Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index; 1 of the 6 sources its claims cite were checked for support.
Abstract
Data about the quality of cancer information that chatbots and other artificial intelligence systems provide are limited. Here, we evaluate the accuracy of cancer information on ChatGPT compared with the National Cancer Institute’s (NCI’s) answers by using the questions on the “Common Cancer Myths and Misconceptions” web page. The NCI’s answers and ChatGPT answers to each question were blinded, and then evaluated for accuracy (accurate: yes vs no). Ratings were evaluated independently for each question, and then compared between the blinded NCI and ChatGPT answers. Additionally, word count and Flesch-Kincaid readability grade level for each individual response were evaluated. Following expert review, the percentage of overall agreement for accuracy was 100% for NCI answers and 96.9% for ChatGPT outputs for questions 1 through 13 (ĸ = ‒0.03, standard error = 0.08). There were few noticeable differences in the number of words or the readability of the answers from NCI or ChatGPT. Overall, the results suggest that ChatGPT provides accurate information about common cancer myths and misconceptions.
Overview
CoChat Summary
TL;DR
This brief report evaluated whether ChatGPT provides accurate answers to 13 common cancer myths and misconceptions compared with National Cancer Institute (NCI) answers. Expert reviewers found ChatGPT outputs largely accurate and similar to NCI answers, though with some hedging/uncertainty noted.
Key findings
- NCI answers were rated accurate by 5 of 5 reviewers for 13 of 13 questions, giving 100% interrater agreement.
- ChatGPT outputs were rated accurate by 5 of 5 reviewers for 11 of 13 questions, with 96.9% overall agreement; the remaining 2 questions were rated accurate by 4 of 5 reviewers (Fleiss ĸ = ‒0.03, SE = 0.08, P = .6).
- There were few noticeable differences in word count or Flesch-Kincaid readability between NCI and ChatGPT answers, though both were written at a less readable level than health literacy advocates would likely recommend.
- Five repeated runs for each of the 13 questions showed subtle sentence-structure changes but consistent answers, suggesting accuracy remained stable with repetitive questioning.
Methods
- On December 20, 2022, the authors asked ChatGPT (December 15, 2022, version) the 13 questions from the NCI “Common Cancer Myths and Misconceptions” web page.
- NCI and ChatGPT answers were blinded and independently rated for accuracy (yes vs no) by 5 scientific reviewers with expertise in cancer treatment and cancer misinformation between December 20, 2022, and January 3, 2023.
- Interrater agreement was assessed with Fleiss ĸ; word count and Flesch-Kincaid grade level were evaluated for each response, and analyses used Stata version 17.
Limitations
- The paper states that it evaluated only common cancer misinformation in English, so more obscure myths may have incomplete or English-only information and may not be answered accurately.
- The paper states that ChatGPT outputs may be trained on models that could be scientifically outdated, and ChatGPT was limited to data collected before 2021, so accuracy may be delayed as new scientific information emerges.
- Evident from the text: this was a small-scale study of 13 questions using one ChatGPT version at one time point; the authors did not code for specific message features, though multiple observers perceived hedging and uncertainty in ChatGPT messages.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 0 Not valid · 5 Not checked · 17 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“There were few noticeable differences in the number of words or the readability of the answers from NCI or ChatGPT.”
- Also stated in: § Abstract · plain
“There were few noticeable differences in the number of words or the readability of the answers from NCI or ChatGPT.”
§ Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information > Abstract
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.
- Also stated in: § Abstract · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The remaining 2 questions (question 5, “Does my attitude—positive or negative—determine my risk of getting or surviving cancer?” and question 9, “Do power lines cause cancer?”) were rated as accurate by 4 of 5 reviewers, with a single unique reviewer rating each question as inaccurate (ĸ = ‒0.03, SE = 0.08, P = .6).”
§ Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information > Abstract
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we completed 5 runs repeatedly from the same input for each of the 13 questions (Supplementary Table 1, available online). On review, although subtle sentence structure changes were noted, the answers remained consistent”
§ Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information > Abstract
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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Answers from both sources were written at a less readable rate than would likely be recommended by health literacy advocates, for example.”
§ Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information > Abstract
hedged- 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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“suggesting that answers remain accurate with repetitive questioning.”
§ Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information > Abstract
hedged- 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.
3 more claims
Create a free account to see all 23 claims and to verify the 5 references still open.
- Probably not a substantial claim. 10
- It may state two separate claims as one. 5
- The quote only partly states this claim. 1
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 cited source says what the claim attributes to it.
In the citing paper
“it was observed that ChatGPT responses were relevant and had a high level of accuracy, similar to the responses of the National Cancer Institute [32].”
From Is there any room for ChatGPT AI bot in speech-language pathology? (2025) · cites this paper as [32]
The cited source says what the claim attributes to it.
In the citing paper
“ChatGPT was shown to exhibit good performance at answering questions about cancer myths and misconceptions (159).”
From Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions (2024) · cites this paper as [159]
Citations
Cites
Measuring nominal scale agreement among many raters.
Fleiss, J. L. (1971) · Psychological Bulletin · doi:10.1037/h0031619 · Cited by 8,733 · cited 1×
“Interrater agreement was evaluated by Fleiss Œ (5).”
MethodDissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“There is concern that algorithms reinforce current health disparities and inequities (9), although the extent to which this is true about health information specifically is currently unknown.”
BackgroundChatbots in the fight against the COVID-19 pandemic
Miner, A. S., Laranjo, L., & Kocaballi, A. B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0280-0 · Cited by 322 · cited 1×
“spaces (3); recently, 1 such AI system receiving a lot of public and”
BackgroundAn Initial Model of Trust in Chatbots for Customer Service—Findings from a Questionnaire Study
Nordheim, C. B., Følstad, A., & Bjørkli, C. A. (2019) · Interacting with Computers · doi:10.1093/iwc/iwz022 · Cited by 233 · cited 1×
“Other practical considerations about how people will interpret AI-generated chat responses in terms of trust and credibility (10) exist, particularly as they relate to medical and health information, behaviors, and services compared with consumer products, behaviors, and services.”
BackgroundCancer misinformation and harmful information on Facebook and other social media: a brief report
Johnson, S. B., Parsons, M., Dorff, T., Moran, M. S., Ward, J. H., Cohen, S. A., Akerley, W., Bauman, J., Hubbard, J., Spratt, D. E., et al. (2022) · JNCI: Journal of the National Cancer Institute · doi:10.1093/jnci/djab141 · Cited by 210 · cited 1×
“JNCI Cancer Spectrum, 2023, 7(2), pkad015”
Self-citationCalixte, R., Rivera, A., Oridota, O., Beauchamp, W., & Camacho-Rivera, M. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17186856 · Cited by 112 · cited 1×
“Patients are increasingly turning to the internet for information about cancer, with 80% of US adults reportedly using the internet to seek health information (1).”
Background
Research works printed but not linked: 1
- Hundt A, Agnew W, Zeng V, Kacianka S, Gombolay M. Robots enact malignant stereotypes. FACCT’22: 2022 ACM Conference on Fairness, Accountability, and Transparency. 2022; 743- 756.
Cited by
Items 201–289 of 289
Qiu, X., Luo, C., Zhang, Q., Chung, K. Y., Chen, W., & Chen, H. (2025) · Translational Vision Science & Technology · doi:10.1167/tvst.14.8.19 · Cited by 4
Leslie, S. E., Durden, J. A., & Tevis, S. E. A. (2024) · Cancer · doi:10.1002/cncr.35651 · Cited by 3
“15 In addition, there is a responsibility for the creators of ChatGPT to use validation methods that help their GenAI model identify credible sources, and to be transparent about the origins of information and the vetting processes the tool undergoes before release to the public.”
Performance of Microsoft Copilot in the Diagnostic Process of Pulmonary Embolism
Arslan, B., Sutaşır, M. N., & Altınbilek, E. (2025) · Western Journal of Emergency Medicine · doi:10.5811/westjem.24995 · Cited by 2
“14 Furthermore, these LLMs have shown high accuracy by generating differential diagnosis lists based on provided clinical vignettes.”
Artificial Intelligence Chatbots and Their Responses to Most Searched Spanish Cancer Questions
Cheng, E., Anampa, J. D. S., Bernabe, C., Lin, J., Xue, X., Isasi, C. R., Moadel-Robblee, A. B., & Chu, E. (2025) · Cancer Medicine · doi:10.1002/cam4.71364 · Cited by 2
Effectiveness of ChatGPT to provide esophageal cancer information: A SERVQUAL-based analysis
Cheng, W., Liu, Y., Zhou, C., & Xie, C. (2025) · Digital Health · doi:10.1177/20552076251393291 · Cited by 3
Miller Fisher’s Rules and Digital Health: The Best of Both Worlds
de Andrade, J. B. C., Mendes, G. N. N., & Silva, G. S. (2024) · Cerebrovascular Diseases · doi:10.1159/000539323 · Cited by 4
Joshi, S., Ha, E., Rivera, Y. M., & Singh, V. K. (2024) · PubMed Central · doi:10.48550/arxiv.2407.09481 · Cited by 9
“This is consistent with previous studies that found that ChatGPT can generate accurate and relevant answers to health-related questions in some contexts 31,32 .”
BackgroundResultInfluentialEffects of Dietary Modifications and Physical Activity on Cancer Prevention and Treatment
Ogunlakin, A. D., Ihiasota, P. O., Ojo, O. A., Ogunlakin, M., Ogunlakin, O. A., Olujinmi, F. E., Olagookun, F. I., Ogunlakin, B., & Adeyeye, S. A. (2024) · Dietary Supplements and Nutraceuticals · doi:10.31989/dsn.v3i6.1362 · Cited by 4
ChatGPT’s Role in Gerontology Research
Kaufmann, C. N., Bai, C., Borgia, B., Leeuwenburgh, C., Lin, Y., Mardini, M., McElroy, T., Swanson, C. W., Wimberly, K., Zapata, R., et al. (2024) · The Journals of Gerontology Series A · doi:10.1093/gerona/glae184 · Cited by 4
Gonzalez, X. T., Roubaud, M. S., Schaverien, M. V., Largo, R. D., Parham, C. S., Francis, A. M., Chen, T. A., Hoffman, A. S., Dickey, R. M., Markey, M. K., et al. (2025) · Plastic & Reconstructive Surgery Global Open · doi:10.1097/gox.0000000000006625 · Cited by 3
“Recently, studies have investigated the quality of answers generated by LLMs to questions about breast cancer care, 24–26 including breast reconstruction topics.”
Washington, C. J., Divaker, J., Gould, M. K., Silvestri, G. A., Crane, T. E., Hochhegger, B., Karanth, S. D., & Braithwaite, D. (2025) · CHEST Pulmonary · doi:10.1016/j.chpulm.2025.100167 · Cited by 4
Comparative Analysis of Large Language Models for Answering Cancer-Related Questions in Korean
Chang, H. K., Jung, J.-W., & Kim, Y. (2025) · Yonsei Medical Journal · doi:10.3349/ymj.2024.0200 · Cited by 2
An Initial Examination of ChatGPT Responses to Questions About Decision Making in Advanced Cancer
McDarby, M., Mroz, E. L., Kastrinos, A. L., Bates-Pappas, G. E., Banerjee, S. C., & Parker, P. A. (2024) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2024.04.020 · Cited by 2
Kim, H.-W., Shin, D.-H., Kim, J., Lee, G.-H., & Cho, J. W. (2023) · doi:10.2196/preprints.48718 · Cited by 2
Examining ChatGPT’s Ability to Answer Cirrhosis Related Questions in Arabic Compared to EnglishPreprint
Samaan, J. S., Yeo, Y. H., Ng, W. H., Ting, P., Trivedi, H. D., Vipani, A., Yang, J. D., Liran, O., Spiegel, B. M. R., Kuo, A., et al. (2023) · medRxiv · doi:10.1101/2023.07.05.23292147 · Cited by 2
Chérrez-Ojeda, I., Robles‐Velasco, K., Osorio, M. F., Gallardo-Bastidas, J. C., Vélez-León, E. M., Velastegui, M. A. L., Pauletto, P., Aguilar-Díaz, F. D. C., Squassi, A., Eras, S. P. G., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4527770 · Cited by 2
Gökçearslan, E., Çelik, S. T., Akdeniz, E. T., & Öztürk, E. (2025) · Journal of Evidence-Based Social Work · doi:10.1080/26408066.2025.2480396 · Cited by 1
Ishida, K. (2025) · Cureus · doi:10.7759/cureus.81029 · Cited by 1
“ChatGPT is also being used in the medical field for various purposes, such as diagnostic support for common major complaints, cancer screening, automatic generation of diagnostic reports, and medical education [2-5].”
Schmidl, B., Lauterbach, M., Stögbauer, F., Mogler, C., Ribbat‐Idel, J., Perner, S., & Wollenberg, B. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26083719 · Cited by 1
“While the introduction of PD-1 inhibition has revolutionized the therapeutic landscape, there is still a response rate of only 20% for HNSCC [5,6].”
The Role of Artificial Intelligence in Misinformation: Study of Selected Indian Metropolitan Cities
Needhipathi, J. J., Kumar, S., & Karim, S. (2025) · doi:10.1109/icoact63339.2025.11005340 · Cited by 1
“In light of all the data, it is clear that ChatGPT corrects frequent misunderstandings regarding cancer [4].”
A Study on Medical Diagnosis with Help of LLM: Advancement in Disease Detection
Karthikeyan, R. S., Dharshne, M., Mohanasundari, M., Hariharan, K., Prathika, T. V., & Deepa, S. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-78937-3_15 · Cited by 1
Usage of ChatGPT on English Language Skills of Students at Maputi Senior High School
Lariosa, J., Bajao, K., Talaroc, J., Amancio, E., Buna, J., & Villarin, S. J. (2025) · Psychology and Education A Multidisciplinary Journal · doi:10.70838/pemj.430309 · Cited by 3
From Evidence to Recommendations With Large Language Models: A Feasibility Study
Zhao, W., Xia, D., Ye, Z., Lai, H., Sun, M., Huang, J., Liu, J., Liu, J., & Ge, L. (2025) · Journal of Evidence-Based Medicine · doi:10.1111/jebm.70067 · Cited by 1
“AI can provide actionable suggestions for clinicians, support decision-making, and improve treatment outcomes [3, 21, 22], demonstrating good application potential in the medical question-and-answer field [23–26].”
Prazeres, F. (2025) · Psychiatry International · doi:10.3390/psychiatryint6040135 · Cited by 1
“The ability of LLMs to set straight health-related myths has also been validated in other areas, such as cancer [15], Alzheimer’s disease [16], and diabetes [17].”
Evaluation of AI chatbot responses to brachytherapy frequently asked questions
Kouzy, R., İbrahim, Nemr, P., Vinjamuri, S., Ballout, B., Diaz, J. S. G. G., Figueroa, D. N., Alam, M. B. E., Kouzi, Z. E., Hassanzadeh, C., et al. (2025) · Brachytherapy · doi:10.1016/j.brachy.2025.10.005 · Cited by 3
Yin, C., Sun, X., Dai, A., Ye, X., Lu, Y., Wang, W., Chen, Y., Jiang, H., Yu, J., Chong, S., et al. (2026) · APL Bioengineering · doi:10.1063/5.0299327 · Cited by 2
Sümbüllü, M., Adam, E. O., ALTUN, E. A., & Arslan, H. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08327-1 · Cited by 2
“This is particularly important in health-related materials, as misunderstanding such information may adversely affect patients [55].”
Kollayan, B. Y., & Cebeci, T. (2026) · BMC Oral Health · doi:10.1186/s12903-026-08530-0 · Cited by 1
“Previous studies have demonstrated the potential of LLMs in this domain[20–22].”
Shah, J., Wells-Gatnik, W. D., Palmer, B., Acharya, P., & Cheungpasitporn, W. (2026) · Frontiers in Nephrology · doi:10.3389/fneph.2026.1857793 · Cited by 2
Artificial Intelligence and Cerebrovascular Diseases: ChatGPT Model
Altunışık, E. (2023) · Cerebrovascular Diseases · doi:10.1159/000533967 · Cited by 2
Perioperative Management of Patients on Buprenorphine: A Literature Review
Furtado-Pessoa-de-Mendonca, L., Hunt, C., Mosquera‐Moscoso, J., Encalada, S., Prokop, L. J., Pai, S., & Eldrige, J. S. (2024) · Current anesthesiology reports · doi:10.1007/s40140-024-00612-5 · Cited by 1
“This mechanism allows patients using BpN to experience relief from cravings and withdrawal symptoms, with a lower risk of respiratory depression and reduced abuse potential [5, 8].”
ChatGPT/GPT-4 in Healthcare: Potential Opportunities and Limitations
Wang, R. (2024) · Placenta and Reproductive Medicine · doi:10.54844/prm.2024.0528 · Cited by 1
Will ChatGPT be Useful for Korean Neurologists in Clinical Practice?
Ko, P. (2024) · Journal of the Korean Neurological Association · doi:10.17340/jkna.2024.0029 · Cited by 2
Chirino, A., Cabral, G., Cavallazzi, R., Prado, J., Chandler, T. R., Furmanek, S. P., Mattingly, W. A., Wiemken, T. L., Carrico, R., Song, M., et al. (2024) · Norton Healthcare Medical Journal · doi:10.59541/001c.127927 · Cited by 1
Responses of Artificial Intelligence Chatbots to Testosterone Replacement Therapy: Patients Beware!
Pabla, H., Lange, A., Nadiminty, N., & Sindhwani, P. (2025) · Société Internationale d’Urologie Journal · doi:10.3390/siuj6010013 · Cited by 1
“From a physician’s perspective, it is essential to recognize the limitations of these chatbots and engage in thorough discussions with patients to dispel common myths and misconceptions.”
ChatGPT in Dermatology: A Comprehensive Systematic Review (Preprint)Preprint
Gabashvili, I. S. (2023) · doi:10.2196/preprints.48979 · Cited by 2
Ray, P. P. (2023) · JNCI Cancer Spectrum · doi:10.1093/jncics/pkad053 · Cited by 1
“These studies must account for the unique characteristics of each platform, such as the static knowledge base of ChatGPT vs the dynamic internet access of search engines (2,3).”
Applications of GPT in Cancer for Screening, Diagnosis and Treatment - A Global Comprehensive ReviewPreprint
Xu, P., Xu, A., Chai, Z., Xu, H., Xu, A., Huang, J., Kong, X., Huo, Y., Ge, Z., & Zhang, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4885555 · Cited by 1
Tang, T., Li, A. K. C., Tan, X., Ji, Q., Si, L., & Bao, L. (2025) · medRxiv · doi:10.1101/2025.04.07.25325243 · Cited by 1
“LLMs have significantly impacted various aspects of clinical trials and medical documentation [2, 3], including clinical trial planning [4, 5], patient-trial matching [6], technical writing [7], clinical decision making [8, 9], and medical queries [10, 11].”
Assessing the utility of artificial intelligence throughout the triage outpatientsPreprint
Liu, X., Lai, R., Yan, C., Jing, H., & Zhang, W. (2023) · Research Square · doi:10.21203/rs.3.rs-2957289/v1
Andalib, S., Spina, A., Halaseh, F. F., Vermani, R., Liang, J., & Wiechmann, W. F. (2023) · doi:10.2196/preprints.51209
Alamrain, A. A., Adewunmi, M. A., Amrain, M. A. A., Wong, M. C., & Yee, K. C. (2023) · doi:10.2196/preprints.51444
(2023) · Advances in educational technologies and instructional design book series · doi:10.4018/978-1-6684-9300-7.ch013
O ChatGPT na educação em saúde de pessoas com estomias intestinais: Potencialidades e controvérsias
Júnior, A. J. S. C., Teles, A. A. D. S., Lima, L. D. E. S., de Lima, F. C., Reis, R. K., de Santana, M. E., & Sonobe, H. M. (2023) · Temas em Educação e Saúde · doi:10.26673/tes.v19i00.18435
TBHEB 2023-4 Vol 80 Full Printed Journal
ERCÖMERT, U. (2023) · Turkish Bulletin of Hygiene and Experimental Biology · doi:10.5505/turkhijyen.2023.97572
Ye, Z., Lai, H., Sun, M., Huang, J., Liu, J., Xia, D., Zhao, W., Liu, J., & Ge, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4756038
Alamrain, A. A., Adewunmi, M. A., Amrain, M. A. A., Wong, M. C., & Yee, K. C. (2023) · JMIR Cancer · doi:10.2196/51444
Debunking Myths and Misconceptions in the Healthcare Sector: A ChatGPT-Powered Evaluation
Rao, C. V. G., Sastri, A., Pillai, R. H., Thangam, M. M. N., Kathwal, J., & Banappagoudar, S. B. (2024) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-2716-2_28
Xu, A., Chai, Z., Sun, C., Xu, H., Xu, A., Huang, J., Kong, X., Ge, Z., Huo, Y., & Zhang, L. (2024) · doi:10.2196/preprints.66857
Bernstein, E., Ramsamooj, A., Miller, K. L., & Lum, Z. C. (2024) · doi:10.2196/preprints.68603
Analysis of Japanese Clinical Engineer License Examinations using ChatGPT (GPT-4V)
石田, 開., 有阪, 直., & 藤井, 清. (2024) · JAPANES JOURNAL OF MEDICAL INSTRUMENTATION · doi:10.4286/jjmi.94.514
Communication for Cancer Control
Wiljer, D., & Kane, G. M. (2025) · doi:10.1002/9781394191369.ch6.2
ChatGPT in Education and Healthcare: Applications, Challenges, and Ethical Implications
Liu, S. (2025) · Applied and Computational Engineering · doi:10.54254/2755-2721/2025.kl22304 · Cited by 1
Estrada-Mendizábal, R. J., Cojuc‐Konigsberg, G., Labib, E. N., Cruz, C., Gonzalez‐Estrada, A., Cuervo‐Pardo, L., Zwiener, R. D., & Canel-Paredes, A. (2025) · The Journal of Allergy and Clinical Immunology In Practice · doi:10.1016/j.jaip.2025.02.022
ChatGPT Is Scoring Better Than Surgeons in Its Responses to Thyroid-Related Patient Questions
Taylor, G. A., & Dream, S. Y. (2025) · Clinical Thyroidology · doi:10.1089/ct.2025;37.176-178
Observed Correction Increases Accuracy
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0003
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0005
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.002.0006
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0009
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0008
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0007
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0001
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.002.0009
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0004
The Theory of Observed Correction
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0002 · Cited by 1
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0006
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.003.0010
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.002.0007
Bode, L., & Vraga, E. K. (2025) · Oxford University Press eBooks · doi:10.1093/oso/9780197565896.002.0004
AVALIAÇÃO DAS RESPOSTAS DO CHATGPT A DÚVIDAS RELACIONADAS À INTRODUÇÃO ALIMENTAR
Pinheiro, R. B. M., Schmidt, L., Alvim, V. F., & Grünewald, S. T. F. (2025) · Arquivos de Ciências da Saúde da UNIPAR · doi:10.25110/arqsaude.v29i2.2025-11628 · Cited by 1
Ahmed, H. S., Suhas, D., D’Souza, L., Jayaram, P. R., Gupta, A. K., & Sache, M. S. (2025) · General Thoracic and Cardiovascular Surgery · doi:10.1007/s11748-025-02203-5 · Cited by 1
“Moreover, our study examined the questions from multiple angles, whereas previous studies typically evaluated accuracy based on a single measure involving two or three reviewers [3] and a single readability metric [30].”
Khan, W. A., Soomro, M. Y., Afzal, M., & Zaki, A. (2025) · Research Square · doi:10.21203/rs.3.rs-7472185/v1
Auditing TikTok’s recommendations: Understanding the prevalence of misinformation on the platform
Gunasekara, S., Pareek, S., Kelly, R., Kostakos, V., & Gonçalves, J. (2026) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2026.103929
Yılmaz, F. H., Büyükeren, M., Özcan, B., Keçeci, R., & Körez, M. K. (2026) · Journal of Pediatric Ophthalmology & Strabismus · doi:10.3928/01913913-20251111-01
The Impact of AI‐Generated Content on Decision Making for Topics Requiring Expertise
Li, S., Chen, T., & Demartini, G. (2026) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/3410621
Verawati, Y., Rahmat, A., & Sanjaya, Y. (2025) · Jurnal Penelitian Pendidikan IPA · doi:10.29303/jppipa.v11i2.8694 · Cited by 1
“The results were found in studies on the use of ChatGPT in several fields, such as those conducted by Hopkins et al. (2023), Johnson et al. (2023), and Kleesiek et al. (2023).”
Zheng, X., Lai, Y., Yi, J., Li, Z., Zhao, J., & Hu, L. (2026) · BMC Gastroenterology · doi:10.1186/s12876-026-04827-0
“It is noteworthy that the aforementioned four LLMs can not only enhance the efficiency of healthcare professionals but also improve public awareness of diseases and self-management, thereby transforming the landscape of information aggregation and dissemination within the healthcare sector [27].”
AI in cancer education and screening: Improving patient awareness and quality of life
Sharma, D., Pal, D., & Sharma, L. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-45004-4.00001-3
Yang, Q., Dong, Z., Yang, Y., Liu, J.-Y., Cai, L., Bai, N., & Wang, T. (2026) · Intelligent Pharmacy · doi:10.1016/j.ipha.2026.05.003
Zhang, J., Ren, W., Chen, H., Song, Y., Feng, J., Zhan, X., Chen, S., Ouyang, L., Liu, F., Cai, X., et al. (2026) · doi:10.2196/preprints.101283
Zhou, J., & Zhou, T. (2026) · Philosophy of engineering and technology · doi:10.1007/978-981-95-8023-1_8 · Cited by 1
Anand, R., Semple, C. J., Strutt, L., Paul, S., & Hanna, J. R. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001493 · Cited by 1
“[79] Consequently, people with cancer are obtaining information from digital and AI sources where powerful algorithms are shaping what content is provided, regardless of what the person actually needs [39].”
Aşut, Ö., Çalı, Ş., Cynthia, A. N., Awad, R. A. O., Muhammad, H. S., Usman, A. S., & Husain, H. A. U. (2026) · Research Square · doi:10.21203/rs.3.rs-9880300/v1
Acıpınar, Ş., Şahinbaş, M., Aydın, İ. S., & Yalcin, M. (2026) · Sağlık Bilimleri Dergisi · doi:10.34108/eujhs.1817475
Zuo, X., Zuo, H., Zhang, M., & Zheng, W. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1926980
“For patient-facing TBI health information, future models should not only provide accurate content but also clearly state the limits of general advice, cite reliable sources when possible, and distinguish general educational information from individualized clinical decision-making (26, 27, 31, 32).”
Gu, L., Gong, Z., Qian, X., Miao, L., & Gu, Z. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1942799
“Evaluations involving patients and caregivers are also needed to determine whether the questions reflect their priorities, whether the answers are understood as intended, and whether chatbot advice changes help-seeking or self-management behavior (34).”
Altunpak, B. (2026) · Surgical Innovation · doi:10.1177/15533506261488588
Chen, Z., Liu, W., Zhang, J., Zheng, T., Li, Y., Bao, Q., Ji, P., Yao, H., & He, Y. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1945318
Metadata
- Authors
- Johnson, S. B., King, A. J., Warner, E. L., Aneja, S., Kann, B. H., & Bylund, C. L.
- Affiliations
- University of Utah (US)
- Yale University (US)
- Brigham and Women's Hospital (US)
- University of Florida Health (US)
- Corresponding author
- Johnson, Skyler B
- Venue
- JNCI Cancer Spectrum
- Publisher
- Oxford University Press (OUP)
- Published
- 2023-03-01
- Volume
- 7
- Issue
- 2
- ISSN
- 2515-5091 (ISSN-L)
- PMC
- PMC10020140
- OpenAlex
- W4327681325
- Cited by
- 289
- References
- 6
- Citations by year
- 2026: 21 · 2025: 77 · 2024: 116 · 2023: 75
- FWCI
- 11.54
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- JNCI Cancer Spectrum (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Huntsman Cancer Institute
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › General Health Professions › Health Literacy and Information Accessibility
- Social Sciences › Health › Social Media in Health Education
- Keywords
- ChatGPT, cancer myths, cancer misconceptions, artificial intelligence, chatbots, health information accuracy, National Cancer Institute, information quality, readability
- MeSH terms
- Artificial Intelligence, Humans, Neoplasms, United States, National Cancer Institute (U.S.)
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.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.