Li B, Ding S, Song G, Li J, Zhang Q. Computer-Aided Diagnosis and Clinical Trials of Cardiovascular Diseases Based on Artificial Intelligence Technologies for Risk-Early Warning Model.
J Med Syst 2019;
43:228. [PMID:
31197490 DOI:
10.1007/s10916-019-1346-x]
[Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2019] [Accepted: 05/20/2019] [Indexed: 11/25/2022]
Abstract
The use of artificial intelligence in medicine is currently an issue of great interest, especially with regard to the diagnostic or predictive analysis of medical data. In order to achieve the regional medical and public health data analysis through artificial intelligence technologies, spark data analysis is adopted as the research platform for hypertension patients, and artificial intelligence technologies are used to preprocess the data with inconsistency, redundancy, incompleteness, noise and error; Aiming at the unbalanced data sets, the Z-score standard is adopted to convert data into usable form suitable for data mining. And, the application of Logistic, Naive Bayesian regression, and support vector machine based on three groups of different prognosis in severe cases, including stroke, heart failure and renal failure symptoms, establish the risk early warning model for 3 years time. In addition, to select the optimal feature subset based on medicine big-data features, the model simplification and optimization are done in training process, the experimental results show that the feature subset selection can ensure the classification performance similar to the clinical features of the model. Therefore, according to chronic cardiovascular disease, acute cardiovascular events and cardiovascular events caused by critical illness events, we screen out the relevant prognosis of serious illness (stroke, heart failure, renal failure), which is related to the prognosis of serious illness. Targeted prevention has a guiding role and practical significance according to the results of artificial intelligence analysis.
Collapse