Analyzing Sequence Pattern Variants in Sequential Pattern Mining and Its Application to Electronic Medical Record Systems

• Published in: Database and Expert Systems Applications Vol. 11707; pp. 393 - 408
• Main Authors: Le, Hieu Hanh, Yamada, Tatsuhiro, Honda, Yuichi, Kayahara, Masaaki, Kushima, Muneo, Araki, Kenji, Yokota, Haruo
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 01.01.2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Electronic medical record system; Sequence pattern variant; Sequential pattern mining
• ISBN: 9783030276171; 3030276171
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-27618-8_29

Sequential pattern mining (SPM) is widely used for data mining and knowledge discovery in various application domains, such as medicine, e-commerce, and the World Wide Web. There has been much work on improving the execution time of SPM or enriching it via considering the time interval between items in sequences. However, no study has evaluated the sequence pattern variant (SPV) that is the original sequence containing frequent patterns including variants, and studied the factors that lead to the variants. Such a study is meaningful for medical tasks such as improving the quality of a disease’s treatment method. This paper proposes methods for evaluating SPVs and understanding variant factors based on a statistical approach while considering the safety and efficiency of sequences and the relating static and dynamic information of the variants. Our proposal is confirmed to be effective by experimentally evaluating the electronic medical record system’s real dataset and feedback from medical workers.