{"title":"ABACUS: a knowledge-based system for the interpretation of arrhythmias in long term ECG","authors":"A. Taddei, M. Niccolai, M. Emdin, C. Marchesi","doi":"10.1109/CIC.1993.378297","DOIUrl":null,"url":null,"abstract":"Describes the development of a system for the interpretation of arrhythmias in long term ECG. The architecture consists of a preprocessing module for feature extraction and qualitative description of waveforms, and of a knowledge-based module for diagnostic classification. Medical knowledge for ECG interpretation was represented by rules and objects, while forward chaining was mainly applied for inference. Contextual information related to the patient is also used for diagnosis. Classification of ECG abnormalities is performed in a number of steps by the evaluation of specific rules. Beat types as well as rhythm changes are identified. Performance of beat classification was assessed on selected records.<<ETX>>","PeriodicalId":20445,"journal":{"name":"Proceedings of Computers in Cardiology Conference","volume":"127 1","pages":"887-890"},"PeriodicalIF":0.0000,"publicationDate":"1993-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of Computers in Cardiology Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIC.1993.378297","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
Describes the development of a system for the interpretation of arrhythmias in long term ECG. The architecture consists of a preprocessing module for feature extraction and qualitative description of waveforms, and of a knowledge-based module for diagnostic classification. Medical knowledge for ECG interpretation was represented by rules and objects, while forward chaining was mainly applied for inference. Contextual information related to the patient is also used for diagnosis. Classification of ECG abnormalities is performed in a number of steps by the evaluation of specific rules. Beat types as well as rhythm changes are identified. Performance of beat classification was assessed on selected records.<>