CoD, towards an interpretable medical agent using chain of diagnosis
Open accessAbstract
The field of AI healthcare has undergone a significant transformation with the advent of large language models (LLMs), yet the challenge of interpretability in these models remain largely unaddressed.This study introduces Chain-of-Diagnosis (CoD) to enhance the interpretability of medical automatic diagnosis.CoD transforms the diagnostic process into a diagnostic chain that mirrors a physician's thought process, providing a transparent reasoning pathway.Additionally, CoD outputs the disease confidence distribution to ensure transparency in decision-making.This interpretability makes model diagnostics controllable and aids in identifying critical symptoms for inquiry through the entropy reduction of confidences.With CoD, we developed DiagnosisGPT, capable of diagnosing 9,604 diseases for validating CoD.Experimental results demonstrate that DiagnosisGPT outperforms other LLMs on automatic diagnostic tasks across three real-world benchmarks.Moreover, Diagnosis-GPT provides interpretability while ensuring controllability in diagnostic rigor.Code, datasets, and models are publicly available at https://github.com/FreedomIntelligence/Chain- of-Diagnosis.Johnson, and Albert M Lai.2014.A review of approaches to identifying patient phenotype cohorts using electronic health records.
Integrity signals
Registry
Cites
Statistics
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?
Structured decoding approaches enforce interpretable reasoning pathways by construction, rather than hoping that prompted models will faithfully externalize their computations.
“Structured decoding approaches [65,96,101,115,122] enforce interpretable reasoning pathways by construction, rather than hoping that prompted models will faithfully externalize their computations.”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [101]
Others expose intermediate reasoning steps such as agentic traces or structured decoding chains that allow clinicians to audit the logic.
“Others expose intermediate reasoning steps such as agentic traces, structured decoding chains etc that allow clinicians to audit the logic , as in agentic systems [66,77,88,102,118] and structureddecoding approaches [65,101].”
From Explainability of decoder-only clinical large language models: A scoping review (2026) · cites this paper as [101]
Cites
Still being checked.
Cited by
Sorted by citations
Quantifying the reasoning abilities of LLMs on clinical cases
Qiu, P., Wu, C., Liu, S., Fan, Y., Zhao, W., Chen, Z., Gu, H., Peng, C., Zhang, Y., Wang, Y., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-64769-1 · Cited by 53 · see citing works
Healthcare agent: eliciting the power of large language models for medical consultation
Ren, Z., Zhan, Y., Yu, B., Ding, L., Xu, P., & Tao, D. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00021-x · Cited by 49 · see citing works
A comprehensive survey of AI agents in healthcare
Xu, G., Li, X., Chen, Y., Duan, Y., Wu, S., Yu, H., Chiu, C.-H., Ni, J., Tang, N., Li, T. J.-J., et al. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105045 · Cited by 32 · see citing works
ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis
Zhao, Y., Kang, J., Zhang, T. Y., Han, P., & Chen, T. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209476 · Cited by 24 · see citing works
Xu, X., & Sankar, R. (2025) · Information · doi:10.3390/info16100894 · Cited by 20 · see citing works
Explainable differential diagnosis with dual-inference large language models
Zhou, S., Lin, M., Ding, S., Wang, J., Chen, C., Melton, G. B., Zou, J., & Zhang, R. (2025) · npj Health Systems · doi:10.1038/s44401-025-00015-6 · Cited by 20 · see citing works
Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problems
Chen, J., Cai, Z., Ji, K., Wang, X., Liu, W., Wang, R., & Wang, B. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.751 · Cited by 14 · see citing works
Self-citationYu, H., Chen, T., Zhang, X., Yang, Y., Liu, Q., Yang, C., Shen, K., Li, H., Tang, W., Zhong, X., et al. (2025) · Journal of Medical Internet Research · doi:10.2196/77334 · Cited by 13 · see citing works
Exploring finetuned audio-LLM on heart murmur features
Florea, A. N., Jiang, X., Mesgarani, N., & Jiang, X. (2025) · Smart Health · doi:10.1016/j.smhl.2025.100557 · Cited by 8 · see citing works
DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration
Jia, Z., Jia, M., Duan, J., & Wang, J. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.1340 · Cited by 6 · see citing works
Medical Reasoning With Large Language Models: A Systematic Review and Evaluation
Ren, X., Fan, C., Ma, W., He, H., Gao, C., Zhao, X., & Feng, F. (2026) · iNew Medicine · doi:10.1002/inm3.70056 · Cited by 5 · see citing works
Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification
Wu, X., Yu, W., Zhaı, X., & Liu, N. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737120 · Cited by 3 · see citing works
Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise
Liu, X., Liang, J., Tang, L., Ye, M., Ma, W., & Xi, Z. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.647 · Cited by 3 · see citing works
CLARITY: Clinical Assistant for Routing, Inference, and Triage
Shaposhnikov, V., Nesterov, A., Kopanichuk, I. V., Bakulin, I. K., Egor, Z., Abramov, R., Tsapieva, E., Bespalov, I. R., Dylov, D. V., & Oseledets, I. V. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-industry.127 · Cited by 2 · see citing works
Multimodal Models for Comprehensive Cardiac Diagnostics via ECG Interpretation
Guo, M., Zhou, Y., & Tang, S. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822122 · Cited by 2 · see citing works
MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning
Ghosh, R., Gupta, A., McBride, H., Vaidya, A. J., & Mahmood, F. (2025) · doi:10.18653/v1/2025.sciprodllm-1.4 · Cited by 1 · see citing works
Knowledge Graph-Enhanced Long-CoT for Complex Biomolecular Reasoning
Lyu, T., Zhuang, X., Ding, K., Cao, X., Liang, L., Zhao, W., Chen, H., & Zhang, Q. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818882 · Cited by 1 · see citing works
A survey of LLM reasoning in healthcare and medicine: Individual modeling and collaborative agents
Lin, Q., Xiao, L., Pu, B., Shi, K., Du, Y., Xu, J., He, K., Zhao, S., Zhang, J., Cambria, E., et al. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104827 · Cited by 1 · see citing works
Explainability of decoder-only clinical large language models: A scoping review
Mishra, N., Abu-Hanna, A., & Calixto, I. (2026) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2026.103501
Unlocking LLMs’ Self-Improvement Capacity with Autonomous Learning for Domain Adaptation
Ji, K. F., Chen, J., Gao, A., Xie, W., Wan, X., & Wang, B. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.1084
Self-citationDubey, M., Chong, K. J., Pun, Y. R., Foo, L. Y., Ooi, M. G. M., TAN, I., Tan, D. S. P., Ngiam, K. Y., & Wee, H. L. (2026) · JCO Clinical Cancer Informatics · doi:10.1200/cci-25-00226
ControlMed: Adding Reasoning Control to Medical Language Model
Lee, S.-M., Lee, S., Kim, J., & Roh, K. (2025) · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL) · doi:10.18653/v1/2025.ijcnlp-long.149
From Medical LLMs to Versatile Medical Agents: A Comprehensive SurveyPreprint
Zhou, Y., Zheng, H., Chen, D., Yang, H., Han, W., & Shen, J. (2026) · doi:10.22541/au.177437366.61663600/v1
SPARROW: subtyping Parkinson’s disease with agentic reasoning and robust omics workflow
Reyes, D. M., & Yan, P. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00109-y
Lee, A., Lee, S., & You, S. C. (2026) · doi:10.2196/preprints.105215
ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models
Hou, R., Zhu, S., Huai, Z., Yu, G., Fan, Y., Wang, C., & Ruan, T. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.943
Jabbar, S., Bougzime, O., Cruz, C., & Bertolim, M. A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35387-0_36
Wang, L., Liu, X., Tian, T., Chen, J., Liu, L., Wang, Y., Li, Y., & Li, J. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3729263
Self-citation
- Authors
- Chen, J., Gui, C., Gao, A., Ji, K., Wang, X., Wan, X., & Wang, B.
- Affiliations
- Shenzhen Research Institute of Big Data (CN)
- Chinese University of Hong Kong, Shenzhen (CN)
- Venue
- Findings of the Association for Computational Linguistics: ACL 2025
- Published
- 2025
- Pages
- 14345-14368
- OpenAlex
- W4412888016
- Cited by
- 13
- References
- 0
- Citations by year
- 2026: 6 · 2025: 6 · 2024: 1
- FWCI
- 11.48
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (12326608)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- interpretability, large language models, diagnosis, automated diagnosis, controllability, entropy reduction
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
