SAFE.AI：農村のがんケアにおける経済的エンパワーメントのためのAIベースハイブリッドチャットボットの開発とテスト
SAFE.AI：農村のがん治療における金融エンパワーメントのためのAIベースハイブリッドチャットボットの開発とテスト
This is a randomized, two-arm, parallel-group pilot trial investigating a new chatbot tool designed to support cancer patients and caregivers, particularly those in rural communities. Approximately 60 participants will be randomized 1:1 to interact with either a hybrid chatbot or an AI-enabled chatbot. Participants will use their assigned chatbot to obtain clear and helpful information related to insurance, travel costs, and other financial aspects of cancer care.
調査の概要
詳細な説明
Costs of cancer care will approach $246 billion by 2030, making cancer one of the most expensive health conditions for individuals. Cancer-related financial hardships negatively impacts psychological wellbeing, health-related quality of life, medication adherence, and decisions to delay or forgo care. Rural cancer patients and families have a higher prevalence of financial hardships, incur greater travel-related expenses, face unique employment and income stressors, and have lower access to specialized cancer care services and providers-- including those that support financial needs.
Few financial toxicity interventions are designed for the needs of rural cancer patients and families. While financial navigation can effectively reduce cancer patients' out-of-pocket costs, cancer programs' financial and rural patient navigation services, including at the Huntsman Cancer Institute (HCI), are overstrained. Most centers respond to financial hardships reactively rather than proactively, and programs are less equipped to assist with non-medical sources of cancer costs, such as travel and employment hardships.
To address this gap, Self-Advocacy for Financial Empowerment (SAFE) resource toolkit with a community advisory board consisting of rural cancer patients, caregivers, and healthcare stakeholders. Community-engaged research also identified the need for individualized and accessible information about financial resources and supports, stigma as a barrier to seeking help, and the time and resource-intensive nature of financial navigation that limits the penetration and reach of these essential services among rural communities impacted by cancer.
Chatbots, or conversational agents, are a type of artificial intelligence (AI) system that applies machine learning to reproduce realistic human conversations. Scripted chatbots, based on clearly defined information boundaries, offer accurate, reliable, and individualized responses to questions. Conversely, AI-based chatbots that use large language models (LLM) like GPT4, can address ambiguous, open-ended questions while continuing to preserve privacy. Chatbots facilitate individualized, chunked information that enhances complex information communication, promotes users' privacy and support needs, and addresses workforce challenges.[
GARDE-Chat, an open-source platform, has been established for health system-level risk assessment and genetic testing for hereditary cancer at HCI. GARDE-Chat supports scripted, hybrid, and AI-chatbots. Prior to this pilot test, GARDE-Chat will be used to create a chatbot designed to provide responses for financial toxicity, based on the SAFE toolkit content and verified resources to develop the scripted version of the chatbot. A large language model component of the chatbot will be incorporated for the hybrid version that will enable users to ask more complex and open-ended questions, refined with community stakeholder input.
This is a randomized, two-arm, parallel-group pilot trial investigating a new chatbot tool designed to support cancer patients and caregivers, particularly those in rural communities. Approximately 60 participants will be randomized 1:1 to interact with either a hybrid chatbot or an AI-enabled chatbot. Participants will use their assigned chatbot to obtain clear and helpful information related to insurance, travel costs, and other financial aspects of cancer care. Enrolled participants will complete three surveys (pretest, posttest, and 2-week follow-up) and interact with the chatbot prior to the posttest. Participants can interact with the chatbot between the posttest and the 2-week followup as they choose. Participants will share feedback on the usefulness, ease of use, and overall experience using the chatbot and complete pre-and posttest measures to assess preliminary efficacy for secondary outcome measures. All research activities will be done online.
研究の種類
入学 (推定)
段階
- 適用できない
連絡先と場所
研究場所
-
-
Utah
-
Salt Lake City、Utah、アメリカ、84112
- 募集
- Huntsman Cancer Institute/ University of Utah
-
コンタクト：
- Djin Tay, PhD, RN
- 電話番号：801-646-6440
- メール：Djin.Tay@nurs.utah.edu
-
主任研究者：
- Djin Tay, PhD, RN
-
-
参加基準
適格基準
就学可能な年齢
健康ボランティアの受け入れ
受講資格のある性別
説明
Inclusion Criteria:
- Adults (18 years and older)
- Cancer patients or financially responsible caregivers of cancer patients who:
- Reside in the Huntsman Cancer Institute's five-state catchment area (Utah, Idaho, Wyoming, Montana, and Nevada),
- Are able to read and write in English, and
- Live in a rural area, defined by endorsement of a residential ZIP code classified as non-metropolitan (RUCA codes 4-10) per the USDA Rural-Urban Commuting Area Codes.
Exclusion Criteria:
- Respondents who do not live within this 5-state region--The SAFE toolkit material was developed for the Huntsman Cancer Institute patient population which serves UT, ID, MT, WY, & NV
- Respondents who only speak Spanish or other exclusively non-English speaking groups--The large language model for the chatbot will be developed in the English language. As non-English language training for the chatbot is not part of the scope of this study, participants who are unable to read and write in English may not be appropriate. As such, we will not be recruiting participants who only speak Spanish or other exclusively non-English speaking groups. Future studies will include adaptation of the chatbot to other languages.
- Caregivers who are not primarily responsible for the financial aspects of patients' cancer care--The topic of financial hardship of cancer care may be less relevant for caregivers who are not financially involved in care.
- Non-rural dwelling
研究計画
研究はどのように設計されていますか？
デザインの詳細
- 主な目的：支持療法
- 割り当て：ランダム化
- 介入モデル：並列代入
- マスキング：なし（オープンラベル）
武器と介入
参加者グループ / アーム |
介入・治療 |
|---|---|
|
他の：Rule-based Chatbot
Participants randomized to this arm will be asked to use the rule-based chatbot. |
The rule-based (scripted) SAFE.ai chatbot is a guided conversational tool built to provide structured, accurate, and consistent information to rural cancer patients and caregivers experiencing cancer-related financial toxicity. This chatbot is grounded in the Self-Advocacy for Financial Empowerment (SAFE) resource toolkit, which was co-developed with a community advisory board (CAB) composed of rural patients, caregivers, nurses, and financial navigation experts across HCI's five-state catchment area. All scripted responses reflect priorities identified during qualitative needs assessment sessions, ensuring that content is culturally aligned with rural patient experiences and real-world financial challenges. The chatbot follows a rule-based decision tree. Users progress through the conversation by selecting a response from a set of fixed options displayed on-screen. This ensures that all content is clinically vetted, safe, consistent, and aligned with evidence-based practices. |
|
他の：Hybrid Chatbot
Participants randomized to this arm will be asked to use the hybrid chatbot |
The hybrid SAFE.ai chatbot builds on the existing rule-based system by integrating a large language model (LLM) layer to support more flexible, open-ended, and conversational interactions. While the rule-based chatbot provides structured conversations through predefined content, the hybrid approach allows users to ask complex or personalized questions about financial toxicity. To ensure safety and accuracy, the hybrid chatbot is not allowed to generate responses from the open internet. By combining the consistency of rule-based logic with the adaptability of an LLM, the hybrid chatbot will enable users to ask follow-up questions, describe nuanced financial situations, request clarification in their own words, and receive more tailored guidance while still ensuring adherence to SAFE content. |
この研究は何を測定していますか？
主要な結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Single-Item Helpfulness Rating
時間枠：up to 2 weeks
|
Helpfulness is assessed using a 5-point Likert-scale item with response options ranging from Very unhelpful (1) to Very helpful (5). Total scores range from a minumum of 1 to a maximum of 5, with lower scores indicating lower perceived helpfulness, and higher scores indicating greater perceived helpfulness. |
up to 2 weeks
|
|
System Usability Scale (SUS)
時間枠：up to 2 weeks
|
The SUS is a 10-item, 5 point Likert scale (0 = strongly disagree, 5 = strongly agree). Total scores range from a minimum of 0 to a maximum of 100, with lower values indicating less usability and higher values indicating higher usability. |
up to 2 weeks
|
|
Acceptability of Intervention Measure (AIM)
時間枠：up to 2 weeks
|
The AIM is a 4-item, 5-point Likert scale (1 = strongly disagree, 5 = strongly agree). Total scores range from a minimum of 4 a maximum of 20, with lower values indicating lower acceptability and higher values indicating higher acceptability. |
up to 2 weeks
|
|
Chatbot User Satisfaction (CUS) - Satisfaction Subscale
時間枠：up to 2 weeks
|
The Satisfaction subscale of the CUS measure is a 5 item Likert-scale ( 1 = strongly disagree, 5 = strongly agree). Total scores range from a minimum of 5 to a maximum of 25, with lower values indicating lower user satisfaction, and higher values indicating higher satisfaction. |
up to 2 weeks
|
|
Trust in Automated Systems Test (TOAST)
時間枠：up to 2 weeks
|
The TOAST is a 9-item 7-point Likert scale (1 = strongly disagree, 7 = strongly agree). Total scores range from a minimum of 9 to a maximum of 63, with lower values indicating lower trust, and higher values indicating higher trust. |
up to 2 weeks
|
二次結果の測定
結果測定 |
メジャーの説明 |
時間枠 |
|---|---|---|
|
Self-reported Financial Worry
時間枠：up to 2 weeks
|
Financial Worry will be assessed by the COST (COmprehensive Score for financial Toxicity) assessment. COST is a 12-item, 5-point Likert scale (0=Not at All to 4 =Very Much). Total scores range from a minimum of 0 to a maximum of 44, with lower scores indicating worse Financial Well-Being and higher scores indicating better Financial Well-Being. This outcome measure will report mean COST score. |
up to 2 weeks
|
|
Health-Related Quality of Life (QOL)
時間枠：up to 2 weeks
|
Health-related quality of life will be assessed with the 36-item short-form Health Survey (SF-36). The SF-36 has two subscales, the Physical Component Summary (PCS) and the Mental Component Summary (MCS). Each subscale ranges from 0-100, with lower scores indicating worse QOL and higher scores indicating better QOL. This outcome measure will report the mean PCS and MCS scores. |
up to 2 weeks
|
|
Self-Efficacy for Coping with Cancer
時間枠：up to 2 weeks
|
Self-efficacy for coping with cancer will be assessed with the Cancer Behavior Inventory-Brief Version (CBI-B) questionnaire. CBI-B is a 12-item, 9-point Likert scale (1=Not at All Confident to 9=Totally Confident). Total CBI-B scores range from 9 to 108, with lower scores indicating worse self-efficacy and higher scores indicating better self-efficacy. |
up to 2 weeks
|
|
Psychosocial Distress
時間枠：up to 2 weeks
|
Psychosocial distress will be measured by the Patient Health Questionnaire-4 (PHQ-4). PHQ-4 is a 4-item, 4-point Likert scale (0 = Not at All to 3 = Nearly every day). Total PHQ-4 scores range from 0 to 12, with lower scores indicating less psychosocial distress and higher scores indicating more severe psychosocial distress. |
up to 2 weeks
|
|
User Engagement with SAFE.AI
時間枠：up to 2 weeks
|
User engagement with the SAFE.AI will be assessed using an engagement instrument developed for evaluating AI chatbots in a posttest survey. |
up to 2 weeks
|
協力者と研究者
スポンサー
捜査官
- 主任研究者：Djin Tay, PhD, RN、Huntsman Cancer Institute
出版物と役立つリンク
一般刊行物
- Ware J Jr, Kosinski M, Keller SD. A 12-Item Short-Form Health Survey: construction of scales and preliminary tests of reliability and validity. Med Care. 1996 Mar;34(3):220-33. doi: 10.1097/00005650-199603000-00003.
- Heitzmann CA, Merluzzi TV, Jean-Pierre P, Roscoe JA, Kirsh KL, Passik SD. Assessing self-efficacy for coping with cancer: development and psychometric analysis of the brief version of the Cancer Behavior Inventory (CBI-B). Psychooncology. 2011 Mar;20(3):302-12. doi: 10.1002/pon.1735.
- Yezefski T, Steelquist J, Watabayashi K, Sherman D, Shankaran V. Impact of trained oncology financial navigators on patient out-of-pocket spending. Am J Manag Care. 2018 Mar;24(5 Suppl):S74-S79.
- Hyzy M, Bond R, Mulvenna M, Bai L, Dix A, Leigh S, Hunt S. System Usability Scale Benchmarking for Digital Health Apps: Meta-analysis. JMIR Mhealth Uhealth. 2022 Aug 18;10(8):e37290. doi: 10.2196/37290.
- Zahnd WE, Davis MM, Rotter JS, Vanderpool RC, Perry CK, Shannon J, Ko LK, Wheeler SB, Odahowski CL, Farris PE, Eberth JM. Rural-urban differences in financial burden among cancer survivors: an analysis of a nationally representative survey. Support Care Cancer. 2019 Dec;27(12):4779-4786. doi: 10.1007/s00520-019-04742-z. Epub 2019 Apr 10.
- Chavez-Yenter D, Kimball KE, Kohlmann W, Lorenz Chambers R, Bradshaw RL, Espinel WF, Flynn M, Gammon A, Goldberg E, Hagerty KJ, Hess R, Kessler C, Monahan R, Temares D, Tobik K, Mann DM, Kawamoto K, Del Fiol G, Buys SS, Ginsburg O, Kaphingst KA. Patient Interactions With an Automated Conversational Agent Delivering Pretest Genetics Education: Descriptive Study. J Med Internet Res. 2021 Nov 18;23(11):e29447. doi: 10.2196/29447.
- Del Fiol G, Kohlmann W, Bradshaw RL, Weir CR, Flynn M, Hess R, Schiffman JD, Nanjo C, Kawamoto K. Standards-Based Clinical Decision Support Platform to Manage Patients Who Meet Guideline-Based Criteria for Genetic Evaluation of Familial Cancer. JCO Clin Cancer Inform. 2020 Jan;4:1-9. doi: 10.1200/CCI.19.00120.
- Bradshaw RL, Kawamoto K, Kaphingst KA, Kohlmann WK, Hess R, Flynn MC, Nanjo CJ, Warner PB, Shi J, Morgan K, Kimball K, Ranade-Kharkar P, Ginsburg O, Goodman M, Chambers R, Mann D, Narus SP, Gonzalez J, Loomis S, Chan P, Monahan R, Borsato EP, Shields DE, Martin DK, Kessler CM, Del Fiol G. GARDE: a standards-based clinical decision support platform for identifying population health management cohorts. J Am Med Inform Assoc. 2022 Apr 13;29(5):928-936. doi: 10.1093/jamia/ocac028.
- Mariotto AB, Enewold L, Zhao J, Zeruto CA, Yabroff KR. Medical Care Costs Associated with Cancer Survivorship in the United States. Cancer Epidemiol Biomarkers Prev. 2020 Jul;29(7):1304-1312. doi: 10.1158/1055-9965.EPI-19-1534. Epub 2020 Jun 10.
- Carrera PM, Kantarjian HM, Blinder VS. The financial burden and distress of patients with cancer: Understanding and stepping-up action on the financial toxicity of cancer treatment. CA Cancer J Clin. 2018 Mar;68(2):153-165. doi: 10.3322/caac.21443. Epub 2018 Jan 16.
- Lyman GH, Kuderer N. Financial Toxicity, Financial Abuse, or Financial Torture: Let's Call It What It is! Cancer Invest. 2020 Mar;38(3):139-142. doi: 10.1080/07357907.2020.1735084. Epub 2020 Mar 4. No abstract available.
- Pisu M, Henrikson NB, Banegas MP, Yabroff KR. Costs of cancer along the care continuum: What we can expect based on recent literature. Cancer. 2018 Nov 1;124(21):4181-4191. doi: 10.1002/cncr.31643. Epub 2018 Oct 17.
- Yabroff KR, Mariotto A, Tangka F, Zhao J, Islami F, Sung H, Sherman RL, Henley SJ, Jemal A, Ward EM. Annual Report to the Nation on the Status of Cancer, Part 2: Patient Economic Burden Associated With Cancer Care. J Natl Cancer Inst. 2021 Nov 29;113(12):1670-1682. doi: 10.1093/jnci/djab192.
- Knight TG, Deal AM, Dusetzina SB, Muss HB, Choi SK, Bensen JT, Williams GR. Financial Toxicity in Adults With Cancer: Adverse Outcomes and Noncompliance. J Oncol Pract. 2018 Oct 24:JOP1800120. doi: 10.1200/JOP.18.00120. Online ahead of print.
- Allcott N, Dunham L, Levy D, Carr J, Stitzenberg K. Financial burden amongst cancer patients treated with curative intent surgery alone. Am J Surg. 2019 Sep;218(3):452-456. doi: 10.1016/j.amjsurg.2019.01.033. Epub 2019 Jan 31.
- Williams CP, Gallagher KD, Deehr K, Aswani MS, Azuero A, Daniel CL, Ford EW, Ingram SA, Balch AJ, Rocque GB. Quantifying treatment preferences and their association with financial toxicity in women with breast cancer. Cancer. 2021 Feb 1;127(3):449-457. doi: 10.1002/cncr.33287. Epub 2020 Oct 27.
- Belcher SM, Lee H, Nguyen J, Curseen K, Lal A, Zarrabi AJ, Gantz L, Rosenzweig MQ, Hill JL, Yeager KA. Financial Hardship and Quality of Life Among Patients With Advanced Cancer Receiving Outpatient Palliative Care: A Pilot Study. Cancer Nurs. 2023 Jan-Feb 01;46(1):3-13. doi: 10.1097/NCC.0000000000001052. Epub 2021 Dec 31.
- Petermann V, Zahnd WE, Vanderpool RC, Eberth JM, Rohweder C, Teal R, Vu M, Stradtman L, Frost E, Trapl E, Koopman Gonzalez S, Vu T, Ko LK, Cole A, Farris PE, Shannon J, Lee J, Askelson N, Seegmiller L, White A, Edward J, Davis M, Wheeler SB. How cancer programs identify and address the financial burdens of rural cancer patients. Support Care Cancer. 2022 Mar;30(3):2047-2058. doi: 10.1007/s00520-021-06577-z. Epub 2021 Oct 16.
- Charlton M, Schlichting J, Chioreso C, Ward M, Vikas P. Challenges of Rural Cancer Care in the United States. Oncology (Williston Park). 2015 Sep;29(9):633-40.
- Spencer JC, Rotter JS, Eberth JM, Zahnd WE, Vanderpool RC, Ko LK, Davis MM, Troester MA, Olshan AF, Wheeler SB. Employment Changes Following Breast Cancer Diagnosis: The Effects of Race and Place. J Natl Cancer Inst. 2020 Jun 1;112(6):647-650. doi: 10.1093/jnci/djz197.
- Kent EE, Lee S, Asad S, Dobbins EE, Aimone EV, Park EM. "If I wasn't in a rural area, I would definitely have more support": social needs identified by rural cancer caregivers and hospital staff. J Psychosoc Oncol. 2023;41(4):393-410. doi: 10.1080/07347332.2022.2129547. Epub 2022 Oct 10.
- Zhang M, Wang X, Shao M, Li T, Guo S, Yang Y, Yu L, Bin M, Li D, Zhou H, Yao L, Chen C, Wang T. Financial toxicity of informal caregivers of colorectal cancer patients: A cross-sectional study. Eur J Oncol Nurs. 2024 Apr;69:102519. doi: 10.1016/j.ejon.2024.102519. Epub 2024 Feb 9.
- Crabtree-Ide C, Sevdalis N, Bellohusen P, Constine LS, Fleming F, Holub D, Rizvi I, Rodriguez J, Shayne M, Termer N, Tomaszewski K, Noyes K. Strategies for Improving Access to Cancer Services in Rural Communities: A Pre-implementation Study. Front Health Serv. 2022 Mar 14;2:818519. doi: 10.3389/frhs.2022.818519. eCollection 2022.
- Spencer JC, Samuel CA, Rosenstein DL, Reeder-Hayes KE, Manning ML, Sellers JB, Wheeler SB. Oncology navigators' perceptions of cancer-related financial burden and financial assistance resources. Support Care Cancer. 2018 Apr;26(4):1315-1321. doi: 10.1007/s00520-017-3958-3. Epub 2017 Nov 9.
- de Moor JS, Kent EE, McNeel TS, Virgo KS, Swanberg J, Tracy JK, Banegas MP, Han X, Qin J, Yabroff KR. Employment Outcomes Among Cancer Survivors in the United States: Implications for Cancer Care Delivery. J Natl Cancer Inst. 2021 May 4;113(5):641-644. doi: 10.1093/jnci/djaa084.
- Sherman DE. Transforming Practices Through the Oncology Care Model: Financial Toxicity and Counseling. J Oncol Pract. 2017 Aug;13(8):519-522. doi: 10.1200/JOP.2017.023655. Epub 2017 Jun 7. No abstract available.
- Xu L, Sanders L, Li K, Chow JCL. Chatbot for Health Care and Oncology Applications Using Artificial Intelligence and Machine Learning: Systematic Review. JMIR Cancer. 2021 Nov 29;7(4):e27850. doi: 10.2196/27850.
- Kaphingst KA, Kohlmann WK, Lorenz Chambers R, Bather JR, Goodman MS, Bradshaw RL, Chavez-Yenter D, Colonna SV, Espinel WF, Everett JN, Flynn M, Gammon A, Harris A, Hess R, Kaiser-Jackson L, Lee S, Monahan R, Schiffman JD, Volkmar M, Wetter DW, Zhong L, Mann DM, Ginsburg O, Sigireddi M, Kawamoto K, Del Fiol G, Buys SS. Uptake of Cancer Genetic Services for Chatbot vs Standard-of-Care Delivery Models: The BRIDGE Randomized Clinical Trial. JAMA Netw Open. 2024 Sep 3;7(9):e2432143. doi: 10.1001/jamanetworkopen.2024.32143.
- Ta V, Griffith C, Boatfield C, Wang X, Civitello M, Bader H, DeCero E, Loggarakis A. User Experiences of Social Support From Companion Chatbots in Everyday Contexts: Thematic Analysis. J Med Internet Res. 2020 Mar 6;22(3):e16235. doi: 10.2196/16235.
- Hazarika I. Artificial intelligence: opportunities and implications for the health workforce. Int Health. 2020 Jul 1;12(4):241-245. doi: 10.1093/inthealth/ihaa007.
- De Souza JA, Wroblewski K, Proussaloglou E, Nicholson L, Hantel A, Wang Y. Validation of a financial toxicity (FT) grading system. American Society of Clinical Oncology; 2017.
- Hamm RF, Levine LD, Szymczak JE, Parry S, Srinivas SK, Beidas RS. An innovative sequential mixed-methods approach to evaluating clinician acceptability during implementation of a standardized labor induction protocol. BMC Med Res Methodol. 2023 Aug 29;23(1):195. doi: 10.1186/s12874-023-02010-7.
- Watkins JM, Brunnemer JE, Heeter KN, Medellin AM, Churchill WC, Goss JM, Hobson JM, Werner NE, Weaver RG, Kercher VMM, Kercher KA. Evaluating the feasibility and acceptability of a co-designed physical activity intervention for rural middle schoolers: a pilot study. BMC Public Health. 2024 Jul 9;24(1):1830. doi: 10.1186/s12889-024-19356-2.
- Stanhope J. Patient Health Questionnaire-4. Occup Med (Lond). 2016 Dec;66(9):760-761. doi: 10.1093/occmed/kqw165. No abstract available.
- Møller CG, Ang KE, Bongiovanni MDL, Khalid MS, Wu J. Metrics of success: evaluating user satisfaction in AI chatbots. In: Proceedings of the 8th International Conference on Advances in Artificial Intelligence (ICAAI 2024). Association for Computing Machinery; 2025:168-173. doi:10.1145/3704137.3704182
研究記録日
主要日程の研究
研究開始 (推定)
一次修了 (推定)
研究の完了 (推定)
試験登録日
最初に提出
QC基準を満たした最初の提出物
最初の投稿 (実際)
学習記録の更新
投稿された最後の更新 (実際)
QC基準を満たした最後の更新が送信されました
最終確認日
詳しくは
この情報は、Web サイト clinicaltrials.gov から変更なしで直接取得したものです。研究の詳細を変更、削除、または更新するリクエストがある場合は、register@clinicaltrials.gov。 までご連絡ください。 clinicaltrials.gov に変更が加えられるとすぐに、ウェブサイトでも自動的に更新されます。