SAFE.AI: Developing and Testing an AI-based Hybrid Chatbot for Financial Empowerment in Rural Cancer Care

NCT07410689 | Not Yet Recruiting

• 1 other identifier: HCI193501
• Study Type: interventional
• Target: 60
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Cancer; Financial Toxicity

Outcome Measures

Primary Outcomes (5)

• Single-Item Helpfulness Rating

  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)

  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)

  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

  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)

  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

Secondary Outcomes (5)

• Self-reported Financial Worry

  up to 2 weeks

• Health-Related Quality of Life (QOL)

  up to 2 weeks

• Self-Efficacy for Coping with Cancer

  up to 2 weeks

• Psychosocial Distress

  up to 2 weeks

• User Engagement with SAFE.AI

  up to 2 weeks

Study Arms (2)

Rule-based Chatbot

OTHER

Participants randomized to this arm will be asked to use the rule-based chatbot.

Other: Rule-Based Chatbot

Hybrid Chatbot

OTHER

Participants randomized to this arm will be asked to use the hybrid chatbot

Other: Hybrid Chatbot

Interventions

Rule-Based Chatbot OTHER

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.

Rule-based Chatbot

Hybrid Chatbot OTHER

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.

Hybrid Chatbot

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• 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

Sponsors & Collaborators

• University of Utah: lead
• Huntsman Cancer Institute: collaborator

Study Sites (1)

Huntsman Cancer Institute/ University of Utah

Salt Lake City, Utah, 84112, United States

Location

Related Publications (35)

• 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.

  PMID: 32522832 BACKGROUND

• 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.

  PMID: 29338071 BACKGROUND

• 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.

  PMID: 32093505 BACKGROUND

• 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.

  PMID: 30475400 BACKGROUND

• 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.

  PMID: 34698839 BACKGROUND

• 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.

  PMID: 30355027 BACKGROUND

• 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.

  PMID: 30771864 BACKGROUND

• 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.

  PMID: 33108023 BACKGROUND

• 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.

  PMID: 34974507 BACKGROUND

• 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.

  PMID: 30972645 BACKGROUND

• 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.

  PMID: 34655327 BACKGROUND

• 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.

  PMID: 26384798 BACKGROUND

• 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.

  PMID: 31599949 BACKGROUND

• 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.

  PMID: 36214743 BACKGROUND

• 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.

  PMID: 38402718 BACKGROUND

• 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.

  PMID: 36925773 BACKGROUND

• 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.

  PMID: 29620814 BACKGROUND

• 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.

  PMID: 29124417 BACKGROUND

• 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.

  PMID: 32533839 BACKGROUND

• 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.

  PMID: 28590794 BACKGROUND

• 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.

  PMID: 34847056 BACKGROUND

• 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.

  PMID: 34792472 BACKGROUND

• 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.

  PMID: 31951474 BACKGROUND

• 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.

  PMID: 35224632 BACKGROUND

• 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.

  PMID: 39250153 BACKGROUND

• 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.

  PMID: 32141837 BACKGROUND

• 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.

  PMID: 32300794 BACKGROUND

• 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.

  BACKGROUND

• 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.

  PMID: 8628042 BACKGROUND

• 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.

  PMID: 20878830 BACKGROUND

• 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.

  PMID: 37644387 BACKGROUND

• 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.

  PMID: 38982408 BACKGROUND

• 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.

  PMID: 35980732 BACKGROUND

• Stanhope J. Patient Health Questionnaire-4. Occup Med (Lond). 2016 Dec;66(9):760-761. doi: 10.1093/occmed/kqw165. No abstract available.

  PMID: 27994085 BACKGROUND

• 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

  BACKGROUND

MeSH Terms

Conditions

Neoplasms; Financial Stress

Condition Hierarchy (Ancestors)

Stress, Psychological; Behavioral Symptoms; Behavior

Study Officials

• Djin Tay, PhD, RN

  Huntsman Cancer Institute/ University of Utah

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: SUPPORTIVE CARE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: December 31, 2025
• First Posted: February 13, 2026
• Study Start: May 1, 2026
• Primary Completion (Estimated): December 1, 2027
• Study Completion (Estimated): December 1, 2027
• Last Updated: May 6, 2026

Record last verified: 2026-05

Locations

US (1)