| 設樂 一碩 | D, 中間発表 | 知能コミュニケーション | 中村 哲, 渡辺 太郎, 田中 宏季 |
|
title: Psychological Distress Estimation during Cognitive Behavior Therapy with a Virtual Agent
abstract: Cognitive behavior therapy (CBT) is a well-established mental health care technique for treating mental disorders and daily mental health care. Virtual agents, interfaces that enable face-to-face interaction and automated conversation, are expected to deliver CBT automatically. However, previous studies have not sufficiently investigated the relationship between system effectiveness and response selection based on the estimation of psychological distress (e.g., anxiety, depression). Furthermore, previous studies have not examined to estimate psychological distress during CBT. We aim to develop a virtual agent that estimates distress and selects an appropriate system response. Therefore, we propose a method to accurately estimate distress during CBT using multimodal information, including text, audio, and visual. language of the presentation: Japanese | |||
| 岩内 厚大 | M, 2回目発表 | 知能コミュニケーション | 中村 哲, 荒牧 英治, 田中 宏季 |
|
title: Toward Detection of Autism Spectrum Disorders and Schizophrenia by Eye Movement Analysis Focusing on Multiple Stimuli abstract: In today's clinical practice, the diagnosis of psychiatric disorders such as schizophrenia (Sz) and autism spectrum disorder (ASD) is made by several psychiatrists who follow diagnostic criteria and use a medical interview to make a definitive diagnosis. This process is complex, and there is a need for simple objective measures to aid in diagnosis. The relationship between objectively measurable oculomotor abnormalities and visual cognitive deficits in psychiatric disorders has been pointed out, and the possibility that oculomotor measures could serve as a diagnostic aid has been discussed. In recent years, studies have been conducted using machine learning to make more accurate predictions. Eye movement specificity during facial expression recognition has been studied extensively in the past, but modeling taking into account differences in specificity among facial expressions has not been conducted. We propose a method to detect ASD or Sz from eye movement during the Facial Emotion Identification Test (FEIT) while considering differences in eye movement due to the facial expressions presented. language of the presentation: Japanese 発表題目: 複数の刺激に着目した眼球運動解析による自閉スペクトラム症、統合失調症の検出に向けて 発表概要: 今日の臨床現場において、統合失調症（Sz）や自閉スペクトラム症（ASD）などの精神疾患の診断は、複数の精神科医によって、診断基準に従った、問診を用いて確定診断が行われる。このプロセスは複雑であり、診断を補助するような簡易な客観指標が必要とされている。精神疾患における客観的に測定可能な眼球運動異常と視覚認知障害の関係が指摘され、眼球運動測定が診断補助のひとつになりうる可能性が議論されてきた。近年では、より精度の高い予測を行うために、機械学習を用いた研究が行われている。表情認知時の眼球運動特異性を用いた疾患を予測する研究はなされているが、表情ごとの特異性の違いを考慮したモデリングは行われていない。そこで本発表では、提示された表情による眼球運動の違いを考慮しながら、表情認知課題（FEIT）中の眼球運動からASDとSzを検出する方法を提案する。 | |||
| 古賀 貴士 | M, 2回目発表 | ソーシャル・コンピューティング | 荒牧 英治, 中村 哲, 若宮 翔子 |
|
title: Construction of Error Correction Models in Electronic Medical Records
abstract: Electronic medical records (EHR), which have been introduced in recent years, have enabled comprehensive tracking of patient dynamics and have contributed to a significant improvement in the work of physicians.However, there have been reports of cases in which physicians have entered incorrect information into EHR systems, resulting in medical accidents.In this study, we aims to construct a model that can detect whether or not an abnormal input in EHRs. language of the presentation: Japanese 発表題目: 電子カルテにおける誤り訂正モデルの構築 発表概要: 近年導入が進められてきた電子化された診療録（電子カルテ）は、患者動態を網羅的に追跡を可能とし、医師の大幅な業務改善に貢献してきた．一方で，電子カルテシステムに記録する際に医師による誤入力が発生し，医療事故に発展するケースが報告されている．そこで本研究では，電子カルテに異常な記載があった際に誤入力であるか否かを検知するモデルの構築を目指す． | |||
| 安藤 晶 | M, 2回目発表 | ソーシャル・コンピューティング | 荒牧 英治, 中村 哲, 若宮 翔子, 矢田 竣太郎, 大竹 義人 |
|
title: Data-to-Text Chief Complaint Generation on Nursing Records
abstract: The nursing record is a document that tracks nursing practice. In addition to certifying what nurses have done, it is helpful to improve nursing practice by extracting expressions regarding nursing activities and patient status from its text. We designed a novel patient-status annotation scheme and created an annotated corpus consisting of 1,000 pseudo nursing records. We applied a Data-to-Text model based on patient-status entity using the corpus to generate the sentences containing the chief complaint. language of the presentation: Japanese 発表題目: 看護記録の主訴文生成 発表概要: 看護記録とは看護実践の一連の過程を記録したもので，看護実践の証明，継続性と一貫性の担保，評価および質の向上を図るために記述が義務付けられている．しかし医療人材不足が問題となっている現在，看護記録の作成は看護師を疲弊させる業務のひとつになっている． そこで本研究では看護記録業務の効率化を目的として，新しく設計した患者状態アノテーション仕様のもと疑似看護記録コーパスを作成し，患者状態表現エンティティに基づくData-to-Textモデルを用いて看護記録主訴文の生成を行う． | |||