Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis (2401.06541v1)

Published 12 Jan 2024 in cs.CL and cs.AI

Abstract: Medical dialogue systems have attracted growing research attention as they have the potential to provide rapid diagnoses, treatment plans, and health consultations. In medical dialogues, a proper diagnosis is crucial as it establishes the foundation for future consultations. Clinicians typically employ both intuitive and analytic reasoning to formulate a differential diagnosis. This reasoning process hypothesizes and verifies a variety of possible diseases and strives to generate a comprehensive and rigorous diagnosis. However, recent studies on medical dialogue generation have overlooked the significance of modeling a differential diagnosis, which hinders the practical application of these systems. To address the above issue, we propose a medical dialogue generation framework with the Intuitive-then-Analytic Differential Diagnosis (IADDx). Our method starts with a differential diagnosis via retrieval-based intuitive association and subsequently refines it through a graph-enhanced analytic procedure. The resulting differential diagnosis is then used to retrieve medical knowledge and guide response generation. Experimental results on two datasets validate the efficacy of our method. Besides, we demonstrate how our framework assists both clinicians and patients in understanding the diagnostic process, for instance, by producing intermediate results and graph-based diagnosis paths.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Diaformer: Automatic Diagnosis via Symptoms Sequence Generation. In Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, 4432–4440. AAAI Press.
  2. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, 1597–1607. PMLR.
  3. A benchmark for automatic medical consultation system: frameworks, tasks and datasets. Bioinformatics. Btac817.
  4. Croskerry, P. 2009. A universal model of diagnostic reasoning. Academic medicine, 84(8): 1022–1028.
  5. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171–4186. Minneapolis, Minnesota: Association for Computational Linguistics.
  6. Fleiss, J. L. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5): 378.
  7. DialMed: A Dataset for Dialogue-based Medication Recommendation. In Proceedings of the 29th International Conference on Computational Linguistics, 721–733. Gyeongju, Republic of Korea: International Committee on Computational Linguistics.
  8. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering. In Merlo, P.; Tiedemann, J.; and Tsarfaty, R., eds., Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, EACL 2021, Online, April 19 - 23, 2021, 874–880. Association for Computational Linguistics.
  9. Context-Aware Symptom Checking for Disease Diagnosis Using Hierarchical Reinforcement Learning. In McIlraith, S. A.; and Weinberger, K. Q., eds., Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, 2305–2313. AAAI Press.
  10. Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 4958–4972. Online: Association for Computational Linguistics.
  11. Teaching and learning communication skills in medicine. CRC press.
  12. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Jurafsky, D.; Chai, J.; Schluter, N.; and Tetreault, J. R., eds., Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, 7871–7880. Association for Computational Linguistics.
  13. Semi-Supervised Variational Reasoning for Medical Dialogue Generation. In Diaz, F.; Shah, C.; Suel, T.; Castells, P.; Jones, R.; and Sakai, T., eds., SIGIR ’21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021, 544–554. ACM.
  14. Task-oriented Dialogue System for Automatic Disease Diagnosis via Hierarchical Reinforcement Learning. ArXiv, abs/2004.14254.
  15. Lin, C.-Y. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out, 74–81. Barcelona, Spain: Association for Computational Linguistics.
  16. Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, February 2-9, 2021, 13362–13370. AAAI Press.
  17. Enhancing Dialogue Symptom Diagnosis with Global Attention and Symptom Graph. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 5033–5042. Hong Kong, China: Association for Computational Linguistics.
  18. ”My nose is running.””Are you also coughing?”: Building A Medical Diagnosis Agent with Interpretable Inquiry Logics. ArXiv, abs/2204.13953.
  19. MedDG: An Entity-Centric Medical Consultation Dataset for Entity-Aware Medical Dialogue Generation. In Lu, W.; Huang, S.; Hong, Y.; and Zhou, X., eds., Natural Language Processing and Chinese Computing - 11th CCF International Conference, NLPCC 2022, Guilin, China, September 24-25, 2022, Proceedings, Part I, volume 13551 of Lecture Notes in Computer Science, 447–459. Springer.
  20. Heterogeneous graph reasoning for knowledge-grounded medical dialogue system. Neurocomputing, 442: 260–268.
  21. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  22. Conversation analysis, doctor–patient interaction and medical communication. Medical education, 39(4): 428–435.
  23. OpenAI. 2023. GPT-4 Technical Report. CoRR, abs/2303.08774.
  24. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 311–318. Philadelphia, Pennsylvania, USA: Association for Computational Linguistics.
  25. Language models are unsupervised multitask learners. OpenAI blog, 1(8): 9.
  26. Attention-based Interpretability with Concept Transformers. In International Conference on Learning Representations.
  27. Introduction to information retrieval, volume 39. Cambridge University Press Cambridge.
  28. Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models. In Schuurmans, D.; and Wellman, M. P., eds., Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, Arizona, USA, 3776–3784. AAAI Press.
  29. MidMed: Towards Mixed-Type Dialogues for Medical Consultation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 8145–8157. Toronto, Canada: Association for Computational Linguistics.
  30. Retrieval Augmentation Reduces Hallucination in Conversation. In Moens, M.; Huang, X.; Specia, L.; and Yih, S. W., eds., Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021, 3784–3803. Association for Computational Linguistics.
  31. Skills for communicating with patients. crc press.
  32. Symptom to Diagnosis: An Evidence-Based Guide, 4e. McGraw-Hill Education.
  33. Sequence to Sequence Learning with Neural Networks. In Ghahramani, Z.; Welling, M.; Cortes, C.; Lawrence, N. D.; and Weinberger, K. Q., eds., Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, 3104–3112.
  34. Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors’ Reasoning with Deep Reinforcement Learning. In NeurIPS.
  35. Principles of anatomy and physiology. John Wiley & Sons.
  36. Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net.
  37. Task-oriented Dialogue System for Automatic Diagnosis. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 201–207. Melbourne, Australia: Association for Computational Linguistics.
  38. Medical Dialogue Generation via Dual Flow Modeling. In Findings of the Association for Computational Linguistics: ACL 2023, 6771–6784. Toronto, Canada: Association for Computational Linguistics.
  39. End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, 7346–7353. AAAI Press.
  40. ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues. In Amigó, E.; Castells, P.; Gonzalo, J.; Carterette, B.; Culpepper, J. S.; and Kazai, G., eds., SIGIR ’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022, 3013–3024. ACM.
  41. MedDialog: Large-scale Medical Dialogue Datasets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 9241–9250. Online: Association for Computational Linguistics.
  42. Medical Dialogue Response Generation with Pivotal Information Recalling. In Zhang, A.; and Rangwala, H., eds., KDD ’22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14 - 18, 2022, 4763–4771. ACM.
  43. On the Generation of Medical Dialogs for COVID-19. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 886–896. Online: Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Kaishuai Xu (16 papers)
  2. Wenjun Hou (13 papers)
  3. Yi Cheng (78 papers)
  4. Jian Wang (967 papers)
  5. Wenjie Li (183 papers)

Summary

Introduction to Medical Dialogue Systems

Medical dialogue systems (MDS) are a rapidly growing field of research, aiming to enhance the capabilities of healthcare services. These systems are designed to provide diagnosis, treatment plans, and health advice through automated conversations. Accurate diagnosis plays a critical role in medical dialogues and lays the groundwork for future consultations and patient care.

The Challenge in Modeling Differential Diagnosis

In a clinical setting, physicians use a combination of intuition and analytical reasoning to formulate a differential diagnosis—a list of possible conditions to guide further investigation. Intuitive reasoning is fast and experiential, while analytic reasoning entails a systematic and methodical approach to refining diagnoses.

Past approaches in MDS have primarily leveraged pre-trained LLMs for dialogue generation, but these often lack a meticulously grounded diagnostic process. As a result, while responses may appear coherent, they often fail to offer an interpretable, diagnostic-based rationale, which is key for both clinician and patient acceptance.

Proposing an Intuitive-then-Analytic Framework

The solution presented in the discussed paper is a framework called Intuitive-then-Analytic Differential Diagnosis (IADDx), which aims to mimic the clinician's reasoning process. IADDx consists of two principal stages:

  1. Intuitive Association: By examining patient conditions within the dialogue, a preliminary list of diseases is generated via similarity-based retrieval of past cases and disease documentation.
  2. Analytic Refinement: A diagnosis-oriented graph that includes body systems, organs, diseases, and symptoms is created. Through enhanced entity embeddings and multi-disease classification, IADDx refines the initial list of diseases, yielding a more accurate and interpretable diagnosis.

This method translates to more precise response generation, as medical knowledge is retrieved based on a differential diagnosis, and guides the conversation flow.

Verified through Experimental Validation

Upon testing the proposed framework on two medical datasets, IADDx demonstrates a notable improvement over baseline models, especially in generating responses that are coherent and medically accurate. The paper observed marked enhancements in automatic evaluation metrics like B-1, B-2, and B-4, which are indicators of the response's quality and the model's language understanding.

Additionally, IADDx's potential is reaffirmed through a human evaluation where medical professionals rated generated responses higher in fluency, knowledge accuracy, and overall quality compared to established models.

Conclusion

IADDx stands as an innovative response to the challenge of effectively modeling differential diagnosis in MDS. It not only solidifies the importance of a structured diagnosis process in conversation generation but also underscores the usefulness of combining intuitive and analytical reasoning for more informative and reliable medical dialogue systems. Given its performance in experiments, IADDx is poised to make significant contributions to improving MDS and thereby enhancing virtual healthcare services.

File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets