases in internal medicine based on cloud computing technology. This platform is designed to help people effectively prevent chronic diseases in internal medicine and reduce the risk of complications. Although there are already ways to combine random optimization with algorithms such as KNN and RF, the prediction accuracy is not high. Therefore, this study combines KNN, RF and other algorithms with grid search optimization methods. Compared with previous methods, this strategy can provide users with a more accurate algorithm prediction model. The results indicate that the XGBoost algorithm based on grid search optimization performs better than other models and can be used for intelligent diagnosis of hypertension. Based on the characteristics of this hypertension dataset, although this method performs well in predicting this dataset, it remains to be verified whether it can also exhibit this feature on other datasets.
Liu et al. (Fri,) studied this question.