A framework for human evaluation of large language models in healthcare derived from literature review.
Open accessThe DOI matches its Crossref record; 107 of the 107 references it cites were found in a registry or an index.
Abstract
With generative artificial intelligence (GenAI), particularly large language models (LLMs), continuing to make inroads in healthcare, assessing LLMs with human evaluations is essential to assuring safety and effectiveness. This study reviews existing literature on human evaluation methodologies for LLMs in healthcare across various medical specialties and addresses factors such as evaluation dimensions, sample types and sizes, selection, and recruitment of evaluators, frameworks and metrics, evaluation process, and statistical analysis type. Our literature review of 142 studies shows gaps in reliability, generalizability, and applicability of current human evaluation practices. To overcome such significant obstacles to healthcare LLM developments and deployments, we propose QUEST, a comprehensive and practical framework for human evaluation of LLMs covering three phases of workflow: Planning, Implementation and Adjudication, and Scoring and Review. QUEST is designed with five proposed evaluation principles: Quality of Information, Understanding and Reasoning, Expression Style and Persona, Safety and Harm, and Trust and Confidence.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures









Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“Healthcare evaluation frameworks already stress reliability, generalizability, human evaluation, safety, harm, trust, and confidence [24].”
From Machine Psychometrics: A Mathematical Psychology of Artificial Intelligence (2026) · cites this paper as [24]
In the citing paper
“Tam et al. 168 reviewed 142 papers on the human evaluation of LLM application in healthcare in general and find that generalizability, applicability, and reliability are lacking in current evaluation practices”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [168]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · cited 1×
“Wealsoexcludedstudieswhichexamine onlynon-generativepretrainedlanguagemodelslikeBERT 59 , RoBERTa 60 , etc. and multimodal studies such as image-to-text or text-to-image application of generative LLMs.”
BackgroundLearning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 1×
“There are also technical advancements of multimodal LLMs and text-to-image foundational models such as CLIP 58 .”
BackgroundBeyond Accuracy: What Data Quality Means to Data Consumers
Wang, R. Y., & Strong, D. M. (1996) · Journal of Management Information Systems · doi:10.1080/07421222.1996.11518099 · Cited by 4,672
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Charnock, D., Shepperd, S., Needham, G., & Gann, R. (1999) · Journal of Epidemiology and Community Health · doi:10.1136/jech.53.2.105 · Cited by 3,329
Ayers, J. W., Poliak, A., Dredze, M., Leas, E. C., Zhu, Z., Kelley, J. B., Faix, D. J., Goodman, A. M., Longhurst, C. A., Hogarth, M., et al. (2023) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.1838 · Cited by 2,613
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Gilson, A., Safranek, C. W., Huang, T., Socrates, V., Chi, L., Taylor, R. A., & Chartash, D. (2023) · JMIR Medical Education · doi:10.2196/45312 · Cited by 2,078 · cited 1×
“Gilson et al. 50 executed a thorough examination of outputs from ChatGPTacrosssituationsextractedfromUSMLE 50 .”
BackgroundChecklist for Artificial Intelligence in Medical Imaging (CLAIM): a guide for authors and reviewers
Mongan, J., Moy, L., & Kahn, C. E. (2020) · Radiology: Artificial Intelligence · doi:10.1148/ryai.2020200029 · Cited by 1,443
Shoemaker, S. J., Wolf, M. S., & Brach, C. (2014) · Patient Education and Counseling · doi:10.1016/j.pec.2014.05.027 · Cited by 1,322
Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist.
Norgeot, B., Quer, G., Beaulieu-Jones, B. K., Torkamani, A., Dias, R., Gianfrancesco, M., Arnaout, R., Kohane, I. S., Saria, S., Topol, E., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-1041-y · Cited by 665
Evaluating large language models on medical evidence summarization
Tang, L., Sun, Z., Idnay, B., Nestor, J. G., Soroush, A., Elias, P. A., Xu, Z., Ding, Y., Durrett, G., Rousseau, J. F., et al. (2023) · npj Digital Medicine · doi:10.1038/s41746-023-00896-7 · Cited by 423
Self-citationEvaluating Large Language Models on Medical Evidence Summarization
Tang, L., Sun, Z., Idnay, B., Nestor, J. G., Soroush, A., Elias, P. A., Xu, Z., Ding, Y., Durrett, G., Rousseau, J., et al. (2023) · doi:10.1101/2023.04.22.23288967 · Cited by 423
Self-citationUsing AI-generated suggestions from ChatGPT to optimize clinical decision support
Liu, S., Wright, A. P., Patterson, B. L., Wanderer, J. P., Turer, R. W., Nelson, S. D., McCoy, A. B., Sittig, D. F., & Wright, A. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad072 · Cited by 397 · cited 1×
“Liu et al. combined the -Whitne- Manny Wilcoxon test and the Kruskal – Wallis test for evaluating the reviewer ratings for the AI-generated suggestions 5 .”
MethodHirosawa, T., Harada, Y., Yokose, M., Sakamoto, T., Kawamura, R., & Shimizu, T. (2023) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph20043378 · Cited by 343
Sounderajah, V., Ashrafian, H., Golub, R. M., Shetty, S., De Fauw, J., Hooft, L., Moons, K., Collins, G., Moher, D., Bossuyt, P. M., et al. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-047709 · Cited by 333
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.870 · Cited by 331
Can Large Language Models Be an Alternative to Human Evaluations?
Chiang, C.-H., & Lee, H.-Y. (2023) · arXiv · doi:10.48550/arxiv.2305.01937 · Cited by 331
ChatGPT outperforms humans in emotional awareness evaluations
Elyoseph, Z., Hadar-Shoval, D., Asraf, K., & Lvovsky, M. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1199058 · Cited by 324 · cited 1×
“52 usedICCtoassess rater agreement and diagnostic capabilities.”
Holistic Evaluation of Language Models
Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, Y., Narayanan, D., Wu, Y., Kumar, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2211.09110 · Cited by 255
Bernstein, I. A., Zhang, Y. (., Govil, D., Majid, I., Chang, R. T., Sun, Y., Shue, A., Chou, J. C., Schehlein, E., Christopher, K. L., et al. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.30320 · Cited by 247 · cited 1×
“The studies by Tang et al. 34 , Moramarco et al. 35 , Bernstein et al. 36 , and Hirosawaetal.”
Giannakopoulos, K., Kavadella, A., Aaqel Salim, A., Stamatopoulos, V., & Kaklamanos, E. G. (2023) · Journal of Medical Internet Research · doi:10.2196/51580 · Cited by 227
Large language model (ChatGPT) as a support tool for breast tumor board
Sorin, V., Klang, E., Sklair-Levy, M., Cohen, I., Zippel, D. B., Balint Lahat, N., Konen, E., & Barash, Y. (2023) · npj Breast Cancer · doi:10.1038/s41523-023-00557-8 · Cited by 218
Sivarajkumar, S., Kelley, M., Samolyk-Mazzanti, A., Visweswaran, S., & Wang, Y. (2024) · JMIR Medical Informatics · doi:10.2196/55318 · Cited by 213
Self-citationThe Potential and Concerns of Using AI in Scientific Research: ChatGPT Performance Evaluation
Khlaif, Z. N., Mousa, A., Hattab, M. K., Itmazi, J., Hassan, A. A., Sanmugam, M., & Ayyoub, A. (2023) · JMIR Medical Education · doi:10.2196/47049 · Cited by 205
Evaluation of ChatGPT-generated medical responses: A systematic review and meta-analysis
Wei, Q., Yao, Z., Cui, Y., Wei, B., Jin, Z., & Xu, X. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104620 · Cited by 201 · cited 1×
“Wei et al. 13 reviewed 60 articles that used ChatGPT ’ s responses to medical questions to assess the performance of ChatGPT in medical Question-Answering (QA).”
Applicability of ChatGPT in Assisting to Solve Higher Order Problems in Pathology
Sinha, R. K., Deb Roy, A., Kumar, N., & Mondal, H. (2023) · Cureus · doi:10.7759/cureus.35237 · Cited by 187 · cited 1×
“Evaluates the complexity and depth of LLM responses tomedical queries, ranging from basic factual information to more advanced, integrated understanding 98 .”
BackgroundAssessing the research landscape and clinical utility of large language models: a scoping review
Park, Y.-J., Pillai, A., Deng, J., Guo, E., Gupta, M., Paget, M., & Naugler, C. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02459-6 · Cited by 187
Chou, R., Aronson, N., Atkins, D., Ismaila, A. S., Santaguida, P., Smith, D. H., Whitlock, E., Wilt, T. J., & Moher, D. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2008.06.007 · Cited by 184
Deiana, G., Dettori, M., Arghittu, A., Azara, A., Gabutti, G., & Castiglia, P. (2023) · Vaccines · doi:10.3390/vaccines11071217 · Cited by 168
Large Language Models for Therapy Recommendations Across 3 Clinical Specialties: Comparative Study
Wilhelm, T. I., Roos, J., & Kaczmarczyk, R. (2023) · Journal of Medical Internet Research · doi:10.2196/49324 · Cited by 133
Kavadella, A., Dias da Silva, M. A., Kaklamanos, E. G., Stamatopoulos, V., & Giannakopoulos, K. (2024) · JMIR Medical Education · doi:10.2196/51344 · Cited by 133 · cited 1×
“28 , in which they assessedChatGPT for undergraduate dental education.”
BackgroundSallam, M., Salim, N. A., Al-Tammemi, A. B., Barakat, M., Fayyad, D., Hallit, S., Harapan, H., Hallit, R., & Mahafzah, A. (2023) · Cureus · doi:10.7759/cureus.35029 · Cited by 130
Roosan, D., Padua, P., Khan, R., Khan, H., Verzosa, C., & Wu, Y. (2024) · Journal of the American Pharmacists Association · doi:10.1016/j.japh.2023.11.023 · Cited by 121
Is ChatGPT accurate and reliable in answering questions regarding head and neck cancer?
Kuşcu, O., Pamuk, A. E., Sütay Süslü, N., & Hosal, S. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1256459 · Cited by 117
Cadamuro, J., Cabitza, F., Debeljak, Z., De Bruyne, S., Frans, G., Perez, S. M., Ozdemir, H., Tolios, A., Carobene, A., & Padoan, A. (2023) · Clinical Chemistry and Laboratory Medicine (CCLM) · doi:10.1515/cclm-2023-0355 · Cited by 116
Hatia, A., Doldo, T., Parrini, S., Chisci, E., Cipriani, L., Montagna, L., Laganà, G., Guenza, G., Agosta, E., Vinjolli, F., et al. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13030735 · Cited by 112
Sallam, M., Barakat, M. M., & Sallam, M. (2024) · Interactive Journal of Medical Research · doi:10.2196/54704 · Cited by 105
Gordon, E. B., Towbin, A. J., Wingrove, P., Shafique, U., Haas, B., Kitts, A. B., Feldman, J., & Furlan, A. (2024) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2023.09.011 · Cited by 100
Cheong, R. C. T., Unadkat, S. N., Mcneillis, V., Williamson, A., Joseph, J., Randhawa, P. S., Andrews, P. J., & Paleri, V. (2023) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-023-08319-9 · Cited by 99
Lahat, A., Shachar, E., Avidan, B., Glicksberg, B., & Klang, E. (2023) · Diagnostics · doi:10.3390/diagnostics13111950 · Cited by 92
ChatGPT vs Google for Queries Related to Dementia and Other Cognitive Decline: Comparison of Results
Hristidis, V., Ruggiano, N., Brown, E. L., Ganta, S. R. R., & Stewart, S. (2023) · Journal of Medical Internet Research · doi:10.2196/48966 · Cited by 90
Assessing the Value of ChatGPT for Clinical Decision Support Optimization
Liu, S., Wright, A. P., Patterson, B. L., Wanderer, J. P., Turer, R. W., Nelson, S. D., McCoy, A. B., Sittig, D. F., & Wright, A. (2023) · doi:10.1101/2023.02.21.23286254 · Cited by 90
Song, H., Xia, Y., Luo, Z., Liu, H., Song, Y., Zeng, X., Li, T., Zhong, G., Li, J., Chen, M., et al. (2023) · Journal of Medical Systems · doi:10.1007/s10916-023-02021-3 · Cited by 81
Madrid-García, A., Rosales-Rosado, Z., Freites-Nuñez, D., Pérez-Sancristóbal, I., Pato-Cour, E., Plasencia-Rodríguez, C., Cabeza-Osorio, L., Abasolo-Alcázar, L., León-Mateos, L., Fernández-Gutiérrez, B., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-49483-6 · Cited by 79
Seth, I., Lim, B., Xie, Y., Cevik, J., Rozen, W. M., Ross, R. J., & Lee, M. (2023) · Aesthetic Surgery Journal Open Forum · doi:10.1093/asjof/ojad084 · Cited by 78
Truhn, D., Weber, C. D., Braun, B. J., Bressem, K., Kather, J. N., Kuhl, C., & Nebelung, S. (2023) · Scientific Reports · doi:10.1038/s41598-023-47500-2 · Cited by 71
Yuan, M., Bao, P., Yuan, J., Shen, Y., Chen, Z., Xie, Y., Zhao, J., Li, Q., Chen, Y., Zhang, L., et al. (2024) · Medicine Plus · doi:10.1016/j.medp.2024.100030 · Cited by 70
Exploring the Possible Use of AI Chatbots in Public Health Education: Feasibility Study
Baglivo, F., De Angelis, L., Casigliani, V., Arzilli, G., Privitera, G. P., & Rizzo, C. (2023) · JMIR Medical Education · doi:10.2196/51421 · Cited by 69
Ghosh, A., & Bir, A. (2023) · Cureus · doi:10.7759/cureus.37023 · Cited by 67 · cited 2×
“Ghosh et al. 26 took this a step further, demonstrating through statistical analysis that LLMs can address higher-order problems related to medical biochemistry.”
BackgroundInfluentialMaillard, A., Micheli, G., Lefevre, L., Guyonnet, C., Poyart, C., Canouï, E., Belan, M., & Charlier, C. (2024) · Clinical Infectious Diseases · doi:10.1093/cid/ciad632 · Cited by 64
Sallam, M., Barakat, M., & Sallam, M. (2023) · Cureus · doi:10.7759/cureus.49373 · Cited by 63
Seth, I., Xie, Y., Rodwell, A., Gracias, D., Bulloch, G., Hunter-Smith, D. J., & Rozen, W. M. (2023) · The Journal of Hand Surgery · doi:10.1016/j.jhsa.2023.07.003 · Cited by 62
Diagnostic and Management Applications of ChatGPT in Structured Otolaryngology Clinical Scenarios
Qu, R. W., Qureshi, U., Petersen, G., & Lee, S. C. (2023) · OTO Open · doi:10.1002/oto2.67 · Cited by 62 · cited 1×
“Additionally, 5-point Likert scales have been utilized to capture the perceptions of evaluators regarding the quality of simpli fi ed medical reportsgenerated by LLMs 47 .”
MethodHillmann, H. A. K., Angelini, E., Karfoul, N., Feickert, S., Müller‐Leisse, J., & Duncker, D. (2023) · EP Europace · doi:10.1093/europace/euad369 · Cited by 61
Examining ChatGPT Performance on USMLE Sample Items and Implications for Assessment
Yaneva, V., Baldwin, P., Jurich, D. P., Swygert, K., & Clauser, B. E. (2024) · Academic Medicine · doi:10.1097/acm.0000000000005549 · Cited by 60 · cited 2×
“Thesecond most common application, medical education and examination (24.8%), was explored by researchers like Yaneva et al. 24 , Wu et al. 25 , and Ghosh et al. 26 .”
BackgroundInfluentialChatGPT: Can You Prepare My Patients for [18F]FDG PET/CT and Explain My Reports?
Rogasch, J. M. M., Metzger, G., Preisler, M., Galler, M., Thiele, F., Brenner, W., Feldhaus, F., Wetz, C., Amthauer, H., Furth, C., et al. (2023) · Journal of Nuclear Medicine · doi:10.2967/jnumed.123.266114 · Cited by 58
Martindale, A. P. L., Llewellyn, C. D., de Visser, R. O., Ng, B., Ngai, V., Kale, A. U., di Ruffano, L. F., Golub, R. M., Collins, G. S., Moher, D., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45355-3 · Cited by 58
Knowledge grounded medical dialogue generation using augmented graphs
Varshney, D., Zafar, A., Behera, N. K., & Ekbal, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-29213-8 · Cited by 55 · cited 1×
“Sallam et al. 53 and Varshney et al. 54 have used a combination of t -tests and Cohen ’ s kappa to identify potential sources of disagreement, such as ambiguity in the evaluation guidelines or differences in interpretations.”
MethodXie, Y., Seth, I., Hunter‐Smith, D. J., Rozen, W. M., & Seifman, M. A. (2024) · ANZ Journal of Surgery · doi:10.1111/ans.18666 · Cited by 55
Schmidt, S., Zimmerer, A., Cucos, T., Feucht, M. J., & Navas, L. (2023) · Archives of Orthopaedic and Trauma Surgery · doi:10.1007/s00402-023-05113-4 · Cited by 55 · cited 3×
“It is used to determine the statistical signi fi cance of the differences observed between an LLM ’ s performance and a benchmark 39,76 .”
BackgroundMethodInfluentialChatGPT and Patient Information in Nuclear Medicine: GPT-3.5 Versus GPT-4
Currie, G., Robbie, S., & Tually, P. (2023) · Journal of Nuclear Medicine Technology · doi:10.2967/jnmt.123.266151 · Cited by 54
Ayub, I., Hamann, D., Hamann, C. R., & Davis, M. J. (2023) · Cureus · doi:10.7759/cureus.43717 · Cited by 53
Xie, Y., Seth, I., Rozen, W. M., & Hunter-Smith, D. J. (2023) · Aesthetic Plastic Surgery · doi:10.1007/s00266-023-03443-7 · Cited by 51
ChatGPT performance in laryngology and head and neck surgery: a clinical case-series
Lechien, J. R., Georgescu, B. M., Hans, S., & Chiesa-Estomba, C. M. (2023) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-023-08282-5 · Cited by 51
Comparison of Large Language Models in Answering Immuno-Oncology Questions: A Cross-Sectional Study
Iannantuono, G. M., Bracken-Clarke, D., Karzai, F., Choo-Wosoba, H., Gulley, J. L., & Floudas, C. S. (2024) · The Oncologist · doi:10.1093/oncolo/oyae009 · Cited by 51
Shao, C.-Y., Li, H., Liu, X.-L., Li, C., Yang, L.-Q., Zhang, Y.-J., Luo, J., & Zhao, J. (2023) · Interactive Journal of Medical Research · doi:10.2196/46900 · Cited by 49
Anastasio, A. T., Mills, F. B., Karavan, M. P., & Adams, S. B. (2023) · Foot & Ankle Orthopaedics · doi:10.1177/24730114231209919 · Cited by 49
Riedel, M., Kaefinger, K., Stuehrenberg, A., Ritter, V., Amann, N., Graf, A., Recker, F., Klein, E., Kiechle, M., Riedel, F., et al. (2023) · Frontiers in Medicine · doi:10.3389/fmed.2023.1296615 · Cited by 49 · cited 1×
“Assesses the overall data quality of the medical information generated by LLMs, from the perspective of healthcare professionals and patients 100 .”
BackgroundExploring Capabilities of Large Language Models such as ChatGPT in Radiation Oncology
Dennstädt, F., Hastings, J., Putora, P. M., Vu, E., Fischer, G. F., Süveg, K., Glatzer, M., Riggenbach, E., Hà, H.-L., & Cihoric, N. (2024) · Advances in Radiation Oncology · doi:10.1016/j.adro.2023.101400 · Cited by 48 · cited 1×
“In contrast, Dennstadt et al. utilized blinded evaluations speci fi cally for multiple-choice questions, determining the proportion of correct answers provided by the LLM 51 .”
BackgroundChoi, W. (2023) · BMC Medical Education · doi:10.1186/s12909-023-04832-x · Cited by 48 · cited 1×
“27 ,inwhichtheyassessedChatGPT as a self-learning tool in pharmacology, and Kavadella etal.”
MethodPersonalized Impression Generation for PET Reports Using Large Language Models
Tie, X., Shin, M., Pirasteh, A., Ibrahim, N., Huemann, Z., Castellino, S. M., Kelly, K. M., Garrett, J., Hu, J., Cho, S. Y., et al. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-00985-3 · Cited by 46
Yun, J. Y., Kim, D. J., Lee, N., & Kim, E. K. (2023) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2023.105219 · Cited by 43 · cited 3×
“ANOVA Astatisticaltestusedtodetermineifthereareanystatisticallysigni fi cantdifferencesbetweenthemeansof two or more independent groups 78,82 .”
BackgroundAvailability of ChatGPT to provide medical information for patients with kidney cancer
Choi, J., Kim, J. W., Lee, Y. S., Tae, J. H., Choi, S. Y., Chang, I. H., & Kim, J. H. (2024) · Scientific Reports · doi:10.1038/s41598-024-51531-8 · Cited by 43 · cited 3×
“Studies like Choi et al. 55 shed light on the potential and limitations of LLMs in direct patientinteractionsandlearninggains.”
BackgroundMethodInfluentialGobira, M., Nakayama, L. F., Moreira, R., Andrade, E., Regatieri, C. V. S., & Belfort Jr., R. (2023) · Revista da Associação Médica Brasileira · doi:10.1590/1806-9282.20230848 · Cited by 42 · cited 1×
“It is an alternative to the Chi-Square test in such cases 90,91 .”
MethodPotential Use of ChatGPT for Patient Information in Periodontology: A Descriptive Pilot Study
Babayiğit, O., Tastan Eroglu, Z., Ozkan Sen, D., & Ucan Yarkac, F. (2023) · Cureus · doi:10.7759/cureus.48518 · Cited by 42
Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation
Moramarco, F., Papadopoulos Korfiatis, A., Perera, M., Juric, D., Flann, J., Reiter, E., Belz, A., & Savkov, A. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.394 · Cited by 40
Diagnostic and Management Performance of ChatGPT in Obstetrics and Gynecology
Allahqoli, L., Ghiasvand, M. M., Mazidimoradi, A., Salehiniya, H., & Alkatout, I. (2023) · Gynecologic and Obstetric Investigation · doi:10.1159/000533177 · Cited by 40
Yapar, D., Avcı, Y. D., Sonuvar, E. T., Eğerci, Ö. F., & Yapar, A. (2023) · Joint Diseases and Related Surgery · doi:10.52312/jdrs.2023.1402 · Cited by 40 · cited 1×
“4, a majority of studies have less than 20 evaluators, with only 3 studies recruiting more than 50 evaluators 43 – 45 .”
BackgroundAl-Sharif, E. M., Penteado, R. C., Dib El Jalbout, N., Topilow, N. J., Shoji, M. K., Kikkawa, D. O., Liu, C. Y., & Korn, B. S. (2024) · Ophthalmic Plastic & Reconstructive Surgery · doi:10.1097/iop.0000000000002567 · Cited by 40
Peng, W., feng, Y., Yao, C., Zhang, S., Zhuo, H., Qiu, T., Zhang, Y., Tang, J., Gu, Y., & Sun, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-52853-3 · Cited by 40 · cited 1×
“32 andXieetal.”
Kienzle, A., Niemann, M., Meller, S., & Gwinner, C. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14010069 · Cited by 39
Saibene, A. M., Allevi, F., Calvo‐Henríquez, C., Maniaci, A., Mayo‐Yáñez, M., Paderno, A., Vaira, L. A., Felisati, G., & Craig, J. R. (2024) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-023-08372-4 · Cited by 39
HumanELY: Human evaluation of LLM yield, using a novel web-based evaluation toolPreprint
Awasthi, R., Mishra, S. V., Mahapatra, D., Khanna, A. K., Maheshwari, K. K., Cywiński, J. B., Papay, F., & Mathur, P. (2023) · medRxiv · doi:10.1101/2023.12.22.23300458 · Cited by 37 · cited 1×
“Awasthi et al. 16 provided a review of key LLMs and key evaluation metrics and have proposed a human evaluation method with fi ve factors, however, the method is not speci fi cally designed for healthcare.”
MethodSelf-citationUtilizing ChatGPT in Telepharmacy
Bazzari, F. H., & Bazzari, A. H. (2024) · Cureus · doi:10.7759/cureus.52365 · Cited by 37 · cited 2×
“Bazzari and Bazzari chose the Mann – Whitney U test to compare LLM effectiveness in tele-pharmacyagainsttraditionalmethodswhenfacedwithnon-normalsample distributions 46 .”
BackgroundMethodCankurtaran, R. E., Polat, Y. H., Aydemir, N. G., Umay, E., & Yurekli, O. T. (2023) · Cureus · doi:10.7759/cureus.46736 · Cited by 36
Chari, S., Acharya, P., Gruen, D. M., Zhang, O., Eyigöz, E., Ghalwash, M. F., Seneviratne, O. W., Suárez, F., Meyer, P., Chakraborty, P., et al. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2023.102498 · Cited by 35
Risk stratification of thyroid nodules: Assessing the suitability of ChatGPT for text-based analysis
Sievert, M., Conrad, O., Mueller, S. K., Rupp, R., Balk, M., Richter, D., Mantsopoulos, K., Iro, H., & Koch, M. (2023) · American Journal of Otolaryngology · doi:10.1016/j.amjoto.2023.104144 · Cited by 35
Agarwal, M., Goswami, A., & Sharma, P. (2023) · Cureus · doi:10.7759/cureus.46222 · Cited by 34
Mu, X., Lim, B., Seth, I., Xie, Y., Cevik, J., Sofiadellis, F., Hunter‐Smith, D. J., & Rozen, W. M. (2023) · Skin Health and Disease · doi:10.1002/ski2.313 · Cited by 34
ChatGPT Performance in Diagnostic Clinical Microbiology Laboratory-Oriented Case Scenarios
Sallam, M., Al‐Salahat, K., & Al-Ajlouni, E. (2023) · Cureus · doi:10.7759/cureus.50629 · Cited by 33
An evaluation of AI generated literature reviews in musculoskeletal radiology
Jenko, N., Ariyaratne, S., Jeys, L. M., Evans, S., Iyengar, K. P., & Botchu, R. (2024) · The Surgeon · doi:10.1016/j.surge.2023.12.005 · Cited by 30
Wu, Y., Zhang, Z., Dong, X., Hong, S., Hu, Y., Liang, P., Li, L., Zou, B., Wu, X., Wang, D., et al. (2024) · Epilepsy & Behavior · doi:10.1016/j.yebeh.2024.109645 · Cited by 30 · cited 1×
“Thesecond most common application, medical education and examination (24.8%), was explored by researchers like Yaneva et al. 24 , Wu et al. 25 , and Ghosh et al. 26 .”
BackgroundInfluentialSelf-citationLongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
Krishna, K., Bransom, E., Kuehl, B., Iyyer, M., Dasigi, P., Cohan, A., & Lo, K. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.121 · Cited by 29
Draschl, A., Hauer, G., Fischerauer, S. F., Kogler, A., Leitner, L., Andreou, D., Leithner, A., & Sadoghi, P. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12206655 · Cited by 29
Towards more patient friendly clinical notes through language models and ontologies
Moramarco, F., Juric, D., Savkov, A., Flann, J., Lehl, M., Boda, K., Grafen, T., Zhelezniak, V., Gohil, S., Korfiatis, A. P., et al. (2021) · PubMed · doi:10.48550/arxiv.2112.12672 · Cited by 28 · cited 2×
“The majority of studies have 100 or below LLMs output for human evaluation, but we do observe one outlier study with 2995 samples by Moramarco et al. 35 .”
BackgroundHuespe, I. A., Echeverri, J., Khalid, A., Carboni Bisso, I., Musso, C. G., Surani, S., Bansal, V., & Kashyap, R. (2023) · Critical Care Explorations · doi:10.1097/cce.0000000000000975 · Cited by 27
Evaluating insomnia queries from an artificial intelligence chatbot for patient education
Alapati, R., Campbell, D. J., Molin, N. L., Creighton, E. W., Wei, Z., Boon, M. S., & Huntley, C. T. (2024) · Journal of Clinical Sleep Medicine · doi:10.5664/jcsm.10948 · Cited by 21
“Vertigo, likely peripheral”: the dizzying rise of ChatGPT
Chee, J., Kwa, E. D., & Goh, X. (2023) · European Archives of Oto-Rhino-Laryngology · doi:10.1007/s00405-023-08135-1 · Cited by 20
Zhou, Y., Moon, C. N., Szatkowski, J., Moore, D., & Stevens, J. M. (2023) · European Journal of Orthopaedic Surgery & Traumatology · doi:10.1007/s00590-023-03742-4 · Cited by 20
Using ChatGPT to Generate Research Ideas in Dysphagia: A Pilot Study
Nachalon, Y., Broer, M., & Nativ‐Zeltzer, N. (2023) · Dysphagia · doi:10.1007/s00455-023-10623-9 · Cited by 16
An, Y., Fang, Q., & Wang, L. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107874 · Cited by 12
Artificial Intelligence in Childcare: Assessing the Performance and Acceptance of ChatGPT Responses
Kaneda, Y., Namba, M., Kaneda, U., & Tanimoto, T. E. (2023) · Cureus · doi:10.7759/cureus.44484 · Cited by 10 · cited 1×
“ANOVA Astatisticaltestusedtodetermineifthereareanystatisticallysigni fi cantdifferencesbetweenthemeansof two or more independent groups 78,82 .”
BackgroundLongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
Krishna, K., Bransom, E., Kuehl, B., Iyyer, M., Dasigi, P., Cohan, A., & Lo, K. (2023) · arXiv · doi:10.48550/arxiv.2301.13298 · Cited by 3
Research works printed but not linked: 4
- 8. Lin, C.-Y. ROUGE: a package for automatic evaluation of summaries. Text Summarization Branches Out (Association for Computational Linguistics, Barcelona, Spain, 2004).
- 59. Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. Bert: pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers) (eds Burstein, J Doran, C & Solorio, T.) 4171–4186 (Association for Computational Linguistics, 2019).
- 94. Parasuraman, A., Berry, L. L. & Zeithaml, V. A. Refinement and reassessment of the SERVQUAL scale. J. Retail. 67, 420 (1991).
- 97. Biggs, J. B. & Collis, K. F. Evaluating the Quality of Learning: The SOLO Taxonomy (Structure of the Observed Learning Outcome) (Academic Press, 2014).
Cited by
A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation
Asgari, E., Montaña-Brown, N., Dubois, M., Khalil, S., Balloch, J., Yeung, J. A., & Pimenta, D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01670-7 · Cited by 423
Large Language Models in Healthcare and Medical Applications: A Review
Maity, S., & Saikia, M. J. (2025) · Bioengineering · doi:10.3390/bioengineering12060631 · Cited by 249
“Human-centered evaluation frameworks, such as the QUEST protocol, involve physicians, nurses, and pharmacists in the systematic assessment of LLM outputs for accuracy, comprehensiveness, bias, and harm in real clinical scenarios [71].”
Liu, S., McCoy, A. B., & Wright, A. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf008 · Cited by 200
“14 However, these guidelines do not cover RAG applications in clinical settings, emphasizing the need for a more specific guideline.”
Large language models for disease diagnosis: a scoping review
Zhou, S., Xu, Z., Zhang, M., Xu, C., Guo, Y., Zhan, Z., Fang, Y., Ding, S., Wang, J., Xu, K., et al. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00011-z · Cited by 122
A personal health large language model for sleep and fitness coaching
Khasentino, J., Belyaeva, A., Liu, X., Yang, Z., Furlotte, N. A., Lee, C., Schenck, E., Patel, Y., Cui, J., Schneider, L. D., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03888-0 · Cited by 191
“Health metrics: daily data on day of the week, date, resting heart rate, heart rate variability and respiratory rate were provided to assess recovery and stress (Supplementary Tables 32 and 33), along with graphical representations (Fig.”
Metadata
- Authors
- Tam, T. Y. C., Sivarajkumar, S., Kapoor, S., Stolyar, A. V., Polanska, K., McCarthy, K. R., Osterhoudt, H., Wu, X., Visweswaran, S., Fu, S., Mathur, P., Cacciamani, G. E., Sun, C., Peng, Y., & Wang, Y.
- Affiliations
- University of Pittsburgh (US)
- University of Pittsburgh Medical Center (US)
- The University of Texas Health Science Center at Houston (US)
- Cleveland Clinic (US)
- University of Southern California (US)
- Weill Cornell Medicine (US)
- Corresponding author
- Wang, Yanshan
- ORCID
- Venue
- npj Digital Medicine
- Published
- 2024-09-28
- Volume
- 7
- Issue
- 1
- Pages
- 258-258
- ISSN
- 2398-6352 (ISSN-L)
- PMC
- PMC11437138
- OpenAlex
- W4402909345
- Cited by
- 424
- References
- 102
- Citations by year
- 2026: 270 · 2025: 149 · 2024: 5
- FWCI
- 39.64
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- npj Digital Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Digital Commons-TMC (Texas Medical Center) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- U.S. Department of Health & Human Services | National Institutes of Health (UL1TR001857, U24TR004111, R01LM014306)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Keywords
- large language models, human evaluation, health care, generative AI, evaluation framework, evaluation metrics, assessment reliability, trust and confidence, evaluation principles
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
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.