Construction of the integrated multicentre discharge summary database

2014 Fiscal Year Final Research Report

• Project/Area Number: 24300098
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Library and information science/Humanistic social informatics
• Research Institution: Chiba University
• Principal Investigator: SUZUKI Takahiro 千葉大学, 医学部附属病院, 准教授 (40323422)
• Co-Investigator(Renkei-kenkyūsha): DOI Shunsuke 千葉大学, 医学部附属病院, 助教 (90639072) ; TAKASAKI Mitsuhiro 佐賀大学, 医学部附属病院, 准教授 (70236206) ; TSUMOTO Shusaku 島根大学, 医学部附属病院, 教授 (10251555) ; HATAKEYAMA Yutaka 高知大学, 教育研究部医療学系, 准教授 (00376956) ; HONDA Masayuki 長崎大学, 医歯(薬)学総合研究科, 教授 (10143306) ; MATSUMURA Yasushi 大阪大学, 医学部附属病院, 教授 (90252642) ; YOKOI Hideto 香川大学, 医学部附属病院, 教授 (50403788) ; TAKABAYASHI Katsuhiko 千葉大学, 医学部附属病院, 教授 (90188079)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 退院時サマリー / テキストマイニング / 多施設共同研究

Outline of Final Research Achievements

We performed the multi-year project to collect discharge summary from multiple hospitals and made the big text database to built a common document vector space, and developed various application. We extracted 243,907 discharge summaries from seven hospitals (Chiba University hospital, Nagasaki University hospital, Kagawa University hospital, Osaka University hospital, Kochi University hospital, Saga University hospital and St. Luke's International Hospital). There was a difference in term structure and number of terms between the hospitals, however the differences by disease were similar. We built the vector space using TF-IDF method. We performed cross-match analysis of DPC selection among seven hospitals. About 80% cases were correctly matched. The use of model data of other hospitals reduced selection rate to around 10%, however, integrated model data from all hospitals restore the selection rate.

Free Research Field

医療情報学