A generalist medical language model for disease diagnosis assistance
The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.
Abstract
The delivery of accurate diagnoses is crucial in healthcare and represents the gateway to appropriate and timely treatment. Although recent large language models (LLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning, their effectiveness in clinical diagnosis remains unproven. Here we present MedFound, a generalist medical language model with 176 billion parameters, pre-trained on a large-scale corpus derived from diverse medical text and real-world clinical records. We further fine-tuned MedFound to learn physicians' inferential diagnosis with a self-bootstrapping strategy-based chain-of-thought approach and introduced a unified preference alignment framework to align it with standard clinical practice. Extensive experiments demonstrate that our medical LLM outperforms other baseline LLMs and specialized models in in-distribution (common diseases), out-of-distribution (external validation) and long-tailed distribution (rare diseases) scenarios across eight specialties. Further ablation studies indicate the effectiveness of key components in our medical LLM training approach. We conducted a comprehensive evaluation of the clinical applicability of LLMs for diagnosis involving artificial intelligence (AI) versus physician comparison, AI-assistance study and human evaluation framework. Our proposed framework incorporates eight clinical evaluation metrics, covering capabilities such as medical record summarization, diagnostic reasoning and risk manage…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Most have been tested only with text-based, low-stakes interactions,33–38”
From Review of Artificial Intelligence for Clinical Use in Alzheimer's Disease and Related Dementias (2026) · cites this paper as [37]
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“For example, ChatGPT has been found lacking in depth and insight 29 , which produces overly generalized answers that lack medical expertise.”
MIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141 · cited 1×
“MIMIC-III-Note is annotated from an open-access, large-scale clinical database, MIMIC-III, which contains EHRs from 38,597 patients across 49,785 hospital admissions within intensive care units 51 .”
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1×
“Furthermore, the output of generative language models may contain factual errors, logic inconsistencies and problems with coherence 28 .”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263 · cited 2×
“This approach helps the LLM learn to automatically generate more coherent and precise rationales by training it based on a seed set of high-quality diagnostic rationale demonstrations annotated by human expert 55 .”
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 · cited 2×
“2b), thus ensuring consistency with human values 16 .”
Kung, T. H., Cheatham, M., ChatGPT, Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., et al. (2022) · doi:10.1101/2022.12.19.22283643 · Cited by 4,115
Kung, T. H., Cheatham, M., Medenilla, A., Sillos, C., De Leon, L., Elepaño, C., Madriaga, M., Aggabao, R., Diaz-Candido, G., Maningo, J., et al. (2023) · PLOS Digital Health · doi:10.1371/journal.pdig.0000198 · Cited by 4,115 · cited 3×
“GPT-4o is the latest version of ChatGPT, which is reported to have a broader knowledge base and enhanced problem-solving abilities, showing promise in diagnostic tasks.”
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 · cited 2×
“The development of the CLEVER framework was inspired by previous work 14,59 and involved consultations with expert physicians in the United Kingdom and China.”
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 · cited 2×
“The development of the CLEVER framework was inspired by previous work 14,59 and involved consultations with expert physicians in the United Kingdom and China.”
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 · cited 1×
“For primary care physicians who encounter a broad range of diseases in daily clinical work 39 , they can initiate referrals based on MedFound-DX-PA prompts to access more specialized expertise, such as cardiology or neurology.”
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · cited 1×
“Recent advancements demonstrate the potential of LLMs that can interpret and generate text effectively with minimal or no specific fine-tuning, facilitating versatile applications such as interactive decision support and patient chatbots 27 .”
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J., Zhang, H., & Stoica, I. (2023) · Proceedings of the 29th Symposium on Operating Systems Principles · doi:10.1145/3600006.3613165 · Cited by 1,817
Efficient Memory Management for Large Language Model Serving with PagedAttention
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., & Stoica, I. (2023) · arXiv · doi:10.48550/arxiv.2309.06180 · Cited by 1,802
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · cited 1×
“Thus, the loss function is Although COT fine-tuning 56 has demonstrated advantages with LLMs, it remains challenging to acquire a substantial amount of COT demonstrations for fine-tuning, especially within the medical domain.”
BioGPT: generative pre-trained transformer for biomedical text generation and mining
Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., & Liu, T.-Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac409 · Cited by 1,150
Human-in-the-loop machine learning: a state of the art
Mosqueira-Rey, E., Hernández-Pereira, E., Alonso-Ríos, D., Bobes-Bascarán, J., & Fernández-Leal, Á. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10246-w · Cited by 1,025 · cited 1×
“…evaluation interaction between the model assisting physicians and the feedback from physicians can also refine the model, known as human-in-the-loop 49 , enabling the LLM system to evolve continuous improvement in a manner that aligns more closely with the practical needs of clinical environments.”
A visual-language foundation model for computational pathology
Lu, M. Y., Chen, B., Williamson, D. F. K., Chen, R. J., Liang, I., Ding, T., Jaume, G., Odintsov, I., Le, L. P., Gerber, G., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-02856-4 · Cited by 966 · cited 1×
“VLMs have shown promise in fields such as pathology, radiology and echocardiography 43–46 .”
Li, J., Li, D., Savarese, S., & Hoi, S. (2023) · arXiv · doi:10.48550/arxiv.2301.12597 · Cited by 908 · cited 1×
“These advancements are powered by LLMs, which provide extensive domain knowledge and reasoning capabilities 47 , enabling VLMs to perform zero-shot image-to-text generation based on natural language instructions, unlocking emerging capabilities such as visual knowledge reasoning and visual…”
A large language model for electronic health records
Yang, X., Chen, A., PourNejatian, N., Shin, H. C., Smith, K. E., Parisien, C., Compas, C., Martin, C., Costa, A. B., Flores, M. G., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00742-2 · Cited by 847
Self-Consistency Improves Chain of Thought Reasoning in Language Models
Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2203.11171 · Cited by 829 · cited 1×
“To bridge this gap, we introduce MedFound, which Case: Gender: Male, Age: 64.”
A visual–language foundation model for pathology image analysis using medical twitter
Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T. J., & Zou, J. (2023) · Nature Medicine · doi:10.1038/s41591-023-02504-3 · Cited by 693
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2338 · Cited by 686 · cited 4×
“Compared to reinforcement training, DPO offers a more stable training process 19 .”
InfluentialEvaluation and accurate diagnoses of pediatric diseases using artificial intelligence
Liang, H., Tsui, B. Y., Ni, H., Valentim, C. C. S., Baxter, S. L., Liu, G., Cai, W., Kermany, D. S., Sun, X., Chen, J., et al. (2019) · Nature Medicine · doi:10.1038/s41591-018-0335-9 · Cited by 659 · cited 5×
“Furthermore, although existing specialized decision support tools demonstrate certain effectiveness in specific specialties 25 , they are limited to identifying pre-defined coarse-grained disease categories or often struggle with zero-shot scenarios, where they must diagnose diseases that they have…”
InfluentialSelf-citationThe incidence of diagnostic error in medicine
Graber, M. L. (2013) · BMJ Quality & Safety · doi:10.1136/bmjqs-2012-001615 · Cited by 626 · cited 1×
“Despite extensive medical training, diagnosis is prone to errors, with an estimated 20% rate of misdiagnosis at the primary care level 3 , which contributes to approximately 17% of all adverse events in medical practice 4 .”
Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective
Li, J.-P. O., Liu, H., Ting, D. S. J., Jeon, S., Chan, R. V. P., Kim, J. E., Sim, D. A., Thomas, P. B. M., Lin, H., Chen, Y., et al. (2021) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2020.100900 · Cited by 626 · cited 1×
“Additionally, the diagnostic generalist system could facilitate telemedicine by overcoming challenges in resource-limited settings 40,41 by alleviating physician workload through automated integration between clinical assessments.”
Self-citationClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission
Huang, K., Altosaar, J., & Ranganath, R. (2019) · arXiv · doi:10.48550/arxiv.1904.05342 · Cited by 618
Do as AI say: susceptibility in deployment of clinical decision-aids
Gaube, S., Suresh, H., Raue, M., Merritt, A., Berkowitz, S. J., Lermer, E., Coughlin, J. F., Guttag, J. V., Colak, E., & Ghassemi, M. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00385-9 · Cited by 543 · cited 1×
“A substantial gap remains between the development of major medical predictive algorithms and their actual clinical deployment in diverse healthcare settings 6 .”
Kim, H.-E., Kim, H. H., Han, B.-K., Kim, K. H., Han, K., Nam, H., Lee, E. H., & Kim, E.-K. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30003-0 · Cited by 525 · cited 1×
“This phenomenon has also been observed in previous studies (for example, mammography cancer detection 32 and chest X-ray interpretation 33 ).”
Health system-scale language models are all-purpose prediction engines
Jiang, L. Y., Liu, X. C., Nejatian, N. P., Nasir-Moin, M., Wang, D., Abidin, A., Eaton, K., Riina, H. A., Laufer, I., Punjabi, P., et al. (2023) · Nature · doi:10.1038/s41586-023-06160-y · Cited by 460
Self-citationImbalance in the health workforce
Zurn, P., Dal Poz, M. R., Stilwell, B., & Adams, O. (2004) · Human Resources for Health · doi:10.1186/1478-4491-2-13 · Cited by 314 · cited 1×
“Additionally, the diagnostic generalist system could facilitate telemedicine by overcoming challenges in resource-limited settings 40,41 by alleviating physician workload through automated integration between clinical assessments.”
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C. D., & Finn, C. (2023) · arXiv · doi:10.48550/arxiv.2305.18290 · Cited by 293 · cited 4×
“Compared to reinforcement training, DPO offers a more stable training process 19 .”
InfluentialKaur, S., Singla, J., Nkenyereye, L., Jha, S., Prashar, D., Joshi, G. P., El-Sappagh, S., Islam, M. S., & Islam, S. M. R. (2020) · IEEE Access · doi:10.1109/access.2020.3042273 · Cited by 255 · cited 1×
“The delivery of accurate diagnoses plays a crucial role in the field of health-care and represents a fundamental skill for all physicians 1,2 .”
Overhage, J. M., & McCallie, D. (2020) · Annals of Internal Medicine · doi:10.7326/m18-3684 · Cited by 238
Vision–language foundation model for echocardiogram interpretation
Christensen, M., Vukadinovic, M., Yuan, N., & Ouyang, D. (2024) · Nature Medicine · doi:10.1038/s41591-024-02959-y · Cited by 231 · cited 1×
“VLMs have shown promise in fields such as pathology, radiology and echocardiography 43–46 .”
Seah, J. C. Y., Tang, C. H. M., Buchlak, Q. D., Holt, X. G., Wardman, J. B., Aimoldin, A., Esmaili, N., Ahmad, H., Pham, H., Lambert, J. F., et al. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00106-0 · Cited by 229 · cited 1×
“This phenomenon has also been observed in previous studies (for example, mammography cancer detection 32 and chest X-ray interpretation 33 ).”
Three Challenges for AI-Assisted Decision-Making
Steyvers, M., & Kumar, A. (2024) · Perspectives on Psychological Science · doi:10.1177/17456916231181102 · Cited by 217 · cited 1×
“Research suggests that human–AI collaboration faces challenges related to human mental models of the AI, which probably depend on their degree of familiarity with the AI or the reliance on proposed decisions 34,35 .”
Building machines that learn and think with people
Collins, K. M., Sucholutsky, I., Bhatt, U., Chandra, K., Wong, L., Lee, M., Zhang, C. E., Zhi‐Xuan, T., Ho, M. K., Mansinghka, V. K., et al. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-01991-9 · Cited by 216 · cited 1×
“Although a small fraction of work has investigated incorporating clinical knowledge into LLMs for tasks such as medical question-answering 14 or dialogue 15 , their capabilities in clinical diagnostic reasoning have not been fully developed or examined.”
Knowledge-enhanced visual-language pre-training on chest radiology images
Zhang, X., Wu, C., Zhang, Y., Xie, W., & Wang, Y. (2023) · Nature Communications · doi:10.1038/s41467-023-40260-7 · Cited by 207
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
Lehman, E., Jain, S., Pichotta, K., Goldberg, Y., & Wallace, B. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.73 · Cited by 197
What is a disease?: Disease, disability and their definitions
Scully, J. L. (2004) · The EMBO Reports · doi:10.1038/sj.embor.7400195 · Cited by 195
Clinical Decision Support Systems
Wasylewicz, A. T. M., & Scheepers-Hoeks, A. A.-M. (2018) · Springer eBooks · doi:10.1007/978-3-319-99713-1_11 · Cited by 185
(2022) · doi:10.52202/068431-1126 · Cited by 182
STaR: Bootstrapping Reasoning With Reasoning
Zelikman, E., Wu, Y., Mu, J., & Goodman, N. D. (2022) · arXiv · doi:10.48550/arxiv.2203.14465 · Cited by 182 · cited 1×
“To address this issue and further enhance the model’s diagnosis reasoning ability, we adopted a self-bootstrapping approach, following the Self-Taught Reasoner (STaR) 57 .”
Enhancing Clinical Decision Making: Development of a Contiguous Definition and Conceptual Framework
Tiffen, J., Corbridge, S. J., & Slimmer, L. (2014) · Journal of Professional Nursing · doi:10.1016/j.profnurs.2014.01.006 · Cited by 175
Revisiting Neural Scaling Laws in Language and VisionPreprint
Alabdulmohsin, I. M., Neyshabur, B., & Zhai, X. (2022) · Neural Information Processing Systems · doi:10.48550/arxiv.2209.06640 · Cited by 171 · cited 1×
“We chose BLOOM-176B as the base model, owing to its status as the largest open-source language model available, with its emergent capabilities and extensive knowledge base 53 .”
Ball, J. R., & Balogh, E. P. (2015) · Annals of Internal Medicine · doi:10.7326/m15-2256 · Cited by 130
Estimating the number of diseases – the concept of rare, ultra-rare, and hyper-rare
Smith, C. I. E., Bergman, P., & Hagey, D. W. (2022) · iScience · doi:10.1016/j.isci.2022.104698 · Cited by 130 · cited 1×
“To further investigate the model’s diagnostic performance in long-tailed disease distributions involving varying prevalence, we categorized them into ultra-rare (≤0.1% prevalence) and rare (0.1–1% prevalence) groups 26 (Extended Data Fig.”
InfluentialMEDITRON-70B: Scaling Medical Pretraining for Large Language Models
Chen, Z., Cano, A. H., Romanou, A., Bonnet, A., Matoba, K., Salvi, F., Pagliardini, M., Fan, S., Köpf, A., Mohtashami, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.16079 · Cited by 122
Kirk, H. R., Vidgen, B., Röttger, P., & Hale, S. A. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00820-y · Cited by 122 · cited 1×
“Subse-quently, to address the challenges of aligning the LLM’s outputs with clinical requirements 18 , we present a unified preference alignment (PA) framework.”
Tucci, V., Saary, J., & Doyle, T. E. (2022) · Journal of Medical Artificial Intelligence · doi:10.21037/jmai-21-25 · Cited by 116 · cited 1×
“Research suggests that human–AI collaboration faces challenges related to human mental models of the AI, which probably depend on their degree of familiarity with the AI or the reliance on proposed decisions 34,35 .”
ZeRO++: Extremely Efficient Collective Communication for Giant Model TrainingPreprint
Wang, G., Qin, H., Jacobs, S. A., Holmes, C., Rajbhandari, S., Ruwase, O., Yan, F., Yang, L., & He, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.10209 · Cited by 109
Self-citationA Survey of Confidence Estimation and Calibration in Large Language Models . -
Geng, J., Cai, F., Wang, Y., Koeppl, H., Nakov, P., & Gurevych, I. (2024) · Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2024.naacl-long.366 · Cited by 88
The Path to Diagnostic Excellence Includes Feedback to Calibrate How Clinicians Think
Meyer, A. N. D., & Singh, H. (2019) · JAMA · doi:10.1001/jama.2019.0113 · Cited by 71 · cited 1×
“The LLM-based diagnostic generalist has the potential to assist physicians across various stages in clinical workflows, including information gathering, data summarization and interpretation, diagnostic reasoning and formulating final diagnoses 36–38 .”
Revisiting neural scaling laws in language and vision
Alabdulmohsin, I., Neyshabur, B., & Zhai, X. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1620 · Cited by 41
Shen, T. S., Lee, A., Shen, C., & Lin, C. J. (2015) · Genetics Research · doi:10.1017/s0016672315000166 · Cited by 38 · cited 1×
“We expanded our experiments to examine the performance of the LLMs in diagnosing rare diseases characterized by long-tailed distributions 24 .”
Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding
Toma, A., Lawler, P. R., Ba, J., Krishnan, R. G., Rubin, B. B., & Wang, B. (2023) · arXiv · doi:10.48550/arxiv.2305.12031 · Cited by 36
Ghaemi, N. (2018) · Oxford University Press eBooks · doi:10.1093/med/9780199995486.001.0001 · Cited by 20
CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models
Feng, S. Y., Khetan, V., Sacaleanu, B., Gershman, A. V., & Hovy, E. H. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.24 · Cited by 17
Kaur, D., Uslu, S., Durrësi, M., & Durresi, A. (2024) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-57870-0_18 · Cited by 14 · cited 1×
“Furthermore, to enhance the human–computer collaboration for the integration of AI into routine clinical workflows, future work will focus on refining LLM models, such as LLM agents 48 , to better adapt to individual physicians, thereby enhancing the personalization of diagnostic support.”
Aslam, M., & Jaisharma, K. (2021) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci50826.2021.9402571 · Cited by 9 · cited 4×
“We included three representative classification models: a traditional machine learning approach using hierarchical classification (hierarchical random forest (HRF) 30 ); a pre-trained language model tailored for the medical domain using a masked language modeling strategy (Med-BERT 9 ); and a variant of our MedFound a…”
InfluentialMED-Prompt: A novel prompt engineering framework for medicine prediction on free-text clinical notes
Ahmed, A., Zeng, X.-Y., Xi, R., Hou, M.-S., & Shah, S. A. (2024) · Journal of King Saud University: Computer and Information Sciences · doi:10.1016/j.jksuci.2024.101933 · Cited by 5
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Workshop, B., :, Scao, T. L., Fan, A., Akiki, C., Pavlick, E., Ilić, S., Hesslow, D., Castagné, R., Luccioni, A. S., et al. (2022) · arXiv · doi:10.48550/arxiv.2211.05100 · cited 6×
“Here, we leveraged the BLOOM 52 family of LLMs, a decoder-only transformer language model, as our base model for domain pre-training.”
Influential
Research works printed but not linked: 6
- Stern, S.D. Symptom to Diagnosis: An Evidence-Based Guide (McGraw-Hill, 2014).
- Devlin, J. BERT: pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (eds Burstein, J. et al.) 4171–4186 (Association for Computational Linguistics, 2019).
- Zhang, H., Xu, W. & Yu, H. Generative planning for temporally coordinated exploration in reinforcement learning. In Proc. 10th International Conference on Learning Representations https://openreview.net/pdf/0e68ff1fa269567c6c6101685f2f721afcc5d0aa.pdf (ICLR, 2022).
- Achiam, J. et al. GPT-4 technical report. Preprint at https://arxiv.org/abs/2303.08774 (2023). · arXiv
- Hu, E. J. et al. LoRA: low-rank adaptation of large language models. In Proc. 10th International Conference on Learning Representations https://openreview.net/pdf?id=nZeVKeeFYf9 (ICLR, 2022).
- Chihara, L. M. & Hesterberg, T. C. Mathematical Statistics with Resampling and R (John Wiley & Sons, 2022).
Cited by
Foundation models and intelligent decision-making: Progress, challenges, and perspectives
Huang, J., Xu, Y., Wang, Q., Wang, Q., Liang, X., Wang, F., Zhang, Z., Wei, W., Zhang, B., Huang, L., et al. (2025) · The Innovation · doi:10.1016/j.xinn.2025.100948 · Cited by 183
Self-citationLarge Language Models in Medical Diagnostics: Scoping Review With Bibliometric Analysis
Su, H., Sun, Y., Li, R., Zhang, A., Yang, Y., Xiao, F., Duan, Z., Chen, J., Hu, Q., Yang, T., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/72062 · Cited by 79
“LLMs have presented promising performance in undertaking medical tasks [4,6]; for instance, models such as OpenAI’s ChatGPT and Google’s Bard have showcased the potential to enhance clinical decision-making processes [7], refine diagnostic accuracy [8], and facilitate the synthesis of complex…”
Self-citationAn agentic system for rare disease diagnosis with traceable reasoning
Zhao, W., Wu, C., Fan, Y., Qiu, P., Zhang, X., Sun, Y., Zhou, X., Zhang, S., Peng, Y., Wang, Y., et al. (2026) · Nature · doi:10.1038/s41586-025-10097-9 · Cited by 62
“Based on the input, the system generates a ranked list of candidate diagnoses, each supported by a transparent chain of reasoning that directly references verifiable medical evidence, enhancing interpretability and supporting clinician trust in AI-assisted decisions.”
Self-citationReshaping transplantation with AI, emerging technologies and xenotransplantation
Loupy, A., Preka, E., Chen, X., Wang, H., He, J., & Zhang, K. (2025) · Nature Medicine · doi:10.1038/s41591-025-03801-9 · Cited by 62
“Alongside DTs, LLMs are beginning to transform clinical workflows by automating data extraction from EHRs and assisting with complex imaging interpretation, often reaching near-expert performance in identifying key clinical details 133,134 .”
Self-citationMansoor, I., Abdullah, M., Rizwan, M. D., & Fraz, M. M. (2025) · Health Information Science and Systems · doi:10.1007/s13755-025-00403-0 · Cited by 55
“Liu et al. [80] introduce a broad-coverage medical LLM designed to assist in disease diagnosis.”
Metadata
- Authors
- Liu, X., Liu, H., Yang, G., Jiang, Z., Cui, S., Zhang, Z., Wang, H., Tao, L., Sun, Y., Song, Z., Hong, T., Yang, J., Gao, T., Zhang, J., Li, X., Zhang, J., Sang, Y., Yang, Z., Xue, K., Wu, S., Zhang, P., Yang, J., Song, C., & Wang, G.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Peking University Third Hospital (CN)
- Chinese University of Hong Kong (HK)
- China Three Gorges University (CN)
- University of Oxford (GB)
- Shenzhen University (CN)
- Corresponding author
- Yang, Jin
- Yang, Jian
- Song, Chunli
- Wang, Guangyu
- ORCID
- Venue
- Nature Medicine
- Published
- 2025-01-08
- Volume
- 31
- Issue
- 3
- Pages
- 932-942
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- OpenAlex
- W4406152280
- Cited by
- 183
- References
- 57
- Citations by year
- 2026: 103 · 2025: 79
- FWCI
- 43.81
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Nature Medicine (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Wellcome Trust (216593/Z/19/Z)
- National Natural Science Foundation of China (82330078, 61931024, 92359202, 62272055, 12326610, 81874010)
- Medical Research Council (MR/X013189/1)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- clinical language models, chain-of-thought prompting, preference alignment, rare diseases, diagnostic reasoning, risk management, physician comparison, clinical workflow
- MeSH terms
- Artificial Intelligence, Diagnosis, Computer-Assisted, Humans, Language, Natural Language Processing
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.