J. Zhong, X. Yi, Jian Wang, Z. Shao, Panpan Wang, Sen Lin
{"title":"Artificial Intelligence Based Data Governance for Chinese Electronic Health Record Analysis","authors":"J. Zhong, X. Yi, Jian Wang, Z. Shao, Panpan Wang, Sen Lin","doi":"10.5121/IJDKP.2018.8303","DOIUrl":null,"url":null,"abstract":"Electronic health record (EHR) analysis can leverage great insights to improve the quality of human healthcare. However, the low data quality problems of missing values, inconsistency, and errors in the data setseverely hinder buildingrobust machine learning models for data analysis. In this paper, we develop a methodology ofartificial intelligence (AI)-based data governance to predict the missing values or verify if the existing values are correct and what they should be when they are wrong. We demonstrate the performance of this methodology through a case study ofpatient gender prediction and verification. Experimental resultsshow that the deep learning algorithm of convolutional neural network (CNN) works very wellaccording to the testing performance measured by the quantitative metric of F1-Score, and it outperformsthe support vector machine (SVM) models with different vector representations for documents.","PeriodicalId":131153,"journal":{"name":"International Journal of Data Mining & Knowledge Management Process","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Data Mining & Knowledge Management Process","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5121/IJDKP.2018.8303","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Electronic health record (EHR) analysis can leverage great insights to improve the quality of human healthcare. However, the low data quality problems of missing values, inconsistency, and errors in the data setseverely hinder buildingrobust machine learning models for data analysis. In this paper, we develop a methodology ofartificial intelligence (AI)-based data governance to predict the missing values or verify if the existing values are correct and what they should be when they are wrong. We demonstrate the performance of this methodology through a case study ofpatient gender prediction and verification. Experimental resultsshow that the deep learning algorithm of convolutional neural network (CNN) works very wellaccording to the testing performance measured by the quantitative metric of F1-Score, and it outperformsthe support vector machine (SVM) models with different vector representations for documents.