Skip to main content
Erschienen in:

27.06.2024

Learning from Failure: Towards Developing a Disease Diagnosis Assistant That Also Learns from Unsuccessful Diagnoses

verfasst von: Abhisek Tiwari, Swarna S, Sriparna Saha, Pushpak Bhattacharyya, Minakshi Dhar, Sarbajeet Tiwari

Erschienen in: Cognitive Computation | Ausgabe 5/2024

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In recent years, automatic disease diagnosis has gained immense popularity in research and industry communities. Humans learn a task through both successful and unsuccessful attempts in real life, and physicians are not different. When doctors fail to diagnose disease correctly, they re-assess the extracted symptoms and re-diagnose the patient by inspecting a few more symptoms guided by their previous experience and current context. Motivated by the experience gained from failure assessment, we propose a novel end-to-end automatic disease diagnosis dialogue system called Failure Assessment incorporated Symptom Investigation and Disease Diagnosis (FA-SIDD) Assistant. The proposed FA-SIDD model includes a knowledge-guided, incorrect disease projection-aware failure assessment module that analyzes unsuccessful diagnosis attempts and reinforces the assessment for further investigation and re-diagnosis. We formulate a novel Markov decision process for the proposed failure assessment, incorporating symptom investigation and disease diagnosis frameworks, and optimize the policy using deep reinforcement learning. The proposed model has outperformed several baselines and the existing symptom investigation and diagnosis methods by a significant margin (1–3%) in all evaluation metrics (including human evaluation). The improvements over the multiple datasets and across multiple algorithms firmly establish the efficacy of learning gained from unsuccessful diagnoses. The work is the first attempt that investigate the importance of learning gained from unsuccessful diagnoses. The developed assistant learns diagnosis task more efficiently than traditional assistants and shows robust behavior. Furthermore, the code is available at https://​github.​com/​AbhisekTiwari/​FA-SIDA.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
1
Division has been done as per the International Classification of Disease (ICD-10-CM) https://​www.​cdc.​gov/​nchs/​icd/​
 
Literatur
1.
Zurück zum Zitat Rasmussen K, Belisario JM, Wark PA, Molina JA, Loong SL, Cotic Z, Papachristou N, Riboli–Sasco E, Car LT, Musulanov EM, et al. Offline elearning for undergraduates in health professions: a systematic review of the impact on knowledge, skills, attitudes and satisfaction. J Glob Health 2014:4(1). Rasmussen K, Belisario JM, Wark PA, Molina JA, Loong SL, Cotic Z, Papachristou N, Riboli–Sasco E, Car LT, Musulanov EM, et al. Offline elearning for undergraduates in health professions: a systematic review of the impact on knowledge, skills, attitudes and satisfaction. J Glob Health 2014:4(1).
2.
Zurück zum Zitat Ramakrishnan N, Vijayaraghavan BKT, Venkataraman R. Breaking barriers to reach farther: A call for urgent action on tele-icu services. Indian Journal of Critical Care Medicine: Peer-reviewed, Official Publication of Indian Society of Critical Care Medicine. 2020;24(6):393.CrossRef Ramakrishnan N, Vijayaraghavan BKT, Venkataraman R. Breaking barriers to reach farther: A call for urgent action on tele-icu services. Indian Journal of Critical Care Medicine: Peer-reviewed, Official Publication of Indian Society of Critical Care Medicine. 2020;24(6):393.CrossRef
3.
Zurück zum Zitat Kumar Y, Koul A, Singla R, Ijaz MF. Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. J Ambient Intell Humaniz Comput. 2022; pp 1–28. Kumar Y, Koul A, Singla R, Ijaz MF. Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. J Ambient Intell Humaniz Comput. 2022; pp 1–28.
4.
Zurück zum Zitat Semigran HL, Linder JA, Gidengil C, Mehrotra A. Evaluation of symptom checkers for self diagnosis and triage: audit study. BMJ. 2015:351. Semigran HL, Linder JA, Gidengil C, Mehrotra A. Evaluation of symptom checkers for self diagnosis and triage: audit study. BMJ. 2015:351.
5.
Zurück zum Zitat Wei Z, Liu Q, Peng B, Tou H, Chen T, Huang X-J, Wong K-F, Dai X. Task-oriented dialogue system for automatic diagnosis. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018; pp. 201–207. Wei Z, Liu Q, Peng B, Tou H, Chen T, Huang X-J, Wong K-F, Dai X. Task-oriented dialogue system for automatic diagnosis. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018; pp. 201–207.
6.
Zurück zum Zitat Kao H-C, Tang K-F, Chang E. Context-aware symptom checking for disease diagnosis using hierarchical reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2018;32. Kao H-C, Tang K-F, Chang E. Context-aware symptom checking for disease diagnosis using hierarchical reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2018;32.
7.
Zurück zum Zitat Liao K, Liu Q, Wei Z, Peng B, Chen Q, Sun W, Huang X. Task-oriented dialogue system for automatic disease diagnosis via hierarchical reinforcement learning. 2020. arXiv preprint arXiv:2004.14254. Liao K, Liu Q, Wei Z, Peng B, Chen Q, Sun W, Huang X. Task-oriented dialogue system for automatic disease diagnosis via hierarchical reinforcement learning. 2020. arXiv preprint arXiv:​2004.​14254.
8.
Zurück zum Zitat Millwood S. Developing a platform for learning from mistakes: changing the culture of patient safety amongst junior doctors. BMJ Open Quality. 2014;3(1):203658–2114. Millwood S. Developing a platform for learning from mistakes: changing the culture of patient safety amongst junior doctors. BMJ Open Quality. 2014;3(1):203658–2114.
9.
Zurück zum Zitat Tang K-F, Kao H-C, Chou C-N, Chang EY. Inquire and diagnose: Neural symptom checking ensemble using deep reinforcement learning. In: NIPS Workshop on Deep Reinforcement Learning. 2016. Tang K-F, Kao H-C, Chou C-N, Chang EY. Inquire and diagnose: Neural symptom checking ensemble using deep reinforcement learning. In: NIPS Workshop on Deep Reinforcement Learning. 2016.
10.
Zurück zum Zitat Peng Y-S, Tang K-F, Lin H-T, Chang E. Refuel: Exploring sparse features in deep reinforcement learning for fast disease diagnosis. Adv Neural Inf Process Syst. 2018;31:7322–31. Peng Y-S, Tang K-F, Lin H-T, Chang E. Refuel: Exploring sparse features in deep reinforcement learning for fast disease diagnosis. Adv Neural Inf Process Syst. 2018;31:7322–31.
11.
Zurück zum Zitat Lin S, Zhou P, Liang X, Tang J, Zhao R, Chen Z, Lin L. Graph-evolving meta-learning for low-resource medical dialogue generation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021; pp. 13362–13370. AAAI Press. Lin S, Zhou P, Liang X, Tang J, Zhao R, Chen Z, Lin L. Graph-evolving meta-learning for low-resource medical dialogue generation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021; pp. 13362–13370. AAAI Press.
12.
Zurück zum Zitat Naseem U, Khushi M, Dunn AG, Kim J. K-pathvqa: Knowledge-aware multimodal representation for pathology visual question answering. IEEE J Biomed Health Inform. 2023. Naseem U, Khushi M, Dunn AG, Kim J. K-pathvqa: Knowledge-aware multimodal representation for pathology visual question answering. IEEE J Biomed Health Inform. 2023.
13.
Zurück zum Zitat Lu H, Uddin S. A weighted patient network-based framework for predicting chronic diseases using graph neural networks. Sci Rep. 2021;11(1):1–12.CrossRef Lu H, Uddin S. A weighted patient network-based framework for predicting chronic diseases using graph neural networks. Sci Rep. 2021;11(1):1–12.CrossRef
14.
Zurück zum Zitat Dong W, Wozniak M, Wu J, Li W, Bai Z. De-noising aggregation of graph neural networks by using principal component analysis. IEEE Trans Industr Inform. 2022. Dong W, Wozniak M, Wu J, Li W, Bai Z. De-noising aggregation of graph neural networks by using principal component analysis. IEEE Trans Industr Inform. 2022.
15.
Zurück zum Zitat Dong W, Wu J, Zhang X, Bai Z, Wang P, Woźniak M. Improving performance and efficiency of graph neural networks by injective aggregation. Knowl-Based Syst. 2022;254: 109616.CrossRef Dong W, Wu J, Zhang X, Bai Z, Wang P, Woźniak M. Improving performance and efficiency of graph neural networks by injective aggregation. Knowl-Based Syst. 2022;254: 109616.CrossRef
16.
Zurück zum Zitat Sun Z, Yin H, Chen H, Chen T, Cui L, Yang F. Disease prediction via graph neural networks. IEEE J Biomed Health Inform. 2020;25(3):818–26.CrossRef Sun Z, Yin H, Chen H, Chen T, Cui L, Yang F. Disease prediction via graph neural networks. IEEE J Biomed Health Inform. 2020;25(3):818–26.CrossRef
17.
Zurück zum Zitat Bessadok A, Mahjoub MA, Rekik I. Graph neural networks in network neuroscience. IEEE Trans Pattern Anal Mach Intell. 2022;45(5):5833–48.CrossRef Bessadok A, Mahjoub MA, Rekik I. Graph neural networks in network neuroscience. IEEE Trans Pattern Anal Mach Intell. 2022;45(5):5833–48.CrossRef
18.
Zurück zum Zitat Mccombe N, Ding X, Prasad G, Gillespie P, Finn DP, Todd S, Mcclean PL, Wong-Lin K. Alzheimer’s disease assessments optimized for diagnostic accuracy and administration time. IEEE J Transl Eng Health Med. 2022;10:1–9.CrossRef Mccombe N, Ding X, Prasad G, Gillespie P, Finn DP, Todd S, Mcclean PL, Wong-Lin K. Alzheimer’s disease assessments optimized for diagnostic accuracy and administration time. IEEE J Transl Eng Health Med. 2022;10:1–9.CrossRef
19.
Zurück zum Zitat Uddin S, Wang S, Lu H, Khan A, Hajati F, Khushi M. Comorbidity and multimorbidity prediction of major chronic diseases using machine learning and network analytics. Expert Syst Appl. 2022;205: 117761.CrossRef Uddin S, Wang S, Lu H, Khan A, Hajati F, Khushi M. Comorbidity and multimorbidity prediction of major chronic diseases using machine learning and network analytics. Expert Syst Appl. 2022;205: 117761.CrossRef
20.
Zurück zum Zitat Caruccio L, Cirillo S, Polese G, Solimando G, Sundaramurthy S, Tortora G. Can chatgpt provide intelligent diagnoses? a comparative study between predictive models and chatgpt to define a new medical diagnostic bot. Expert Syst Appl. 2024;235: 121186.CrossRef Caruccio L, Cirillo S, Polese G, Solimando G, Sundaramurthy S, Tortora G. Can chatgpt provide intelligent diagnoses? a comparative study between predictive models and chatgpt to define a new medical diagnostic bot. Expert Syst Appl. 2024;235: 121186.CrossRef
21.
Zurück zum Zitat Xu L, Zhou Q, Gong K, Liang X, Tang J, Lin L. End-to-end knowledge-routed relational dialogue system for automatic diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019;33:7346–7353. Xu L, Zhou Q, Gong K, Liang X, Tang J, Lin L. End-to-end knowledge-routed relational dialogue system for automatic diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019;33:7346–7353.
22.
Zurück zum Zitat Dietterich TG. Hierarchical reinforcement learning with the maxq value function decomposition. J Artif Intell Res. 2000;13:227–303.MathSciNetCrossRef Dietterich TG. Hierarchical reinforcement learning with the maxq value function decomposition. J Artif Intell Res. 2000;13:227–303.MathSciNetCrossRef
23.
Zurück zum Zitat Chen W, Zhong C, Peng J, Wei Z. Dxformer: a decoupled automatic diagnostic system based on decoder-encoder transformer with dense symptom representations. Bioinformatics. 2023;39(1):744.CrossRef Chen W, Zhong C, Peng J, Wei Z. Dxformer: a decoupled automatic diagnostic system based on decoder-encoder transformer with dense symptom representations. Bioinformatics. 2023;39(1):744.CrossRef
24.
Zurück zum Zitat Levin E, Pieraccini R, Eckert W. Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP’98 (Cat. No. 98CH36181). 1998;1:201–204. IEEE. Levin E, Pieraccini R, Eckert W. Using markov decision process for learning dialogue strategies. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP’98 (Cat. No. 98CH36181). 1998;1:201–204. IEEE.
25.
Zurück zum Zitat Gu Y-K, Zhang J, Shen Y-J, Fan C-J. Fault tree analysis method based on probabilistic model checking and discrete time markov chain. J Ind Prod Eng. 2019;36(3):146–53. Gu Y-K, Zhang J, Shen Y-J, Fan C-J. Fault tree analysis method based on probabilistic model checking and discrete time markov chain. J Ind Prod Eng. 2019;36(3):146–53.
26.
Zurück zum Zitat Barto AG, Mahadevan S. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems. 2003;13(1):41–77. Barto AG, Mahadevan S. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems. 2003;13(1):41–77.
27.
Zurück zum Zitat Budzianowski P, Ultes S, Su P-H, Mrkšić N, Wen T-H, Casanueva I, Barahona LMR, Gasic M. Sub-domain modelling for dialogue management with hierarchical reinforcement learning. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. 2017; pp. 86–92. Budzianowski P, Ultes S, Su P-H, Mrkšić N, Wen T-H, Casanueva I, Barahona LMR, Gasic M. Sub-domain modelling for dialogue management with hierarchical reinforcement learning. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue. 2017; pp. 86–92.
28.
Zurück zum Zitat Peng B, Li X, Li L, Gao J, Celikyilmaz A, Lee S, Wong K-F. Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017; pp. 2231–2240. Peng B, Li X, Li L, Gao J, Celikyilmaz A, Lee S, Wong K-F. Composite task-completion dialogue policy learning via hierarchical deep reinforcement learning. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017; pp. 2231–2240.
29.
Zurück zum Zitat Liu J, Pan F, Luo L. Gochat: Goal-oriented chatbots with hierarchical reinforcement learning. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020; pp. 1793–1796. Liu J, Pan F, Luo L. Gochat: Goal-oriented chatbots with hierarchical reinforcement learning. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020; pp. 1793–1796.
30.
31.
Zurück zum Zitat Tesauro G, et al. Temporal difference learning and td-gammon. Commun ACM. 1995;38(3):58–68.CrossRef Tesauro G, et al. Temporal difference learning and td-gammon. Commun ACM. 1995;38(3):58–68.CrossRef
32.
Zurück zum Zitat Ramos J, et al. Using tf-idf to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning. 2003;242:29–48. Citeseer. Ramos J, et al. Using tf-idf to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning. 2003;242:29–48. Citeseer.
33.
Zurück zum Zitat Li X, Chen Y-N, Li L, Gao J, Celikyilmaz A. End-to-end task-completion neural dialogue systems. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2017; pp. 733–743. Li X, Chen Y-N, Li L, Gao J, Celikyilmaz A. End-to-end task-completion neural dialogue systems. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2017; pp. 733–743.
34.
Zurück zum Zitat Deemter KV, Theune M, Krahmer E. Real versus template-based natural language generation: A false opposition? Computational Linguistics. 2005;31(1):15–24. Deemter KV, Theune M, Krahmer E. Real versus template-based natural language generation: A false opposition? Computational Linguistics. 2005;31(1):15–24.
36.
Zurück zum Zitat Yan G, Pei J, Ren P, Chen Z, Ren Z, Liang H. M\(\hat{}\) 2-meddialog: A dataset and benchmarks for multi-domain multi-service medical dialogues. 2021. arXiv preprint arXiv:2109.00430. Yan G, Pei J, Ren P, Chen Z, Ren Z, Liang H. M\(\hat{}\) 2-meddialog: A dataset and benchmarks for multi-domain multi-service medical dialogues. 2021. arXiv preprint arXiv:​2109.​00430.
37.
Zurück zum Zitat Zeng G, Yang W, Ju Z, Yang Y, Wang S, Zhang R, Zhou M, Zeng J, Dong X, Zhang R, et al. Meddialog: Large-scale medical dialogue dataset. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020. Zeng G, Yang W, Ju Z, Yang Y, Wang S, Zhang R, Zhou M, Zeng J, Dong X, Zhang R, et al. Meddialog: Large-scale medical dialogue dataset. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.
38.
Zurück zum Zitat Franc V, Hlavác V. Multi-class support vector machine. In: Object Recognition Supported by User Interaction for Service Robots. 2002;2:236–239. IEEE. Franc V, Hlavác V. Multi-class support vector machine. In: Object Recognition Supported by User Interaction for Service Robots. 2002;2:236–239. IEEE.
39.
Zurück zum Zitat Xia Y, Zhou J, Shi Z, Lu C, Huang H. Generative adversarial regularized mutual information policy gradient framework for automatic diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020;34:1062–1069. Xia Y, Zhou J, Shi Z, Lu C, Huang H. Generative adversarial regularized mutual information policy gradient framework for automatic diagnosis. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2020;34:1062–1069.
40.
Zurück zum Zitat Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M. Playing atari with deep reinforcement learning. 2013. arXiv preprint arXiv:1312.5602. Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M. Playing atari with deep reinforcement learning. 2013. arXiv preprint arXiv:​1312.​5602.
41.
Zurück zum Zitat Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2016;30. Van Hasselt H, Guez A, Silver D. Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2016;30.
42.
Zurück zum Zitat Schaul T, Quan J, Antonoglou I, Silver D. Prioritized experience replay. In: ICLR (Poster). 2016. Schaul T, Quan J, Antonoglou I, Silver D. Prioritized experience replay. In: ICLR (Poster). 2016.
43.
Zurück zum Zitat Tiwari A, Raj R, Saha S, Bhattacharyya P, Tiwari S, Dhar M. Towards symptom assessment guided symptom investigation and disease diagnosis. IEEE Trans Artif Intell. 2023. Tiwari A, Raj R, Saha S, Bhattacharyya P, Tiwari S, Dhar M. Towards symptom assessment guided symptom investigation and disease diagnosis. IEEE Trans Artif Intell. 2023.
44.
Zurück zum Zitat Welch BL. The generalization of ‘student’s’ problem when several different population varlances are involved. Biometrika. 1947;34(1–2):28–35.MathSciNet Welch BL. The generalization of ‘student’s’ problem when several different population varlances are involved. Biometrika. 1947;34(1–2):28–35.MathSciNet
Metadaten
Titel
Learning from Failure: Towards Developing a Disease Diagnosis Assistant That Also Learns from Unsuccessful Diagnoses
verfasst von
Abhisek Tiwari
Swarna S
Sriparna Saha
Pushpak Bhattacharyya
Minakshi Dhar
Sarbajeet Tiwari
Publikationsdatum
27.06.2024
Verlag
Springer US
Erschienen in
Cognitive Computation / Ausgabe 5/2024
Print ISSN: 1866-9956
Elektronische ISSN: 1866-9964
DOI
https://doi.org/10.1007/s12559-024-10274-4

Weitere Artikel der Ausgabe 5/2024

Cognitive Computation 5/2024 Zur Ausgabe