• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 前のページに戻る

EmplifAI: Development of an Empathetic AI Chatbot to Support Cancer Follow-up Care

研究課題

研究課題/領域番号 23K17007
研究種目

若手研究

配分区分基金
審査区分 小区分62020:ウェブ情報学およびサービス情報学関連
研究機関奈良先端科学技術大学院大学

研究代表者

SHE WanJou  奈良先端科学技術大学院大学, 先端科学技術研究科, 特任助教 (40967410)

研究期間 (年度) 2023-04-01 – 2026-03-31
研究課題ステータス 交付 (2023年度)
配分額 *注記
4,290千円 (直接経費: 3,300千円、間接経費: 990千円)
2025年度: 1,950千円 (直接経費: 1,500千円、間接経費: 450千円)
2024年度: 650千円 (直接経費: 500千円、間接経費: 150千円)
2023年度: 1,690千円 (直接経費: 1,300千円、間接経費: 390千円)
キーワードEmpathy / Large Language Model / Chatbot / Cancer Care / Medical Advice
研究開始時の研究の概要

This project aims to develop EmplifAI, a chatbot to offer medical advice in an emotionally sensitive manner. We fine-tune the chatbot with conversation data from cancer centers and crowdsourcing. Afterwards, EmplifAI would be deployed for patient evaluation in a pilot study at the OICI hospital.

研究実績の概要

My first-year research aims to develop an empathetic chatbot model for providing emotionally sensitive medical advice to cancer patients. I'm fortunate to utilize emerging Large Language Models (LLMs) like ChatGPT, llama-2, and mixtral, which have significantly enhanced my original study plan with groundbreaking generative AI technology.

In summary, I've collected 280 data points on emotionally challenged medical situations and 4230 data points of empathetic dialogues to address diverse patient emotions through crowdsourcing. I've also conducted interviews with eight cancer professionals to guide empathetic chatbot development. Additionally, I've published three chatbot papers in top HCI venues (CHI and IJHCI) and secured an additional chatbot grant from the JR West-Relief Foundation.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

I'm currently exploring the best methods to fine-tune a language model or construct our Retrieval Augmented Generation (RAG) framework. After receiving predominantly positive yet cautious feedback from our interviews with medical professionals, I've decided to prioritize implementing safety mechanisms in the development of our chatbot prototype. Additionally, I have relocated to Kyoto Institute of Technology and will be submitting the ethical application through the new institution. I aim to publish the two datasets as open-access resources for the Japanese Natural Language Processing research community. The interview data will be analyzed using a thematic analysis approach and submitted to the Journal of Medical Internet Research (JMIR).

今後の研究の推進方策

After successfully developing the language model candidates and integrating them into a chatbot user interface, my next step is to engage doctors in evaluating the safety of the chatbot's responses. The criteria for assessing the safety and performance of the model will include: Scientific Consensus, Potential Harm, Evidence of Miscomprehension, Evidence of Incorrect Retrieval, Evidence of Flawed Reasoning, Inappropriate or Incorrect Content, Helpfulness of Responses, Bedside Manner, and Empathy Level. I aim to enlist up to 5 doctors to evaluate the answers generated by multiple chatbot candidates. These criteria will guide me in selecting the safest and most effective model to advance to the final stage in the third year.

報告書

(1件)
  • 2023 実施状況報告書
  • 研究成果

    (9件)

すべて 2024 2023 その他

すべて 国際共同研究 (2件) 雑誌論文 (2件) (うち国際共著 2件、 査読あり 2件、 オープンアクセス 2件) 学会発表 (3件) (うち国際学会 2件、 招待講演 1件) 備考 (2件)

  • [国際共同研究] Weill Cornell Medicine(米国)

    • 関連する報告書
      2023 実施状況報告書
  • [国際共同研究] University of Kent(英国)

    • 関連する報告書
      2023 実施状況報告書
  • [雑誌論文] “Can I be More Social with a Chatbot?”: Social Connectedness Through Interactions of Autistic Adults with a Conversational Virtual Human2024

    • 著者名/発表者名
      Xygkou Anna、Siriaraya Panote、She Wan-Jou、Covaci Alexandra、Ang Chee Siang
    • 雑誌名

      International Journal of Human-Computer Interaction

      巻: 1 号: 24 ページ: 1-18

    • DOI

      10.1080/10447318.2023.2292880

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [雑誌論文] Exploring the use of AI text-to-image generation to downregulate negative emotions in an expressive writing application2023

    • 著者名/発表者名
      Azuaje Gamar、Liew Kongmeng、Buening Rebecca、She Wan Jou、Siriaraya Panote、Wakamiya Shoko、Aramaki Eiji
    • 雑誌名

      Royal Society Open Science

      巻: 10 号: 1 ページ: 220238-220238

    • DOI

      10.1098/rsos.220238

    • 関連する報告書
      2023 実施状況報告書
    • 査読あり / オープンアクセス / 国際共著
  • [学会発表] MindTalker: Navigating the Complexities of AI-Enhanced Social Engagement for People with Early-Stage Dementia2024

    • 著者名/発表者名
      Xygkou, Anna, Chee Siang Ang, Panote Siriaraya, Jonas Kopecki, Alexandra Covaci, Eiman Kanjoand Wan-Jou She
    • 学会等名
      2024 CHI Conference on Human Factors in Computing Systems
    • 関連する報告書
      2023 実施状況報告書
    • 国際学会
  • [学会発表] The "Conversation" about Loss: Understanding How Chatbot Technology was Used in Supporting People in Grief2023

    • 著者名/発表者名
      Xygkou, Anna, Panote Siriaraya, Alexandra Covaci, Holly Gwen Prigerson, Robert Neimeyer, Chee Siang Ang, and Wan-Jou She
    • 学会等名
      2023 CHI Conference on Human Factors in Computing Systems
    • 関連する報告書
      2023 実施状況報告書
    • 国際学会
  • [学会発表] AI Augmented Medical Technology2023

    • 著者名/発表者名
      Wan-Jou She
    • 学会等名
      11th Annual Conference of Entrepreneurship and Innovation
    • 関連する報告書
      2023 実施状況報告書
    • 招待講演
  • [備考] Autistic Chatbot CHI paper

    • URL

      https://www.tandfonline.com/doi/full/10.1080/10447318.2023.2292880

    • 関連する報告書
      2023 実施状況報告書
  • [備考] Grief Chatbot CHI paper

    • URL

      https://dl.acm.org/doi/full/10.1145/3544548.3581154

    • 関連する報告書
      2023 実施状況報告書

URL: 

公開日: 2023-04-13   更新日: 2024-12-25  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi