Therapist feedback and implications on adoption of an artificial intelligence-based co-facilitator for online cancer support groups: mixed methods single-arm usability study
Open accessPublished version of a preprint
Abstract
Background: The recent onset of the COVID-19 pandemic and the social distancing requirement have created an increased demand for virtual support programs. Advances in artificial intelligence (AI) may offer novel solutions to management challenges such as the lack of emotional connections within virtual group interventions. Using typed text from online support groups, AI can help identify the potential risk of mental health concerns, alert group facilitator(s), and automatically recommend tailored resources while monitoring patient outcomes. Objective: The aim of this mixed methods, single-arm study was to evaluate the feasibility, acceptability, validity, and reliability of an AI-based co-facilitator (AICF) among CancerChatCanada therapists and participants to monitor online support group participants’ distress through a real-time analysis of texts posted during the support group sessions. Specifically, AICF (1) generated participant profiles with discussion topic summaries and emotion trajectories for each session, (2) identified participant(s) at risk for increased emotional distress and alerted the therapist for follow-up, and (3) automatically suggested tailored recommendations based on participant needs. Online support group participants consisted of patients with various types of cancer, and the therapists were clinically trained social workers. Methods: Our study reports on the mixed methods evaluation of AICF, including therapists’ opinions as well as quantitative measures. AICF’s ability to detect distress was evaluated by the patient's real-time emoji check-in, the Linguistic Inquiry and Word Count software, and the Impact of Event Scale-Revised. Results: Although quantitative results showed only some validity of AICF’s ability in detecting distress, the qualitative results showed that AICF was able to detect real-time issues that are amenable to treatment, thus allowing therapists to be more proactive in supporting every group member on an individual basis. However, therapists are concerned about the ethical liability of AICF’s distress detection function. Conclusions: Future works will look into wearable sensors and facial cues by using videoconferencing to overcome the barriers associated with text-based online support groups. International Registered Report Identifier (IRRID): RR2-10.2196/21453
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI-based cofacilitators for online cancer support groups provide targeted emotional support for both patients and their caregivers in response to the detection of emotional distress.
“AI-based cofacilitators for online cancer support groups were shown to provide targeted emotional support for both patients and their caregivers in response to the detection of emotional distress [16].”
From Empathic AI for Patient-Centered Cancer Care: A Scoping Review of Patient Navigation, Support, and Clinical Practice (2026) · cites this paper as [16]
The Introduction describes an AI co-facilitator that detects distress, alerts therapists, and suggests tailored resources. The Results (Focus Group Findings; page unavailable) say therapists used its warnings to provide timely support to distressed patients. The study does not show the AI itself providing emotional support, and its evaluated participants were patients, not caregivers. (LLM, conf=0.88)
Experimental — accuracy not yet measuredAI can be used to detect distress and other emotions.
“AI can, therefore, be used to detect distress and other emotions as shown by the results of using an AI-based therapy group cofacilitator [16]”
From Empathic AI for Patient-Centered Cancer Care: A Scoping Review of Patient Navigation, Support, and Clinical Practice (2026) · cites this paper as [16]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods
Tausczik, Y. R., & Pennebaker, J. W. (2010) · Journal of Language and Social Psychology · doi:10.1177/0261927x09351676 · Cited by 5,774 · see citing works
An Empirical Evaluation of the System Usability Scale
Bangor, A., Kortum, P. T., & Miller, J. T. (2008) · International Journal of Human–Computer Interaction · doi:10.1080/10447310802205776 · Cited by 5,181 · see citing works
The Impact of Event Scale: Revised
Weiss, D. S. (2007) · Springer eBooks · doi:10.1007/978-0-387-70990-1_10 · Cited by 3,009 · see citing works
Crawford, J. R., & Henry, J. D. (2004) · British Journal of Clinical Psychology · doi:10.1348/0144665031752934 · Cited by 2,957 · cited 1× · see citing works
“The AICF development details are shown in Multimedia Appendix 1 [6-25].”
Focus-group interview and data analysis
Rabiee, F. (2004) · Proceedings of The Nutrition Society · doi:10.1079/pns2004399 · Cited by 2,050 · see citing works
Sentiment Analysis and Opinion Mining
Liu, B. (2012) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-02145-9 · Cited by 1,872 · see citing works
Cohesion and Performance in Groups: A Meta-Analytic Clarification of Construct Relations.
Beal, D. J., Cohen, R. R., Burke, M. J., & McLendon, C. L. (2003) · Journal of Applied Psychology · doi:10.1037/0021-9010.88.6.989 · Cited by 1,321 · see citing works
The Theory and Practice of Group Psychotherapy
Fidler, J. W. (1976) · International Journal of Group Psychotherapy · doi:10.1080/00207284.1976.11492282 · Cited by 1,190 · see citing works
Understanding receiver operating characteristic (ROC) curves
Fan, J., Upadhye, S., & Worster, A. (2006) · Canadian Journal of Emergency Medicine · doi:10.1017/s1481803500013336 · Cited by 843 · see citing works
The Use of Facebook in Recruiting Participants for Health Research Purposes: A Systematic Review
Whitaker, C., Stevelink, S. A. M., & Fear, N. T. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.7071 · Cited by 731 · see citing works
Requirements for Minimum Sample Size for Sensitivity and Specificity Analysis
Bujang, M. A. (2016) · JOURNAL OF CLINICAL AND DIAGNOSTIC RESEARCH · doi:10.7860/jcdr/2016/18129.8744 · Cited by 627 · see citing works
Measuring emotional expression with the Linguistic Inquiry and Word Count.
Kahn, J., Tobin, R. M., Massey, A. E., & Anderson, J. (2007) · American Journal of Psychology · doi:10.2307/20445398 · Cited by 555 · see citing works
Lee, E., Torous, J. B., Choudhury, M. D., Depp, C. A., Graham, S. A., Kim, H., Paulus, M. P., Krystal, J. H., & Jeste, D. V. (2021) · Biological Psychiatry Cognitive Neuroscience and Neuroimaging · doi:10.1016/j.bpsc.2021.02.001 · Cited by 477 · see citing works
Can seeking happiness make people unhappy? Paradoxical effects of valuing happiness.
Mauss, I. B., Tamir, M., Anderson, C. L., & Savino, N. S. (2011) · Emotion · doi:10.1037/a0022010 · Cited by 399 · see citing works
Development and validation of the Counselor Activity Self-Efficacy Scales.
Lent, R. W., Hill, C. E., & Hoffman, M. A. (2003) · Journal of Counseling Psychology · doi:10.1037/0022-0167.50.1.97 · Cited by 341 · see citing works
Virtual care use before and during the COVID-19 pandemic: A repeated cross-sectional study
Bhatia, R. S., Chu, C., Pang, A., Tadrous, M., Stamenova, V., & Cram, P. (2021) · CMAJ Open · doi:10.9778/cmajo.20200311 · Cited by 272 · see citing works
Ford, B. Q., Lam, P., John, O. P., & Mauss, I. B. (2018) · Journal of Personality and Social Psychology · doi:10.1037/pspp0000157 · Cited by 264 · cited 2× · see citing works
“This pattern can occur in both text-based and in-person groups and influence group participants to feel the need to remain positive to mask their negative feelings [29,34].”
Management of distress in cancer patients.
Holland, J. C., & Alici, Y. (2010) · PubMed · Cited by 164 · see citing works
Using Peer Support to Strengthen Mental Health During the COVID-19 Pandemic: A Review
Suresh, R., Alam, A., & Karkossa, Z. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.714181 · Cited by 146 · see citing works
Osborne, R. H., Elsworth, G. R., Sprangers, M. A. G., Oort, F. J., & Hopper, J. L. (2004) · Quality of Life Research · doi:10.1023/b:qure.0000015292.56268.e7 · Cited by 119 · see citing works
The language of well-being: Tracking fluctuations in emotion experience through everyday speech.
Sun, J., Schwartz, H. A., Son, Y., Kern, M. L., & Vazire, S. (2019) · Journal of Personality and Social Psychology · doi:10.1037/pspp0000244 · Cited by 116 · see citing works
Norgeot, B., Muenzen, K., Peterson, T. A., Fan, X., Glicksberg, B. S., Schenk, G., Rutenberg, E., Oskotsky, B., Sirota, M., Yazdany, J., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0258-y · Cited by 115 · see citing works
Meijer, R. R., de Vries, R. M., & van Bruggen, V. (2011) · Psychological Assessment · doi:10.1037/a0021292 · Cited by 106 · see citing works
The lay assessment of subclinical depression in daily life.
Mehl, M. R. (2006) · Psychological Assessment · doi:10.1037/1040-3590.18.3.340 · Cited by 105 · see citing works
Analysis of polarity information in medical text.
Niu, Y., Zhu, X., Li, J., & Hirst, G. (2005) · PubMed Central · Cited by 87 · see citing works
Self-citationUsing wearable technology to predict health outcomes: a literature review
Burnham, J. P., Lu, C., Yaeger, L., Bailey, T. C., & Kollef, M. H. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy082 · Cited by 84 · see citing works
Telemental Health Use in the COVID-19 Pandemic: A Scoping Review and Evidence Gap Mapping
Abraham, A., Jithesh, A., Doraiswamy, S., Al-Khawaga, N., Mamtani, R., & Cheema, S. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.748069 · Cited by 81 · see citing works
“What concerns me is…” Expression of emotion by advanced cancer patients during outpatient visits
Anderson, W. G., Alexander, S. C., Rodriguez, K. L., Jeffreys, A. S., Olsen, M. K., Pollak, K. I., Tulsky, J. A., & Arnold, R. M. (2007) · Supportive Care in Cancer · doi:10.1007/s00520-007-0350-8 · Cited by 78 · see citing works
Factor structure and validity of the Therapeutic Factors Inventory–Short Form.
Joyce, A. S., MacNair-Semands, R., Tasca, G. A., & Ogrodniczuk, J. S. (2011) · Group Dynamics: Theory, Research, and Practice · doi:10.1037/a0024677 · Cited by 67 · see citing works
Sadasivam, R. S., Cutrona, S. L., Kinney, R. L., Marlin, B. M., Mazor, K. M., Lemon, S. C., & Houston, T. K. (2016) · Journal of Medical Internet Research · doi:10.2196/jmir.4448 · Cited by 48 · see citing works
Creed, T. A., Kuo, P. B., Oziel, R., Reich, D., Thomas, M. L., O’Connor, S., Imel, Z. E., Hirsch, T., Narayanan, S. S., & Atkins, D. C. (2021) · Administration and Policy in Mental Health and Mental Health Services Research · doi:10.1007/s10488-021-01167-x · Cited by 33 · see citing works
Leung, Y. W., Wouterloot, E., Adikari, A., Hirst, G., Silva, D. D., Wong, J., Bender, J. L., Gancarz, M., Gratzer, D., Alahakoon, D., et al. (2021) · JMIR Research Protocols · doi:10.2196/21453 · Cited by 29 · see citing works
Self-citationBandaragoda, T., Ranasinghe, W., Adikari, A., de Silva, D., Lawrentschuk, N., Alahakoon, D., Persad, R., & Bolton, D. (2018) · Annals of Surgical Oncology · doi:10.1245/s10434-018-6372-2 · Cited by 29 · see citing works
Self-citationTonsing, K. N., & Vungkhanching, M. (2017) · Social Work in Health Care · doi:10.1080/00981389.2017.1402844 · Cited by 25 · see citing works
Leung, Y. W., Park, B., Heo, R., Adikari, A., Chackochan, S., Wong, J., Alie, E., Gancarz, M., Kacala, M., Hirst, G., et al. (2022) · JMIR Cancer · doi:10.2196/35893 · Cited by 23 · see citing works
Self-citationWearables and the Quantified Self: Systematic Benchmarking of Physiological Sensors
Sagl, G., Resch, B., Petutschnig, A., Kyriakou, K., Liedlgruber, M., & Wilhelm, F. H. (2019) · Sensors · doi:10.3390/s19204448 · Cited by 22 · see citing works
Human Factors: Bridging Artificial Intelligence and Patient Safety
Choudhury, A., & Asan, O. (2020) · Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care · doi:10.1177/2327857920091007 · Cited by 17 · see citing works
Patient-reported outcomes, emoji, and activity measured on the Apple Watch in cancer patients.
Thompson, C. A., Yost, K. J., Bartz, A., Kumar, A., Ruddy, K. J., Stan, D. L., Uhm, J. H., Warsame, R. M., Witzig, T. E., Novotny, P. J., et al. (2018) · Journal of Clinical Oncology · doi:10.1200/jco.2018.36.15_suppl.6501 · Cited by 12 · see citing works
Professional Online Support Group Facilitators: Guarantors of Maximal Group Utility
Male, D. A., Fergus, K. D., & Stephen, J. E. (2016) · International Journal of Group Psychotherapy · doi:10.1080/00207284.2016.1240587 · Cited by 7 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [14]Arnold MB Review of the emotions: facts, theories and a new model The American Journal of Psychology 2023-03-21 https://www.jstor.org/stable/1421040?origin=crossref
Cited by
Sorted by citations
Artificial intelligence across the cancer care continuum
Riaz, I. B., Khan, M. A., & Osterman, T. J. (2025) · Cancer · doi:10.1002/cncr.70050 · Cited by 40 · see citing works
Insights From Art Therapists on Using AI-Generated Art in Art Therapy: Mixed Methods Study
Shojaei, F., Shojaei, F., Torres, J. O., & Shih, P. C. (2024) · JMIR Formative Research · doi:10.2196/63038 · Cited by 36 · see citing works
Vakili, S. T., Haywood, D., Kirk, D., Abdou, A. M., Gopalakrishnan, R., Sadeghi, S., Guedes, H., Tan, C. J., Thamm, C., Bernard, R., et al. (2024) · JCO Clinical Cancer Informatics · doi:10.1200/cci.24.00119 · Cited by 30 · see citing works
Leung, Y. W., So, J., Sidhu, A., Asokan, V., Gancarz, M., Gajjar, V. B., Patel, A., Li, J. M., Kwok, D. K. S., Nadler, M. B., et al. (2025) · Current Oncology · doi:10.3390/curroncol32030145 · Cited by 8 · see citing works
Self-citationWhite, B. M., Aitken, G. L., Zink, J. A., Kheirkhah Rahimabad, P., Kumsa, F. A., Hashtarkhani, S., Rashid, R., Kheirinejad, S., Girdwood, T., Brett, C. L., et al. (2026) · JMIR Cancer · doi:10.2196/82336 · Cited by 2 · see citing works
“For example, AI-based cofacilitators for online cancer support groups were shown to provide targeted emotional support for both patients and their caregivers in response to the detection of emotional distress [16].”
Ferrarini, F., & Leonelli, S. (2025) · Industrial Management & Data Systems · doi:10.1108/imds-05-2025-0661 · Cited by 3 · see citing works
Artificial Intelligence-generated Psychological Counseling for Cancer Patients
Mahendiran, N., Sheik Mohamed, M. I., & Saravanan, S. (2025) · Current Psychiatry Research and Reviews · doi:10.2174/0126660822338819250214064950 · Cited by 1 · see citing works
How Cancer Online Support Groups Work, for Whom, and in What Circumstances: Realist Review
Bender, J. L., Scruton, S., Wong, G., Squires, L. R., Babinski, S., Englesakis, M. F., Cyr, A. B., POTTS, H. W. W., Tricco, A. C., Wassersug, R. J., et al. (2026) · Journal of Medical Internet Research · doi:10.2196/77445 · Cited by 1 · see citing works
Self-citationShalbaf, N., Ahmadi, N., Nasirimehr, K., & Emami, A. (2025) · InfoScience Trends · doi:10.61186/ist.202502.04.06 · Cited by 1 · see citing works
Bires, J. L., Franklin, E. F., Nelson, K., Bonesteel, K., & Flora, D. B. (2025) · AI in Precision Oncology · doi:10.1089/aipo.2025.0007 · Cited by 1 · see citing works
When AI Meets Art Therapy: Evaluating AI-Generated Art Through Art Therapists Insights (Preprint)Preprint
Shojaei, F., Shojaei, F., Torres, J. O., & Shih, P. C. (2024) · doi:10.2196/preprints.63038
A staged, human–computer interaction-informed model for designing art therapy digital interventions
Shojaei, F., Shojaei, F., Seidman, M., & Shih, P. C. (2026) · International Journal of Art Therapy · doi:10.1080/17454832.2026.2700253
- Authors
- Leung, Y. W., Ng, S., Duan, L., Lam, C., Chan, K., Gancarz, M., Rennie, H., Trachtenberg, L., Chan, K. P., Adikari, A., Fang, L., Gratzer, D., Hirst, G., Wong, J., & Esplen, M. J.
- Affiliations
- University Health Network (CA)
- BC Cancer Agency (CA)
- La Trobe University (AU)
- University of Toronto (CA)
- Centre for Addiction and Mental Health (CA)
- Corresponding author
- Leung, Yvonne W
- ORCID
- Venue
- JMIR Cancer
- Publisher
- JMIR Publications Inc.
- Published
- 2023-06-09
- Volume
- 9
- Pages
- e40113
- ISSN
- 2369-1999 (ISSN-L)
- PMC
- PMC10334721
- OpenAlex
- W4322711856
- Cited by
- 12
- References
- 39
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 3
- FWCI
- 3.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Cancer (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by)
- TSpace (University of Toronto) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Figshare (submittedVersion, cc-by)
- La Trobe University (cc-by)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Health Sciences › Medicine › Oncology › Cancer survivorship and care
- Keywords
- distress detection, therapist feedback, text-based emotion analysis, LIWC, Impact of Event Scale-Revised, social workers, COVID-19 pandemic, feasibility and acceptability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
