| 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.
|
