Evaluating measures of redundancy in clinical texts

摘要: Although information redundancy has been reported as an important problem for clinicians when using electronic health records and clinical reports, measuring in text not extensively investigated. We evaluated several automated techniques to quantify the documents expert-derived reference standard consisting of outpatient documents. The technique that resulted best correlation (82%) with human ratings consisted a modified dynamic programming alignment algorithm over sliding window augmented a) lexical normalization b) stopword removal. When this method was applied overall record, we found notes increased time mean document scores individual patient appear have cyclical patterns corresponding events. These results show large amounts redundant development effective measures warrants additional investigation.