Feature Words to Predict Long Post-Operatively Stay in Semi-structured Medical Records

電気学会 電子図書館 Verified independent store

→

カテゴリ: 国際会議論文No: PS-08グループ名: ACIS2015発行日: 2015/10/15著者名(英語): Haruka Kubo(Kyushu University), Takanori Yamashita(Kyushu University Hospital),Brendan Flanagan(Kyushu University),Yoshi fumi Wakata (Kyushu University Hospital),Naoki Nakashima(Kyushu University Hospital), Hidehisa Soejima (Saiseikai Kumamoto Hospital), Sキーワード: SVM(Support Vector Machine),\nPOMR (Problem Oriented Medical Record), SOAP, Feature Selection要約(英語): The number of medical records is increasing for the quantitative evaluation and improvement of medical process. The records are written in POMR (Problem Oriented Medical Record) format record consists of patients' subjective observation (S), objective items of test results (O), assessment, evaluation and judgement (A), future's treatment policy (P) and free description (F). The present paper applied SVM(support vector machine) to extract characteristic words to predict the patients of long post-operatively stay. Analysis of 3,840 medical records of Saiseikai Kumamoto Hospital revealed that the objective component contains the most crucial words.原稿種別: 英語PDFファイルサイズ: 730 Kバイト Show more