The DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index; 93 of the 113 sources its claims cite were checked for support.
Artificial Intelligence-Based Chatbots for Promoting Health Behavioral Changes: Systematic Review.
Open accessPublished version of a preprint
Abstract
Artificial intelligence (AI)-based chatbots can offer personalized, engaging, and on-demand health promotion interventions. The aim of this systematic review was to evaluate the feasibility, efficacy, and intervention characteristics of AI chatbots for promoting health behavior change. A comprehensive search was conducted in 7 bibliographic databases (PubMed, IEEE Xplore, ACM Digital Library, PsycINFO, Web of Science, Embase, and JMIR publications) for empirical articles published from 1980 to 2022 that evaluated the feasibility or efficacy of AI chatbots for behavior change. The screening, extraction, and analysis of the identified articles were performed by following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Of the 15 included studies, several demonstrated the high efficacy of AI chatbots in promoting healthy lifestyles (n=6, 40%), smoking cessation (n=4, 27%), treatment or medication adherence (n=2, 13%), and reduction in substance misuse (n=1, 7%). However, there were mixed results regarding feasibility, acceptability, and usability. Selected behavior change theories and expert consultation were used to develop the behavior change strategies of AI chatbots, including goal setting, monitoring, real-time reinforcement or feedback, and on-demand support. Real-time user-chatbot interaction data, such as user preferences and behavioral performance, were collected on the chatbot platform to identify ways of providing personalize…
Overview
CoChat Summary
TL;DR
This systematic review found that AI-based chatbots showed efficacy for several health behavior changes, especially healthy lifestyles, smoking cessation, and medication/treatment adherence, but evidence was mixed for feasibility, acceptability, and usability. The authors caution that most included studies had moderate to high risk of internal validity issues and limited reporting of AI methods, so stronger RCTs are needed.
Key findings
- The review included 15 studies; AI chatbots were reported as efficacious for healthy lifestyles (6/15, 40%), smoking cessation (4/15, 27%), treatment or medication adherence (2/15, 13%), and reduction in substance misuse (1/15, 7%).
- Feasibility evidence was limited: 11/15 (73%) studies reported feasibility, but safety was only reported in 1/15 (7%) study, and engagement often declined over time.
- Acceptability was mixed: 7/15 (47%) studies reported acceptability/engagement, but the overall proportion of satisfied participants was less than 50%.
- Usability was also mixed: 11/15 (73%) studies reported usability, with ease of use generally low to moderate and 1/15 (7%) studies reporting technical issues for 82.3% of participants.
Methods
- Systematic review following PRISMA; searched 7 databases (PubMed, IEEE Xplore, ACM Digital Library, PsycINFO, Web of Science, Embase, JMIR publications) for empirical English-language articles from 1980 to 2022.
- Included studies had to evaluate AI-based chatbots for health behavior change; from 1961 records screened, 15 studies met inclusion criteria.
- The authors extracted study characteristics, intervention features, and outcomes; quality was assessed using the NIH quality assessment tool for controlled intervention studies and CONSORT-AI guidance.
Limitations
- The paper states that no meta-analysis was conducted because of heterogeneity in design, outcomes, and measures.
- The review states it did not cover a comprehensive set of behavioral outcomes because of strict inclusion criteria; the included studies focused on healthy lifestyle, smoking cessation, and treatment/medication adherence.
- The text makes evident that many included studies had pre-post designs without control groups, small samples in some studies, and limited description of AI techniques; the paper explicitly notes moderate to high internal validity risk and limited generalizability.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
51 Valid · 5 Not valid · 6 Not checked · 114 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“First, this review did not distinguish between AI-driven chatbots and other chatbots.”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Introduction > Prior Work
What the sources say
- Disputedcites [2] sourceExperimental — accuracy not yet measured
The Methods (Eligibility criteria; page unavailable) limit the review to interventions using AI chatbots, rather than chatbots generally. The Results (Summary of intervention and chatbot characteristics; page unavailable) further distinguish constrained from unconstrained chatbots. The paper therefore does not support the claim that it made no distinction between AI chatbots and other chatbots. (LLM, conf=0.84)
Checked by a reasoning model — may be wrong.
plain- 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.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Second, the selected studies targeted only a limited set of behaviors, including physical activity, diet, and weight management.”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Introduction > Prior Work
What the sources say
- Supportedcites [2] source
The Methods (Eligibility criteria, Table 1; page not available) limit included studies to AI chatbot interventions for physical activity, diet, and/or weight management. The review’s selected studies therefore fall within the limited set of behaviors described in the claim. (LLM, conf=0.93)
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.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The existing digital therapeutic and telehealth interventions with didactic components, which enable health care providers to communicate with patients via digital platforms (eg, email and video call), have encountered several challenges, including relatively low adherence, unsustainability, and inflexibility [3,4].”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Introduction > Background
What the sources say
- Not checked — no full text of the sourcecites [3] source
- Partly supportedcites [4] sourceExperimental — accuracy not yet measured
The Adherence and adverse events section reports low completion of computerised CBT: 10.4% with minimal support and 19.4% with telephone facilitation completed all five sessions. The paper does not establish that these interventions are unsustainable or inflexible; its Implications section instead says telephone-supported CBT could be offered at scale. Its findings also concern CBT for depression, not digital therapeutic and telehealth interventions generally. (LLM, conf=0.88)
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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The overall conversational flexibility offered by AI chatbots in terms of communicating at anytime from anywhere offers a safe space to facilitate interactions with patients who feel or experience stigmatization while seeking health care services [5].”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Introduction > Background
What the sources say
- Partly supportedcites [5] sourceExperimental — accuracy not yet measured
The Discussion (Principal Findings; page unavailable) reports that participants felt more comfortable discussing issues with a robot because they did not expect it to judge them. The Discussion (Limitations and Directions for Future Research; page unavailable) suggests this could encourage discussion of sensitive issues and earlier help-seeking. The study concerns a social robot, however, and does not establish that AI chatbots offer flexible conversation anytime from anywhere or specifically facilitate interactions for patients experiencing stigmatization while seeking health care. (LLM, conf=0.88)
plainstates a cause- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Second, the AI algorithm uses machine learning (ML) and natural language processing (NLP) techniques to identify clinically meaningful patterns and understand user needs [7].”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Introduction > Background
What the sources say
- Partly supportedcites [7] sourceExperimental — accuracy not yet measured
The Introduction (Background; page unavailable) says conversational agents use machine learning and NLP to analyze user input and respond. It does not say they identify clinically meaningful patterns, and the Discussion (Principal Findings; page unavailable) notes that agents often had difficulty understanding users. (LLM, conf=0.86)
plainstates a cause- 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.
- Partly supported
90 more claims · 28 with their cited sources checked
Create a free account to see all 176 claims and every source verdict.
- It may state two separate claims as one. 66
- Probably not a substantial claim. 27
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It is notable that research into the use of AI for the delivery of personalized recommendations is sparse33”
From Impact of digital health interventions on glycemic control and weight management. (2025) · cites this paper as [33]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“These findings align with those of another meta-analysis [122], showing the effectiveness of CAs in outcomes related to lifestyle changes, smoking cessation, substance misuse, and medication adherence.”
From Development and Evaluation of a Smartphone-Based Chatbot Coach to Facilitate a Balanced Lifestyle in Individuals With Headaches (BalanceUP App): Randomized Controlled Trial (2024) · cites this paper as [122]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For example, an AI-driven system might suggest lifestyle modifications, such as dietary changes or exercise routines that are optimized for an individual’s metabolism and cardiovascular risk (57).”
From Generative artificial intelligence in predictive analysis of diabetes and its complications: a narrative review (2025) · cites this paper as [57]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Chatbots provide real-time personalized health promotion, prevention, and screening (Aggarwal et al., 2023; Laranjo et al., 2018).”
From A chatbot-delivered intervention for optimizing social media use and reducing perceived isolation among rural-living LGBTQ+ youth: Development, acceptability, usability, satisfaction, and utility (2023) · cites this paper as Aggarwal et al., 2023
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Chatbots are convenient artificial intelligence–operated conversational agents; they can be deployed within a social media site, do not require user download, and do not take up space in a user's device.”
From A chatbot-delivered intervention for optimizing social media use and reducing perceived isolation among rural-living LGBTQ+ youth: Development, acceptability, usability, satisfaction, and utility (2023) · cites this paper as Aggarwal et al., 2023
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Results > Characteristics of the Reviewed Studies
“All 13 studies were distributed across low-income countries, with 4 (31%) from the United States, 2 (15%) from Australia, and 1 (8%) from each remaining country (ie, South Korea, Spain, the United Kingdom, Japan, France, Switzerland, and the Netherlands).”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Discussion > Limitations of the Reviewed Studies and Future Research Directions
“Out of the 13 studies that reported the geographical locations, all (100%) were conducted in the high-income countries;”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Results > Characteristics of the Reviewed Studies
“Only 27% (4/15) of studies used randomized control trials (RCTs), and most of the studies (9/15, 60%) adopted a quasiexperimental design (ie, pre- and posttests) with no control group, followed by 7% (1/15) of studies with a cross-sectional design and 7% (1/15) of studies with a postexperimental research method.”
§ Artificial Intelligence–Based Chatbots for Promoting Health Behavioral Changes: Systematic Review > Results > Intervention Study Quality Assessment
“In the case of RCTs (4/15, 27%), this bias was minimized because of the experimental setting of the interventions; however, for non-RCT studies (11/14, 73%), there was a high risk of bias owing to the potential effect of confounding variables.”
Citations
Cites
PRISMA-P Group, Moher, D., Shamseer, L., Clarke, M., Ghersi, D., Liberati, A., Petticrew, M., Shekelle, P., & Stewart, L. A. (2015) · Systematic Reviews · doi:10.1186/2046-4053-4-1 · Cited by 26,223
How we design feasibility studies
Bowen, D. J., Kreuter, M., Spring, B., Cofta-Woerpel, L., Linnan, L., Weiner, D., Bakken, S., Kaplan, C. P., Squiers, L., Fabrizio, C., et al. (2009) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2009.02.002 · Cited by 4,021 · cited 1×
“Feasibility was defined as the demand of the intervention, that is, the actual use of the intervention and whether the intervention is doable in a certain setting [16].”
Conversational agents in healthcare: a systematic review
Laranjo, L., Dunn, A. G., Tong, H. L., Kocaballi, A. B., Chen, J., Bashir, R., Surian, D., Gallego, B., Magrabi, F., Lau, A. Y. S., et al. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy072 · Cited by 1,388 · cited 9×
“Artificial intelligence (AI)–driven chatbots (AI chatbots) are conversational agents that mimic human interaction through written, oral, and visual forms of communication with a user [1,2].”
InfluentialChatbots and Conversational Agents in Mental Health: A Review of the Psychiatric Landscape
Vaidyam, A. N., Wisniewski, H., Halamka, J. D., Kashavan, M. S., & Torous, J. B. (2019) · The Canadian Journal of Psychiatry · doi:10.1177/0706743719828977 · Cited by 1,048 · cited 1×
“…findings are consistent with the previous systematic literature reviews that reported that all the chatbot intervention studies were conducted in high-income countries [2,10,11,14], most studies were conducted with adults [2,7], and most studies did not focus on racial or ethnic minorities [2,14].”
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Zhou, H., Huang, M., Zhang, T., Zhu, X., & Liu, B. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11325 · Cited by 763
Liu, X., Rivera, S. C., Moher, D., Calvert, M. J., & Denniston, A. K. (2020) · BMJ · doi:10.1136/bmj.m3164 · Cited by 702
The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review
Milne-Ives, M., de Cock, C., Lim, E., Shehadeh, M. H., de Pennington, N., Mole, G., Normando, E., & Meinert, E. (2020) · Journal of Medical Internet Research · doi:10.2196/20346 · Cited by 626 · cited 8×
“This finding is consistent with the previous systematic literature reviews that reported very few studies discussed participant safety or ethics in terms of adverse events [1,2,7,9] and data security or privacy [2,8].”
InfluentialAbd-Alrazaq, A. A., Rababeh, A., Alajlani, M., Bewick, B. M., & Househ, M. (2020) · Journal of Medical Internet Research · doi:10.2196/16021 · Cited by 503
Embodied conversational agents in clinical psychology: a scoping review
Provoost, S., Lau, H. M., Ruwaard, J., & Riper, H. (2017) · Journal of Medical Internet Research · doi:10.2196/jmir.6553 · Cited by 433 · cited 2×
“Of the extant systematic reviews on AI chatbots, 6 articles targeted at assessing efficacy of AI-chatbots in enhancing mental health outcomes [1,7,9-12], 2 examined the feasibility of AI-chatbots in health care settings [8,13], and 1 described the technical architectures and characteristics of the…”
Zhang, J., Oh, Y. J., Lange, P., Yu, Z., & Fukuoka, Y. (2020) · Journal of Medical Internet Research · doi:10.2196/22845 · Cited by 363 · cited 1×
“As specified in the AI chatbot design literature, user engagement is dependent on the chatbot’s ability to understand the user’s background, build a relation, be persuasive, and offer quick feedback [34].”
Research works printed but not linked: 1
- Radziwill, NM, 2017, arXiv
Cited by
Large language models in medicine
Thirunavukarasu, A. J., Ting, D. S. J., Elangovan, K., Gutierrez, L., Tan, T. F., & Ting, D. S. W. (2023) · Nature Medicine · doi:10.1038/s41591-023-02448-8 · Cited by 3,944
Revolutionizing healthcare: the role of artificial intelligence in clinical practice
Alowais, S. A., Alghamdi, S. S., Alsuhebany, N., Alqahtani, T., Alshaya, A. I., Almohareb, S. N., Aldairem, A., Alrashed, M., Bin Saleh, K., Badreldin, H. A., et al. (2023) · BMC Medical Education · doi:10.1186/s12909-023-04698-z · Cited by 3,146
“AI has the potential to play a significant role in patient education by providing personalized and interactive information and guidance to patients and their caregivers [100].”
BackgroundRoles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review (Preprint)
Laymouna, M., Ma, Y., Lessard, D., Schuster, T., Engler, K., & Lebouché, B. (2024) · doi:10.2196/preprints.56930 · Cited by 302
Roles, Users, Benefits, and Limitations of Chatbots in Health Care: Rapid Review
Laymouna, M., Ma, Y., Lessard, D., Schuster, T., Engler, K., & Lebouché, B. (2024) · Journal of Medical Internet Research · doi:10.2196/56930 · Cited by 305
Innovation and challenges of artificial intelligence technology in personalized healthcare
Li, Y.-H., Li, Y.-L., Wei, M.-Y., & Li, G.-Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-70073-7 · Cited by 275
“By utilizing Natural Language Processing (NLP) and machine learning algorithms, chatbots can learn from patient interactions and adjust their responses to match the patient’s language and style, making the user experience more natural and engaging 5,6 .”
MethodFaiyazuddin, M., Rahman, S. J. Q., Anand, G., Siddiqui, R. K., Mehta, R., Khatib, M. N., Gaidhane, S., Zahiruddin, Q. S., Hussain, A., & Sah, R. (2025) · Health Science Reports · doi:10.1002/hsr2.70312 · Cited by 242
Hirani, R., Noruzi, K., Khuram, H., Hussaini, A. S., Aifuwa, E. I., Ely, K. E., Lewis, J. M., Gabr, A. E., Smiley, A., Tiwari, R. K., et al. (2024) · Life · doi:10.3390/life14050557 · Cited by 210
“One of the biggest implications of the utilization of these chatbots is that it results in higher patient engagement resulting in improved patient adherence to treatment because of shifting to patient-centric care [126].”
BackgroundSystematic review and meta-analysis of the effectiveness of chatbots on lifestyle behaviours
Singh, B., Olds, T., Brinsley, J., Dumuid, D., Virgara, R., Matricciani, L., Watson, A., Szeto, K., Eglitis, E., Miatke, A., et al. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00856-1 · Cited by 224
Can ChatGPT be used in oral and maxillofacial surgery?
Balel, Y. (2023) · Journal of Stomatology, Oral and Maxillofacial Surgery · doi:10.1016/j.jormas.2023.101471 · Cited by 197
Kurniawan, M. H., Handiyani, H., Nuraini, T., Hariyati, R. T. S., & Sutrisno, S. (2024) · Annals of Medicine · doi:10.1080/07853890.2024.2302980 · Cited by 177
A Systematic Literature Review of Information Security in Chatbots
Jing, Y., Chen, Y., Por, L. Y., & Ku, C. S. (2023) · Applied Sciences · doi:10.3390/app13116355 · Cited by 149
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
“Aggarwal et al [37] emphasized the integration of behavior change theories, including goal-setting frameworks, to improve both primary and secondary outcomes.”
InfluentialSmart Smile: Revolutionizing Dentistry With Artificial Intelligence
Dhopte, A., & Bagde, H. S. (2023) · Cureus · doi:10.7759/cureus.41227 · Cited by 202
“Chatbots can also guide patients in emergency situations, providing immediate support until they can receive professional care [20,21].”
BackgroundChatbots in Health Care: Connecting Patients to Information
Clark, M., & Bailey, S. M. (2024) · Canadian Journal of Health Technologies · doi:10.51731/cjht.2024.818 · Cited by 137
Evaluation of the Current State of Chatbots for Digital Health: Scoping Review
Xue, J., Zhang, B., Zhao, Y., Zhang, Q., Zheng, C., Jiang, J., Li, H., Liu, N., Li, Z., Fu, W., et al. (2023) · Journal of Medical Internet Research · doi:10.2196/47217 · Cited by 129
“A systematic review showed that personalized AI chatbots were potentially effective in promoting health behavior change within broad population groups; however, studies with more rigorous designs are needed to confirm their effects [10].”
Wah, J. N. K. (2025) · Frontiers in Public Health · doi:10.3389/fpubh.2025.1530799 · Cited by 91
Artificial intelligence for psychotherapy: a review of the current state and future directions
Beg, M. J., Verma, M., M., V. C. K. M., & Verma, M. K. (2025) · Indian Journal of Psychological Medicine · doi:10.1177/02537176241260819 · Cited by 82
Role of Artificial Intelligence (AI) in Patient Education and Communication in Dentistry
Thorat, V., Rao, P., Joshi, N., Talreja, P., & Shetty, A. R. (2024) · Cureus · doi:10.7759/cureus.59799 · Cited by 144
Wearable Devices to Improve Physical Activity and Reduce Sedentary Behaviour: An Umbrella Review
Longhini, J., Marzaro, C., Bargeri, S., Palese, A., Dell’Isola, A., Turolla, A., Pillastrini, P., Battista, S., Castellini, G., Cook, C. E., et al. (2024) · Sports Medicine - Open · doi:10.1186/s40798-024-00678-9 · Cited by 108
“For example, artificial intelligence chatbots show great promise in promoting healthy lifestyles and physical activity [89], based on several features such as understanding user background, establishing persuasive conversations, and providing input according to behavioural outcomes [90].”
BackgroundA multifaceted vision of the human-AI collaboration: a comprehensive review
Puerta-Beldarrain, M., Gómez-Carmona, O., Sánchez-Corcuera, R., Casado-Mansilla, D., López-de-Ipiña, D., & Chen, L. (2025) · IEEE Access · doi:10.1109/access.2025.3536095 · Cited by 73
“Chatbots,as conversational agents, have evolved significantly in recent years, enhancing their ability to simulate human interactions through text, voice, and visual communication [27], [345].”
Saihi, A., Ben-Daya, M., Hariga, M., & As'ad, R. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100274 · Cited by 75
Potential applications and implications of large language models in primary care
Andrew, A. (2024) · Family Medicine and Community Health · doi:10.1136/fmch-2023-002602 · Cited by 83
An, R., Shen, J., Wang, J., & Yang, Y. (2023) · Journal of sport and health science/Journal of Sport and Health Science · doi:10.1016/j.jshs.2023.09.010 · Cited by 92
Generative AI in Medicine — Evaluating Progress and Challenges
Maddox, T. M., Embí, P. J., Gerhart, J., Goldsack, J. C., Parikh, R. B., & Sarich, T. C. (2025) · New England Journal of Medicine · doi:10.1056/nejmsb2503956 · Cited by 79
Young, J., Jawara, L. M., Nguyen, D. N., Daly, B., Huh-Yoo, J., & Razi, A. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642574 · Cited by 59
Artificial Intelligence in Healthcare: Perception and Reality
Akinrinmade, A. O., Adebile, T. M., Ezuma-Ebong, C., Bolaji, K., Ajufo, A., Adigun, A. O., Mohammad, M., Dike, J. C., & Okobi, O. E. (2023) · Cureus · doi:10.7759/cureus.45594 · Cited by 111
“…recorded even in the presence of the improved efficacy of chatbots in helping the participants promote a better lifestyle and the provision of an avenue for safer space expression that chatbots provided with regard to sensitive and personal questions such as sex-related issues and drug use [24].”
BackgroundMethodInfluentialAssessing the performance of AI chatbots in answering patients' common questions about low back pain
Scaff, S. P. S., dos Reis, F. J. J., Ferreira, G. E., Jacob, M. F., & Saragiotto, B. T. (2024) · Annals of the Rheumatic Diseases · doi:10.1136/ard-2024-226202 · Cited by 71
“23 25 However, LLM-chatbots have some important limitations.”
Lee, H. S., Wright, C., Ferranto, J., Buttimer, J., Palmer, C. E., Welchman, A., Mazor, K. M., Fisher, K. A., Smelson, D., O’Connor, L., et al. (2025) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2024.1505024 · Cited by 55
GPTCoach: Towards LLM-Based Physical Activity Coaching
Jörke, M., Sapkota, S., Warkenthien, L., Vainio, N., Schmiedmayer, P., Brunskill, E., & Landay, J. A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713819 · Cited by 141
Loughnane, C., Laiti, J., O’Donovan, R., & Dunne, P. J. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1536416 · Cited by 76
Saihi, A., Ben‐Daya, M., & Hariga, M. A. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-13023-0 · Cited by 74
ChatGPT in Plastic and Reconstructive Surgery
Sharma, S. C., Ramchandani, J. P., Thakker, A., & Lahiri, A. (2023) · Indian Journal of Plastic Surgery · doi:10.1055/s-0043-1771514 · Cited by 59
“28 This application demonstrates the connection generative AI ’ s can develop with patients and their potential to be powerful aids for preoperative patient optimization.”
BackgroundKim, H. K. (2024) · Healthcare · doi:10.3390/healthcare12050534 · Cited by 78
“[31].”
Kaphingst, K. A., Kohlmann, W. K., Chambers, R. L., Bather, J. R., Goodman, M. S., Bradshaw, R. L., Chavez‐Yenter, D., Colonna, S. V., Espinel, W., Everett, J. N., et al. (2024) · JAMA Network Open · doi:10.1001/jamanetworkopen.2024.32143 · Cited by 60
Kaplan, T. T., & Cankar, M. (2024) · Dental Traumatology · doi:10.1111/edt.12999 · Cited by 66
Bragazzi, N. L., Crapanzano, A., Converti, M., Zerbetto, R., & Khamisy-Farah, R. (2023) · Journal of Medical Internet Research · doi:10.2196/52091 · Cited by 54
“They can enhance sexual health and promote positive behavior changes [41-43] through a variety of strategies, including goal setting, monitoring, real-time reinforcement or feedback, and on-demand support.”
Can natural language processing serve as a consultant in oral surgery?
Acar, A. H. (2023) · Journal of Stomatology Oral and Maxillofacial Surgery · doi:10.1016/j.jormas.2023.101724 · Cited by 56
Kiuchi, K., Otsu, K., & Hayashi, Y. (2023) · Behaviour and Information Technology · doi:10.1080/0144929x.2023.2286528 · Cited by 62
“…Costa, and Righi 2019; Sezgin et al. 2020; Shan, Ji, Xie, Qian, et al., 2022; ter Stal et al. 2020), chatbots (Abd-Alrazaq, Sa fi , et al., 2020; Aggarwal et al. 2023; Gabarron et al. 2020; Han et al. 2023; Oh et al. 2021; Singh et al. 2023; Whit-taker, Dobson, and Garner 2022; Zhang et al.…”
Transforming healthcare with chatbots: Uses and applications—A scoping review
Barreda, M., Cantarero, D., Coca, D., Delgado, A., Lanza‐León, P., Lera, J., Montalbán, R., & Pérez, F. (2025) · Digital Health · doi:10.1177/20552076251319174 · Cited by 72
“Aggarwal et al. 7 approximated the following de fi nition for “ chatbot ” in healthcare: “ AI chatbots are conversational agents that mimic human interaction through written, oral, and visual forms of communication with a user.”
Qin, H., Zhu, Y., Jiang, Y., Luo, S., & Huang, C. (2024) · Technology in Society · doi:10.1016/j.techsoc.2024.102726 · Cited by 66
The application of artificial intelligence in the management of sepsis
Yang, J., Hao, S., Huang, J., Chen, T., Liu, R., Zhang, P., Feng, M., He, Y., Xiao, W., Hong, Y., et al. (2023) · Medical Review · doi:10.1515/mr-2023-0039 · Cited by 53
Understanding older adults’ acceptance of Chatbots in healthcare delivery: an extended UTAUT model
Yu, S., & Chen, T. (2024) · Frontiers in Public Health · doi:10.3389/fpubh.2024.1435329 · Cited by 70
Diet Quality and Caloric Accuracy in AI-Generated Diet Plans: A Comparative Study Across Chatbots
Kaçar, H. K., Kaçar, Ö. F., & Avery, A. (2025) · Nutrients · doi:10.3390/nu17020206 · Cited by 49
“These AI-based tools have garnered significant attention as promising resources for weight loss and lifestyle modification [13].”
Kunitsu, Y. (2023) · JMIR Medical Education · doi:10.2196/48452 · Cited by 51
“More recently, AI chatbots (also known as interactive AI) have been invented and are being used in medicine to automatically converse with human text and voice input [4-6].”
BackgroundREVIEW OF AI APPLICATIONS IN HEALTHCARE: COMPARATIVE INSIGHTS FROM THE USA AND AFRICA
Babarinde, A. O., Ayo-Farai, O., Maduka, C. P., Okongwu, C. C., Ogundairo, O., & Sodamade, O. (2023) · International Medical Science Research Journal · doi:10.51594/imsrj.v3i3.641 · Cited by 42
How reliable is the artificial intelligence product large language model ChatGPT in orthodontics?
Demirsoy, K. K., Büyük, S. K., & Bicer, T. (2024) · The Angle Orthodontist · doi:10.2319/031224-207.1 · Cited by 48
Mercado, J., Espinosa‐Curiel, I. E., & Martínez-Miranda, J. (2023) · Journal of Medical Internet Research · doi:10.2196/52097 · Cited by 56
Wu, P. F., Summers, C., Panesar, A., Kaura, A., & Zhang, L. (2024) · JMIR Human Factors · doi:10.2196/51086 · Cited by 53
“The potential benefits offered by these technologies, such as enhanced health care accessibility [4,36], cost reduction [15], and improved patient outcomes [37], are too substantial to disregard.”
BackgroundJin, E., Ryoo, Y., Kim, W., & Song, Y. G. (2024) · Internet Research · doi:10.1108/intr-08-2023-0702 · Cited by 50
Impact of digital health interventions on glycemic control and weight management.
Veluvali, A., Dehghani Zahedani, A., Hosseinian, A., Aghaeepour, N., McLaughlin, T., Woodward, M., DiTullio, A., Hashemi, N., & Snyder, M. P. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01430-7 · Cited by 45
“The average weight reduction of 3.3 lbs over the 33-day period, with the most signi fi cant loss observed in the prediabetes cohort (4.0 lbs), indicates that digital health interventions can be effective in supporting weight management.”
InfluentialAl Shboul, M. K. I., Alwreikat, A., & Alotaibi, F. A. (2024) · Science & Technology Libraries · doi:10.1080/0194262x.2023.2250835 · Cited by 38
“…promoting health behavioral changes discovered that Chatbots could improve participants’ self-efficacy, disease knowledge, and medication adherence (Aggarwal et al. 2023) Similarly, one study found that using a Chatbot for mental health screening was effective in identifying individuals at risk of…”
Ulrich, S., Gantenbein, A. R., Zuber, V., Von Wyl, A., Kowatsch, T., & Künzli, H. (2024) · Journal of Medical Internet Research · doi:10.2196/50132 · Cited by 36
“Research has highlighted a lack of transparency in describing the handling of input data and algorithms, affecting the reliability and validity of findings [122,135].”
Bias and Inaccuracy in AI Chatbot Ophthalmologist Recommendations
Oca, M. C., Meller, L. L. T., Wilson, K., Parikh, A. O., McCoy, A., Chang, J. Y., Sudharshan, R., Gupta, S., & Zhang-Nunes, S. (2023) · Cureus · doi:10.7759/cureus.45911 · Cited by 41
Berghea, E. C., Ionescu, M. D., Gheorghiu, R. M., Ţincu, I. F., Cobilinschi, C. O., Craiu, M., Bălgrădean, M., & Berghea, F. (2024) · Children · doi:10.3390/children11020240 · Cited by 42
“In addition, AI chatbots have proven effective in health behavior change interventions across broad and varied populations [40].”
BackgroundClinical, Research, and Educational Applications of ChatGPT in Dentistry: A Narrative Review
Puleio, F., Giudice, G. L., Bellocchio, A. M., Boschetti, C. E., & Giudice, R. L. (2024) · Applied Sciences · doi:10.3390/app142310802 · Cited by 44
Büker, M., & Mercan, G. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.105948 · Cited by 44
Hauser-Ulrich, S., Lienhard, N., Künzli, H., & Kowatsch, T. (2024) · JMIR mhealth and uhealth · doi:10.2196/54945 · Cited by 58
“Research highlights the critical issue of inadequate transparency in data input and algorithms, undermining the reliability and validity of results [107,109].”
BackgroundPetrušić, I., Ha, W., Labastida‐Ramírez, A., Messina, R., Onan, D., Tana, C., & Wang, W. (2024) · The Journal of Headache and Pain · doi:10.1186/s10194-024-01847-7 · Cited by 38
“Part 1 will cover challenges in remote healthcare of headache patients with a special focus on virtual health assistants, so-called chatbots [15], and new technologies driven by AI designed to prevent or block migraine attacks.”
BackgroundEscobar-Viera, C. G., Porta, G., Coulter, R. W. S., Martina, J., Goldbach, J., & Rollman, B. L. (2023) · Internet Interventions · doi:10.1016/j.invent.2023.100668 · Cited by 34
Chen, S., Zhang, Q., Chan, C.-K., et al. (2023) · JMIR Research Protocols · doi:10.2196/48447 · Cited by 34
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 50
Jiménez-González, C., Alonso‐Peña, M., Vélez, P. A., Crespo, J., & Iruzubieta, P. (2025) · Nutrients · doi:10.3390/nu17091580 · Cited by 45
“In this context, AI is emerging as a transformative tool to enhance the effectiveness, personalization, and scalability of lifestyle interventions [17].”
Ngo, T. T. A., Phan, T. Y. N., Nguyen, T. K., Le, N. B. T., Nguyen, N. T. A., & Le, T. T. D. (2025) · Acta Psychologica · doi:10.1016/j.actpsy.2025.105468 · Cited by 65
Efficacy and empathy of AI chatbots in answering frequently asked questions on oral oncology
Rokhshad, R., Khoury, Z. H., Mohammad‐Rahimi, H., Motie, P., Price, J. B., Tavares, T., Jessri, M., Bavarian, R., Sciubba, J. J., & Sultan, A. S. (2025) · Oral Surgery Oral Medicine Oral Pathology and Oral Radiology · doi:10.1016/j.oooo.2024.12.028 · Cited by 40
Ho, P. M., Glorioso, T. J., Allen, L. A., Blankenhorn, R. K., Glasgow, R. E., Grunwald, G. K., Khanna, A. D., Magid, D. J., Marrs, J. C., Novins-Montague, S., et al. (2024) · JAMA · doi:10.1001/jama.2024.21739 · Cited by 45
Odone, A., Barbati, C., Amadasi, S., Schultz, T., & Resnik, D. B. (2025) · The Lancet Infectious Diseases · doi:10.1016/s1473-3099(25)00412-8 · Cited by 55
Saatçi, G., Korkut, S., & Ünsal, A. (2024) · Nurse Education in Practice · doi:10.1016/j.nepr.2024.104186 · Cited by 36
Hou, Z., Wu, Z., Qu, Z., Gong, L., Peng, H., Jit, M., Larson, H. J., Wu, J. T. K., & Lin, L. K. (2025) · Nature Medicine · doi:10.1038/s41591-025-03618-6 · Cited by 52
Schillings, C., Meißner, E., Erb, B., Bendig, E., Schultchen, D., & Pollatos, O. (2024) · JMIR Mental Health · doi:10.2196/50454 · Cited by 61
AI Chatbots for Psychological Health for Health Professionals: Scoping Review
Baek, G., Cha, C., & Han, J.-H. (2025) · JMIR Human Factors · doi:10.2196/67682 · Cited by 54
“However, while personalization is a key advantage of AI chatbots, a need also exists for some level of standardization to ensure the interventions’ quality and effectiveness [40].”
Akilesh, S., Sheik Abdullah, A., Abinaya, R., Dhanushkodi, S. R., & Sekar, R. (2023) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate59243.2023.10368616 · Cited by 41
“Avishek Choudhury [6] conducted a cross sectional survey from 607 participants (analysed using partial least squares structural equation modelling) to check if they would use chat-gpt a LLM based AI tool for self-diagnosis and most respondents had positive answers.”
MethodWang, A., Zhou, Y. J., Ma, H., Tang, X., Li, S., Pei, R., & Piao, M. (2024) · Digital Health · doi:10.1177/20552076241284903 · Cited by 43
Shen, J., Yu, J., Zhang, H., Lindsey, M. A., & An, R. (2025) · Journal of sport and health science/Journal of Sport and Health Science · doi:10.1016/j.jshs.2025.101045 · Cited by 37
Role of artificial intelligence in behavior management of pediatric dental patients—a mini review
Acharya, S., Godhi, B. S., Saxena, V., Assiry, A. A., Alessa, N. A., Dawasaz, A. A., Alqarni, A., & Karobari, M. I. (2024) · Journal of Clinical Pediatric Dentistry · doi:10.22514/jocpd.2024.055 · Cited by 45
“Over-reliance on technology could compromise the essential human connection and empathetic interactions pivotal in comforting anxious children [ 48, 49].”
BackgroundHoose, S., & Králiková, K. (2024) · Administrative Sciences · doi:10.3390/admsci14090227 · Cited by 47
Chatbots Utility in Healthcare Industry: An Umbrella Review
Afsahi, A. M., SeyedAlinaghi, S., Molla, A., Mirzapour, P., Jahani, S., Razi, A., Mojdeganlou, P., Karimi, E., Mehrtak, M., Dadras, O., et al. (2024) · Frontiers in Health Informatics · doi:10.30699/fhi.v13i0.561 · Cited by 27
Perioperative application of chatbots: a systematic review and meta-analysis
Lin, S.-J., Sun, C., Chen, D., Kang, Y., Lai, N. M., Chen, K., & Chen, C. (2024) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2023-100985 · Cited by 39
“The necessity of human expertise and supervision should be emphasised.”
Traylor, D., Kern, K. V., Anderson, E. E., & Henderson, R. (2025) · Cureus · doi:10.7759/cureus.76825 · Cited by 48
Santonocito, S., Cicciù, M., & Ronsivalle, V. (2025) · Clinical Oral Investigations · doi:10.1007/s00784-025-06356-8 · Cited by 33
Anser, M. K., Nabi, A. A., Ahmad, I., Abro, M. M. Q., & Zaman, K. (2025) · Health care science · doi:10.1002/hcs2.70018 · Cited by 46
Giansanti, D. (2023) · Life · doi:10.3390/life13051130 · Cited by 29
“The field of addiction was dealt with in three studies [49,57,62].”
BackgroundMethodInfluentialLuo, X., Zhang, A., Li, Y., Zhang, Z., Ying, F., Lin, R., Yang, Q., Wang, J., & Huang, G. (2024) · International Journal of Mental Health Nursing · doi:10.1111/inm.13384 · Cited by 37
Xu, Y., Liu, Q., Pang, J., Zeng, C., Ma, X., Li, P., Ma, L., Huang, J., & Xie, H. (2024) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s477452 · Cited by 37
Using ChatGPT to Improve Readability of Interventional Radiology Procedure Descriptions
Zaki, H. A., Mai, M., Abdel-Megid, H., Liew, S. Q. R., Kidanemariam, S., Omar, A., Tiwari, U., Hamze, J., Ahn, S. H., & Maxwell, A. W. P. (2024) · CardioVascular and Interventional Radiology · doi:10.1007/s00270-024-03803-z · Cited by 26
“Artificial intelligence (AI) in healthcare has already demonstrated widespread utility, such as remote patient monitoring and chatbot-guided promotion of healthy behaviors [9].”
Coelho, J., Pécune, F., Micoulaud‐Franchi, J., Bioulac, B. H., & Philip, P. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1560580 · Cited by 40
“Furthermore, chatbots can potentially reduce mental health care costs by automating routine tasks, thereby freeing up resources for more specialised interventions and reducing healthcare system burdens (33).”
InfluentialArigo, D., Jake‐Schoffman, D. E., & Pagoto, S. (2024) · Journal of Behavioral Medicine · doi:10.1007/s10865-024-00526-x · Cited by 32
“In behavioral medicine, chatbots have been used for weight management, vaccine communication, smoking cessation, and chronic disease management (Aggarwal et al., 2023; Bak & Chin, 2024; Noh et al., 2023; Passanante et al., 2023).”
The Impact and Role of Artificial Intelligence (AI) in Healthcare: Systematic Review
Singh, K., Prabhu, A. A., & Kaur, N. (2025) · Current Topics in Medicinal Chemistry · doi:10.2174/0115680266339394250225112747 · Cited by 28
Wang, Z. J., Chan, P. S.-F., Fang, Y., Yu, F.-Y., Ye, D., Zhang, Q., Wong, M. C. S., & Mo, P. K. H. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.32568 · Cited by 23
A systematic review of chatbot-assisted interventions for substance use
Lee, S., Yoon, J., Cho, Y., & Chun, J. (2024) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2024.1456689 · Cited by 31
Chatbots in higher education: a systematic review
Lambebo, E. A., & Chen, H. (2024) · Interactive Learning Environments · doi:10.1080/10494820.2024.2436931 · Cited by 37
“Another study examined the feasibility, efficacy, and intervention characteristics of AI chatbots for encouraging health behavior change (Aggarwal et al., 2023).”
Cao, Y. Y., Yin, H., Hua, X., Bi, S., & Zhou, D. (2025) · Australian Journal on Ageing · doi:10.1111/ajag.70006 · Cited by 21
“8,9 Although there is still a lack of robust and extensive research data on the intervention effects of artificial intelligence in art therapy, the integration of artificial intelligence and art therapy demonstrates promising potential.”
Artificial intelligence chatbots in endodontic education—Concepts and potential applications
Mohammad‐Rahimi, H., Setzer, F. C., Aminoshariae, A., Dummer, P. M. H., Duncan, H. F., & Nosrat, A. (2025) · International Endodontic Journal · doi:10.1111/iej.14231 · Cited by 31
“In healthcare and education, these systems have shown reliable performance that offers personalized learning experiences and supports clinical decision-making processes (Aggarwal et al., 2023; Ali et al., 2024).”
Performance of 7 Artificial Intelligence Chatbots on Board-style Endodontic Questions
Jalali, P., Mohammad‐Rahimi, H., Wang, F., Sohrabniya, F., Ourang, S. A., Tian, Y., Martinho, F. C., & Nosrat, A. (2025) · Journal of Endodontics · doi:10.1016/j.joen.2025.06.014 · Cited by 33
Investigating psychotherapists’ attitudes towards artificial intelligence in psychotherapy
Wagner, J., & Schwind, A.-S. (2025) · BMC Psychology · doi:10.1186/s40359-025-03071-7 · Cited by 35
“This interpretation aligns with recent research [85] indicating that disorder-specific chatbots can effectively facilitate smaller, targeted interventions, particularly for exercise-based therapeutic tasks.”
Digital safety plan effectiveness and use: Findings from a three-month longitudinal study
Rainbow, C., Tatnell, R., Blashki, G. A., Fuller‐Tyszkiewicz, M., & Melvin, G. A. (2024) · Psychiatry Research · doi:10.1016/j.psychres.2024.115748 · Cited by 27
Abroms, L. C., Yousefi, A., Wysota, C. N., Wu, T.-C., & Broniatowski, D. A. (2024) · Journal of Medical Internet Research · doi:10.2196/66896 · Cited by 27
Arslan, N., Esin, K., & Ayyıldız, F. (2025) · BMC Public Health · doi:10.1186/s12889-025-22507-8 · Cited by 22
“Because AI promotes healthy lifestyles such as physical activity and healthy diet, smoking cessation [21], it may encourage healthier habits, detect health problems early, and increase life satisfaction.”
Wang, K., Mirosa, M., Hou, Y., & Bremer, P. J. (2025) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2025.105050 · Cited by 41
Tilton, A. K., Caplan, B. E., & Cole, B. J. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1616488 · Cited by 31
Artificial intelligence, medications, pharmacogenomics, and ethics
Haga, S. B. (2024) · Pharmacogenomics · doi:10.1080/14622416.2024.2428587 · Cited by 33
Metadata
- Authors
- Aggarwal, A., Tam, C. C., Wu, D., Li, X., & Qiao, S.
- Affiliations
- University of South Carolina (US)
- Corresponding author
- Qiao, Shan
- Venue
- Journal of medical Internet research
- Publisher
- JMIR Publications Inc.
- Published
- 2023-02-24
- Volume
- 25
- Pages
- e40789
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC10007007
- OpenAlex
- W4321748146
- Cited by
- 683
- References
- 36
- Citations by year
- 2026: 239 · 2025: 263 · 2024: 135 · 2023: 46
- FWCI
- 34.57
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- medRxiv (acceptedVersion)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of South Carolina (BDHSC-2021-14)
- National Institutes of Health
- National Institute of Allergy and Infectious Diseases (R01AI127203)
- Topics
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- AI chatbots, health behavior change, health promotion, smoking cessation, medication adherence, substance abuse, behaviour change theory, personalized interventions, feasibility and acceptability, chatbot usability, real-time feedback
- MeSH terms
- Artificial Intelligence, Delivery of Health Care, Health Promotion, Humans, Software, Health Behavior
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (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.
