Qualitative Analysis on Support of Hospitalization and Discharge by Text-mining Approach

2020 Fiscal Year Final Research Report

• Project/Area Number: 19K21725
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 8:Sociology and related fields
• Research Institution: Nagasaki University
• Principal Investigator: KAWASAKI Koji 長崎大学, 病院(医学系), 准教授 (60161303)
• Project Period (FY): 2019-06-28 – 2021-03-31
• Keywords: テキストマイニング / 退院支援 / 共起ネットワーク分析 / 対応分析 / コンセプトコード / 期間別分析 / 転帰別分析

Outline of Final Research Achievements

Based on the text mining of the discharge support patient records for three years from 2004, nine Concept Codes were established: 1) patient's family's concerns and wishes, 2) explanation and interview with patient's family, 3) patient's family's approval, 4) service coordination, 5) cooperation with home health care providers, 6) conference, 7) information provision, collection, and sharing, 8) cooperation with hospital staff, and 9) end-of-life. As a result of co-occurrence network analysis, "Outcome is homecare" was highly related to 4 and 5, and "Outcome is hospital transfer" was highly related to 3 and 8. "Pre-term" was highly associated with 4 and 6, and "Mid-term" and "Post-term" with 1, 2, 3, and 8. As a result of correspondence analysis, " Outcome is homecare " was highly associated with 4, 5, 6, and 9, and " Outcome is hospital transfer " was highly associated with 1, 2, 3, and 8.

Free Research Field

地域医療連携

Academic Significance and Societal Importance of the Research Achievements

退院支援はその支援内容が文章で記録されており、内容を数値化することができないため、退院支援の経時的な変化や患者の転帰（在宅医療や転院）による支援内容の評価がしにくい。そのため退院支援の内容分析が進んでいないという問題がある。そこで過去3年間の退院支援記録をテキストマイニング手法を用い、退院支援内容の経時的変化と転帰による退院支援内容の特徴を評価する事を試みた。本研究では、抽出語から９つのConcept Codeを設定し、共起ネットワーク分析と対応分析から、転帰（在宅、転院）による退院支援の特徴ならびに時期による退院支援内容の変化をConcept Codeとの関連度から評価ができる事を示した。