A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study
Open accessThe DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index; 22 of the 46 sources its claims cite were checked for support.
Abstract
Background: An increase in health anxiety was observed during the COVID-19 pandemic. However, due to physical distancing restrictions and a strained mental health system, people were unable to access support to manage health anxiety. Chatbots are emerging as an interactive means to deliver psychological interventions in a scalable manner and provide an opportunity for novel therapy delivery to large groups of people including those who might struggle to access traditional therapies. Objective: The aim of this mixed methods pilot study was to investigate the feasibility, acceptability, engagement, and effectiveness of a cognitive behavioral therapy (CBT)–based chatbot (Otis) as an early health anxiety management intervention for adults in New Zealand during the COVID-19 pandemic. Methods: Users were asked to complete a 14-day program run by Otis, a primarily decision tree–based chatbot on Facebook Messenger. Health anxiety, general anxiety, intolerance of uncertainty, personal well-being, and quality of life were measured pre-intervention, postintervention, and at a 12-week follow-up. Paired samples t tests and 1-way ANOVAs were conducted to investigate the associated changes in the outcomes over time. Semistructured interviews and written responses in the self-report questionnaires and Facebook Messenger were thematically analyzed. Results: The trial was completed by 29 participants who provided outcome measures at both postintervention and follow-up. Although an average decrease in health anxiety did not reach significance at postintervention (P=.55) or follow-up (P=.08), qualitative analysis demonstrated that participants perceived benefiting from the intervention. Significant improvement in general anxiety, personal well-being, and quality of life was associated with the use of Otis at postintervention and follow-up. Anthropomorphism, Otis’ appearance, and delivery of content facilitated the use of Otis. Technical difficulties and high performance and effort expectancy were, in contrast, barriers to acceptance and engagement of Otis. Conclusions: Otis may be a feasible, acceptable, and engaging means of delivering CBT to improve anxiety management, quality of life, and personal well-being but might not significantly reduce health anxiety. © Yenushka Goonesekera, Liesje Donkin.
Overview
CoChat Summary
## TL;DR
This mixed methods pilot study tested Otis, a Facebook Messenger CBT chatbot, for health anxiety management in 69 adults in New Zealand during COVID-19. Otis was feasible and acceptable and improved general anxiety, well-being, and quality of life, but it did not significantly reduce health anxiety.
## Key findings
- Of the 69 participants who completed baseline measures, 35 (51%) completed the postintervention questionnaire and 29 (42%) completed the 12-week follow-up; 12 of 29 (41%) completed all 14 days.
- Health anxiety decreased from baseline to postintervention and follow-up, but not significantly: SHAI-18 mean 19.93 to 19.31 at postintervention (P=.55) and 17.38 at follow-up (P=.08).
- General anxiety improved significantly: GAD-7 mean 9.69 to 7.58 at postintervention (t28=3.30, P=.003) and 7.00 at follow-up (t28=3.26, P=.003).
- Personal well-being and quality of life also improved significantly: ONS4 mean 5.70 to 6.31 at postintervention and 6.50 at follow-up (both P=.03), and quality of life improved at postintervention (P=.02) and follow-up (P<.001).
- Mean overall user experience was 18.24/30 and overall acceptability was rated 8.24/10; the most common reason for abandonment was lack of time (14/29, 35%).
## Methods
- Single-group, pretest-posttest mixed methods pilot study with semistructured interviews; participants were recruited via social media and email between May and July 2020.
- Sample: adults aged 18+ in New Zealand with Facebook Messenger and internet access; final follow-up sample was 29 participants, predominantly female (25/29, 86%), mean age 37.4 years.
- Intervention and analysis: a 14-day, primarily decision tree–based CBT chatbot (Otis) on Facebook Messenger; outcomes were measured at baseline, postintervention, and 12-week follow-up, analyzed with paired-samples t tests and 1-way ANOVAs, and qualitative data were thematically analyzed.
## Limitations
- The paper states that the observational design limited causal inference, and results may have been confounded by unidentifiable variables such as psychological input outside the intervention and changes in COVID-19 restrictions.
- The sample was mostly New Zealand European and highly educated, limiting generalizability.
- The authors note low statistical power from the small sample size, and the text also suggests a possible floor effect because only 5 participants met the health-anxiety cut-off; these are evident in the paper’s discussion.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
13 Valid · 6 Not valid · 15 Not checked · 89 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“During the initial development phase of a chatbot, it can produce crude responses that users may perceive as invalidating, robotic, or disconnected from their response [26].”
§ A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study > Methods > Intervention
What the sources say
- Partly supportedcites [26] sourceExperimental — accuracy not yet measured
The Discussion (Principal Findings; page unavailable) says chatbots’ limited responses might reflect their early development stage. The Results (Study Findings; page unavailable) report confusing responses, a robotic voice, and failures to understand users’ responses. They do not report that users perceived the responses as invalidating, so that part of the claim is unsupported. (LLM, conf=0.84)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“a previous study concluded that a score of 27 and greater differentiated health anxiety from other anxiety disorders [2].”
§ A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study > Methods > Measures
What the sources say
- Partly supportedcites [2] sourceExperimental — accuracy not yet measured
The Discussion reports that the SHAI differentiated people with health anxiety from people with other anxiety problems, citing Salkovskis et al. (2002). It does not give a score of 27 or conclude that this threshold makes the distinction; a search for that score found no supporting passage. Page numbers are not available in our copy. (LLM, conf=0.86)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Previous effective CBT interventions for health anxiety have been approximately 12 modules [24,25].”
§ A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study > Methods > Intervention
What the sources say
- Could not verifycites [24] sourceExperimental — accuracy not yet measured
The CBT component of CALM section describes treatment for panic disorder, generalized anxiety disorder, social anxiety disorder, and posttraumatic stress disorder—not health anxiety. The Results from CALM Tools for Living section reports an average of 7.63 attended CBT sessions, but does not establish that effective health-anxiety interventions comprised approximately 12 modules. Searches for health anxiety and 12 modules found no supporting passage in our copy. (LLM, conf=0.76)
- Not checked — no full text of the sourcecites [25] source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Previous studies have demonstrated that chatbot interventions improve psychological difficulties including major depressive disorder [15], panic disorder [16], posttraumatic stress disorder [17], antipsychotic medication adherence [18], and perceived stress [19].”
§ A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study > Introduction
What the sources say
- Partly supportedcites [15] sourceExperimental — accuracy not yet measured
Citation [15] is attached to major depressive disorder, not the other conditions in the sentence. The Related Work section says internet-based cognitive behavioral therapy can relieve depressive symptoms, but does not identify those interventions as chatbots. This paper’s Discussion reports that patients with major depressive symptoms accepted and formed a stronger alliance with the relational agent; it does not report that the agent improved their depression. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [16] source
- Partly supportedcites [17] sourceExperimental — accuracy not yet measured
Citation [17] is attached to posttraumatic stress disorder, not the other conditions in the sentence. The Evaluation’s second usability test reports that four former PTSD patients found the virtual-agent system’s questions useful for recalling traumatic memories. It does not demonstrate that the intervention improved PTSD symptoms; the reported outcomes concern recollection and usability. (LLM, conf=0.86)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The themes of technical difficulties and content delivery affecting engagement with Otis reflected the results in the systematic review by Borghouts and colleagues [53].”
§ A Cognitive Behavioral Therapy Chatbot (Otis) for Health Anxiety Management: Mixed Methods Pilot Study > Discussion > Comparison With Prior Work
What the sources say
- Supportedcites [53] source
The Results sections on technology-related and program-related constructs report that technical issues were a common barrier to engagement and that content type and delivery affected engagement. The Discussion’s Principal Findings summarize both as factors influencing engagement with digital mental health interventions; the claim does not attribute findings about Otis itself to the review. (LLM, conf=0.94)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
58 more claims · 3 with their cited sources checked
Create a free account to see all 123 claims and to verify the 3 references still open.
- Probably not a substantial claim. 28
- It may state two separate claims as one. 44
Citations
Cites
A Brief Measure for Assessing Generalized Anxiety Disorder: The GAD-7
Spitzer, R. L., Kroenke, K., Williams, J. B. W., & Löwe, B. (2006) · Archives of Internal Medicine · doi:10.1001/archinte.166.10.1092 · Cited by 31,765 · cited 1×
“92 and high convergent and discriminant validity [32].”
BackgroundThe WHO-5 well-being index: A systematic review of the literature
Topp, C. W., Østergaard, S. D., Søndergaard, S., & Bech, P. (2015) · Psychotherapy and Psychosomatics · doi:10.1159/000376585 · Cited by 4,708 · cited 1×
“A vast set of literature supports the validity and reliability of the measure in several populations [42-45].”
BackgroundFitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730
Qualitative Research: Rigour and qualitative research
Mays, N., & Pope, C. (1995) · BMJ · doi:10.1136/bmj.311.6997.109 · Cited by 2,715 · cited 1×
“Additionally, bias within the interpretation of the qualitative results, a common critique of qualitative research [62], is another limitation of the study.”
BackgroundGarnefski, N., Kraaij, V., Schroevers, M. J., & Somsen, G. A. (2008) · Journal of Clinical Psychology in Medical Settings · doi:10.1007/s10880-008-9136-5 · Cited by 2,479
Fearing the unknown: A short version of the Intolerance of Uncertainty Scale
Carleton, R. N., Norton, M. A. P. J., & Asmundson, G. J. G. (2007) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2006.03.014 · Cited by 2,288 · cited 4×
“AI: artificial intelligence ANOVA: analysis of variance CBT: cognitive behavioral therapy DHI: digital health intervention DSM: Diagnostic Manual of Mental Disorders GAD-7: Generalized Anxiety Disorder 7-item Scale iCBT: internet-based cognitive behavioral therapy IUS-12: Intolerance of Uncertainty Scale mHealth: mobi…”
BackgroundInfluentialThe intolerance of uncertainty scale: psychometric properties of the English version
Buhr, K., & Dugas, M. J. (2002) · Behaviour Research and Therapy · doi:10.1016/s0005-7967(01)00092-4 · Cited by 1,391 · cited 2×
“The ONS4 is widely used among various patient populations [36-40] and has demonstrated good internal reliability (Cronbach α=.”
BackgroundSALKOVSKIS, P. M., RIMES, K. A., WARWICK, H. M. C., & CLARK, D. M. (2002) · Psychological Medicine · doi:10.1017/s0033291702005822 · Cited by 1,351 · cited 5×
“AI: artificial intelligence ANOVA: analysis of variance CBT: cognitive behavioral therapy DHI: digital health intervention DSM: Diagnostic Manual of Mental Disorders GAD-7: Generalized Anxiety Disorder 7-item Scale iCBT: internet-based cognitive behavioral therapy IUS-12: Intolerance of Uncertainty Scale mHealth: mobi…”
InfluentialFear of the coronavirus (COVID-19): Predictors in an online study conducted in March 2020
Mertens, G., Gerritsen, L., Duijndam, S., Salemink, E., & Engelhard, I. M. (2020) · Journal of Anxiety Disorders · doi:10.1016/j.janxdis.2020.102258 · Cited by 1,264 · cited 1×
“However, when this fear is associated with functional impairment and distress, it is termed health anxiety [3].”
BackgroundAdherence in Internet Interventions for Anxiety and Depression
Christensen, H., Griffiths, K. M., & Farrer, L. (2009) · Journal of Medical Internet Research · doi:10.2196/jmir.1194 · Cited by 1,133 · cited 1×
“This study found that approximately 41% of participants completed the study and that, on average, the final sample completed 70% of the intervention, which is higher than seen in most of the literature [48-50].”
Result
Research works printed but not linked: 3
- 2000, Diagnostic and Statistical Manual of Mental Disorders, 4th edition
- Ersoy, K, 2020, Social Sciences Research Journal, 9, 117
- RietzTBenkeIMaedcheAThe impact of anthropomorphic and functional chatbot design features in enterprise collaboration systems on user acceptance201914th International Conference on WirtschaftsinformatikFebruary 24-27, 2019Siegen, Germany
Cited by
Chakraborty, C., Bhattacharya, M., Pal, S., & Lee, S.-S. (2024) · Current Research in Biotechnology · doi:10.1016/j.crbiot.2023.100164 · Cited by 274
Hua, Y., Siddals, S., Ma, Z., Galatzer‐Levy, I., Xia, W., Hau, C., Na, H., Flathers, M., Linardon, J., Ayubcha, C., et al. (2025) · World Psychiatry · doi:10.1002/wps.21352 · Cited by 117
Does the Digital Therapeutic Alliance Exist? Integrative Review
Malouin-Lachance, A., Capolupo, J., Laplante, C., & Hudon, A. (2025) · JMIR Mental Health · doi:10.2196/69294 · Cited by 103
“Goonesekera and Donkin [57] identified anthropomorphic features and engaging content as key facilitators but pointed to technical difficulties and limited interactivity in decision-tree-based chatbots as barriers.”
InfluentialYuan, A., Colato, E. G., Pescosolido, B. A., Song, H., & Samtani, S. (2025) · ACM Transactions on Management Information Systems · doi:10.1145/3701041 · Cited by 109
Sarbay, İ., Berikol, G. B., & Özturan, İ. U. (2023) · Turkish Journal of Emergency Medicine · doi:10.4103/tjem.tjem_79_23 · Cited by 68
Cho, Y., Rai, S., Ungar, L., Sedoc, J., & Guntuku, S. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.698 · Cited by 33
Luca, S., Clausen, M., Shaw, A., Lee, W., Krishnapillai, S., Adi-Wauran, E., Faghfoury, H., Costain, G., Jobling, R. K., Aronson, M. D., et al. (2023) · Human Genetics · doi:10.1007/s00439-022-02512-2 · Cited by 37
“Patient acceptability of chatbots in healthcare has been studied in other disciplines like psychology, (Easton et al. 2019) (Goonesekera and Donkin 2022), oncology (Bibault et al. 2019; Chaix et al. 2019), and public health (Luk et al. 2022).”
BackgroundMorriss, J. (2025) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2025.106138 · Cited by 28
Therapy and Emotional Support through a Chatbot
Andrade-Arenas, L., Yactayo-Arias, C., & Pucuhuayla-Revatta, F. (2024) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v20i02.45377 · Cited by 15
Nguyen, M. H., Sedoc, J., & Taylor, C. O. (2024) · Journal of Medical Internet Research · doi:10.2196/55164 · Cited by 20
“Currently, chatbots are being explored for clinical use as new ways to collect patient data and deliver care asynchronously, with use cases ranging from nutrition journaling to cognitive behavioral therapy delivery [43,44,49].”
Shankar, R., Foo, T. H., Devi, F., & Xu, Q. (2025) · Journal of Mental Health · doi:10.1080/09638237.2025.2595612 · Cited by 16
Kang, A., Hetrick, S. E., Cargo, T., Hopkins, S. A., Ludin, N. M., Bodmer, S., Stevenson, K., Holt‐Quick, C., & Stasiak, K. (2023) · JMIR Formative Research · doi:10.2196/44556 · Cited by 17
“A mixed methods study of a cognitive behavioral therapy chatbot, Otis, found that technological difficulties were one of the main reasons for its abandonment [34].”
BackgroundKuhail, M. A., Al-Shamaileh, O., Farooq, S., Shahin, H., Abdelzaher, F., & Thomas, J. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/9942295 · Cited by 11
Geng, S., Inayoshi, R., Yang, C.-L., Sramek, Z., Umeda, Y., Kasahara, C., Sato, A. J., Hosio, S. J., & Yatani, K. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713918 · Cited by 17
Lee, J., You, J. S., & Lee, D. (2024) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2307695 · Cited by 11
“Unlike a real human, AI counseling chatbots can be accessed 24/7, making it possible for clients to receive counseling at any time without physical restrictions (Bendig et al., 2019; Fitzpatrick et al., 2017; Goonesekera & Donkin, 2022).”
What patients want from healthcare chatbots: insights from a mixed-methods study
Dellavalle, N. S., Ellis, J. R., Moore, A., Akerson, M., Andazola, M., Campbell, E. G., & DeCamp, M. W. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf164 · Cited by 14
Phoenix: A Conversational Agent for Emotional Well-Being and Psychological Support
Benita, J., Jaswanth, S., Bhuvaneshwar, N., Yuvaraj, R., & Narayana, Y. L. (2025) · International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) · doi:10.1109/icmsci62561.2025.10894579 · Cited by 8
“Future enhancements may include personalized interaction and telehealth integration to expand the scope of mental health care [6].”
Therapeutic Artificial Intelligence: Does Agential Status Matter?
Hurley, M. E., Lang, B. H., & Smith, J. N. (2023) · The American Journal of Bioethics · doi:10.1080/15265161.2023.2191037 · Cited by 6
“…tool, users reported that Otis “ made them gain greater insight into health anxiety and develop strategies to challenge their anxious thoughts, ” (Goonesekera and Donkin 2022, 7), pointing to our earlier suggestion that feeling heard and understood may be more important to therapeutic…”
BackgroundStriegl, J., Rottmann, S., & Loitsch, C. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-66329-1_14 · Cited by 4
mHealth Apps on the Rise: Exploring the Influence of App and Individual Characteristics on Adoption
Halvadia, N. B., Bhatt, K., Patel, H., & Halvadia, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-8346-9_5 · Cited by 6
Overview of chatbot usage on mental health: A scoping review
Permatasari, R. I., Artha, D. P., Wiratama, B. S., & Wulandari, H. (2024) · BIO Web of Conferences · doi:10.1051/bioconf/202413205002 · Cited by 4
Investigación mixta: ¿qué es y qué no?
Ballesteros, L. M. G., Gómez–Restrepo, C., Rodríguez, V., de Castro, S. F., & Vásquez-Ponce, M. (2024) · Revista Colombiana de Psiquiatría · doi:10.1016/j.rcp.2024.04.002 · Cited by 18
Chatbots and COVID-19: Taking Stock of the Lessons Learned
Arnold, V., Purnat, T. D., Marten, R., Pattison, A. B., & Gouda, H. (2024) · Journal of Medical Internet Research · doi:10.2196/54840 · Cited by 7
NursingLLM: A Retrieval-Augmented Health Chatbot for Supporting Nursing Home Residents
She, D., Ren, J., Sun, Y., et al. (2025) · doi:10.1145/3714394.3756349 · Cited by 1
Bayram, F., Gündüz, B., & Yakın, İ. (2026) · Bartın University Journal of Faculty of Education · doi:10.14686/buefad.1721049 · Cited by 1
Pareek, S., & Jain, G. (2026) · Journal of College Student Mental Health · doi:10.1080/28367138.2026.2653092 · Cited by 1
Aydın, B. (2023) · EKEV Akademi Dergisi · doi:10.17753/sosekev.1367444 · Cited by 3
Melo, S. A. N., de Aguiar, C. L., da Cunha, L. K. S., & Brustolin, J. C. R. (2024) · Prometeica - Revista de Filosofía y Ciencias · doi:10.34024/prometeica.2024.29.16268 · Cited by 2
Shirvani, M. S., Crowley, J., Peng, C., Liu, J., Chao, T. W.-C., Martinez, S., Brandt, L., Kim, I.-J., & Yoon, D. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790986 · Cited by 4
“During the semi-structured inter-views, we also probed for thick and specific descriptions grounded in concrete cases from participants’ clinical practice or personal experience, using hypothetical futures as an extension of, rather than a substitute for, their real-world expertise.”
Utilizing Chatbots as Predictive Tools for Anxiety and Depression: A Bibliometric Review
Carrillo, M. D. L. D., Pírez, M. O. R., & Chang, G. A. L. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-46813-1_10
Prometeica, R. (2024) · Prometeica - Revista de Filosofía y Ciencias · doi:10.34024/prometeica.2024.29.15900
de Bruijn, G., Jabeen, F., & Bosse, T. (2025) · Wiley eBooks · doi:10.1002/9781394179909.ch13
Prasetya, N. W., Darma, K. J., Sari, W. P., Sari, N. M. A. W., Sidharta, S., & Atmaji, L. T. (2024) · International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS) · doi:10.1109/icimcis63449.2024.10957610
“Despite no significant improvements in health anxiety shown, the authors of the study concluded that the chatbot could act as a feasible solution to alleviate strain in psychological services[15].”
Geng, S., Shimojima, G., Yang, C.-L., Sramek, Z., Norihama, S., Takano, A., Hosio, S. J., & Yatani, K. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711103 · Cited by 4
Nivetha, K., Karuveettil, V., Pillai, A., Jayachandran, M., & Palatty, P. L. (2025) · JBI Evidence Synthesis · doi:10.11124/jbies-24-00533
Xu, J., Shen, J., Wang, J., & Huang, G. (2026) · doi:10.2196/preprints.91108
Wu, W., Egger, S., Bucher, A. M., Vashkite, I., Dolata, M., & Schwabe, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-19687-3_31
Sayed, F., Park, A., Sullivan, P. S., Jordan, A., Kwon, S., & Ge, Y. (2026) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocag044
NeuroBloom: Where AI Meets Inner Peace
Pandgale, P., Chavan, N. V., Bharti, M., & Kumar, A. (2026) · International Conference on Emerging Technologies and Future Innovations (ETFI) · doi:10.1109/etfi68128.2026.11484813
“The first usage of conversational agents in mental health treatment was rule-based chatbots [12].”
ElshikhIdris, M. A. M., Ali, A. S. H., Mahmoud, S. Y., Aziz, Y. M. S., Ali, I., Farah, S., & Altayeb, W. F. M. (2026) · Cureus · doi:10.7759/cureus.111334
“In contrast, a 14-day CBT chatbot (Otis) [19] did not reduce health anxiety (SHAI-18) but did reduce generalized anxiety (GAD-7) and improved well-being and quality of life.”
InfluentialScoping Review: Intervention Methods in Conversational Agent-Based Cognitive Behavioral Therapy
Striegl, J., Butz, N., & Loitsch, C. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29842-3_16
Theilmann, K., Steffny, L., Dahlem, N., Podevin, D., Greff, T., & Bleistein, T. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-29596-5_24
Xu, J., Shen, J., Huang, G., & Wang, J. (2026) · JMIR mhealth and uhealth · doi:10.2196/91108
Metadata
- Authors
- Goonesekera, Y., & Donkin, L.
- Affiliations
- University of Auckland (NZ)
- Corresponding author
- Donkin, Liesje
- Venue
- JMIR Formative Research
- Publisher
- JMIR Publications Inc.
- Published
- 2022-10-20
- Volume
- 6
- Issue
- 10
- Pages
- e37877
- ISSN
- 2561-326X (ISSN-L)
- PMC
- PMC9586257
- OpenAlex
- W4296509688
- Cited by
- 43
- References
- 58
- Citations by year
- 2026: 11 · 2025: 12 · 2024: 12 · 2023: 8
- FWCI
- 7.07
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JMIR Formative Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Social Sciences › Psychology › Clinical Psychology › COVID-19 and Mental Health
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
- Keywords
- health anxiety, cognitive behavioral therapy, chatbots, Otis, COVID-19 pandemic, digital mental health interventions, Facebook Messenger, decision tree, anthropomorphism, feasibility and acceptability, general anxiety, quality of life, well-being, intolerance of uncertainty, barriers to engagement
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.


