[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content

Advertisement

Springer Nature Link
Log in

Clinical causal analysis via iterative active structure learning

  • Regular Research Paper
  • Published:
Memetic Computing Aims and scope Submit manuscript

Abstract

Machine Learning has achieved considerable success in clinical applications such as image-based diagnostics, predictive modeling for patient outcomes, and personalized treatment planning. However, the black-box nature of deep neural networks often results in poor interpretability and reliability of predictions. Traditional neural network architectures, focusing primarily on correlations, fall short in elucidating underlying causal medical mechanisms. Addressing this, causal discovery, aimed at elucidating the structure of causal graphical models from observational or experimental data, is gaining prominence in clinical fields demanding high reliability. Nevertheless, the complexity of search algorithms, the scarcity of real-world data, and the challenges in identifying unique results significantly hinder the reliability of these approaches. To overcome these challenges, we propose an iterative active structure learning approach to ensure reliable clinical causal analysis. Our method begins with the recovery of a causal structure, guided by a set of prior causal presence, followed by an iterative process of active refinement to enhance the output reliability. This involves using violations of known clinical mechanisms as structural constraints to guide successive rounds of learning, thereby correcting and refining the model iteratively. The process continues until there is a convergence between expertise and the data-derived solutions. Our experiments on real-world clinical data demonstrate that Our approach can improve the quality of causal findings and discover new causal associations beyond the basis of expert knowledge. Furthermore, our approach has yielded novel and significant insights from various datasets, which we explore in our discussion.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

No datasets were generated or analysed during the current study.

References

  1. Noman N, Moscato P (2020) Designing optimal combination therapy for personalised glioma treatment. Memetic Comput 12:317–329

    Article  MATH  Google Scholar 

  2. Schaefer G (2014) Aco classification of thermogram symmetry features for breast cancer diagnosis. Memetic Comput 6:207–212

    Article  MATH  Google Scholar 

  3. Cacciola M, Megali G, Fiasché M, Versaci M, Morabito FC (2010) A comparison between neural networks and k-nearest neighbours for blood cells taxonomy. Memetic Comput 2:237–246

    Article  MATH  Google Scholar 

  4. Wang X, Li Y, Ban T, Zhu J, Chen L, Usman M, Wang X, Chen H, Chen X, Leung C et al (2022) Dynamic link prediction for discovery of new impactful COVID-19 research approaches. IEEE J Biomed Health Inform 26(12):5883–5894

    Article  MATH  Google Scholar 

  5. Wang X, Chen L, Lyu D, Ban T, Guan Y, Chen Q (2022) Research concept link prediction via graph convolutional network. In: 2022 8th International Conference on Big Data and Information Analytics (BigDIA), pages 220–225. IEEE

  6. Uddin S, Khan A, Hossain ME, Moni MA (2019) Comparing different supervised machine learning algorithms for disease prediction. BMC Med Inform Decis Mak 19(1):1–16

    Article  MATH  Google Scholar 

  7. Zhi Y, Cai M, Rui D, Qiao Y, Zheng X, Guanghua X, Yan L, Dianpeng W (2023) Quantitative evaluation of anisometropic amblyopia treatment efficacy by coupling multiple visual functions via critic algorithm. BMC Ophthalmol 23(1):162

    Article  Google Scholar 

  8. Yin Q, Zhong L, Song Y, Bai L, Wang Z, Li C, Xu Y, Yang X (2023) A decision support system in precision medicine: contrastive multimodal learning for patient stratification. Annals of Operations Research, pages 1–29

  9. Wang X, Chen L, Ban T, Lyu D, Guan Y, Xingyu W, Zhou X, Chen H (2023) Accurate label refinement from multiannotator of remote sensing data. IEEE Trans Geosci Remote Sens 61:1–13

    Article  MATH  Google Scholar 

  10. Wang X, Chen L, Ban T, Usman M, Guan Y, Liu S, Tianhao W, Chen H (2021) Knowledge graph quality control: a survey. Fundamental Res 1(5):607–626

    Article  MATH  Google Scholar 

  11. Xu F, Uszkoreit H, Du Y, Fan W, Zhao D, Zhu J (2019) Explainable ai: A brief survey on history, research areas, approaches and challenges. In Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019, Proceedings, Part II 8, pages 563–574. Springer

  12. Chattopadhyay A, Manupriya P, Sarkar A, Balasubramanian VN (2019) Neural network attributions: A causal perspective. In International Conference on Machine Learning, pages 981–990. PMLR

  13. Kitson NK, Constantinou AC, Guo Z, Liu Y, Chobtham K (2023) A survey of Bayesian network structure learning. Artif Intell Rev 56(8):8721–8814

    Article  MATH  Google Scholar 

  14. Mani S, Cooper GF (2000) Causal discovery from medical textual data. In Proceedings of the AMIA Symposium, page 542. American Medical Informatics Association

  15. Sesen MB, Nicholson AE, Banares-Alcantara R, Kadir T, Brady M (2013) Bayesian networks for clinical decision support in lung cancer care. PLoS ONE 8(12):e82349

    Article  Google Scholar 

  16. Chen L, Wang X, Ban T, Usman M, Liu S, Lyu D, Chen H (2022) Research ideas discovery via hierarchical negative correlation. IEEE Transactions on Neural Networks and Learning Systems

  17. Ramsey J, Glymour M, Sanchez-Romero R, Glymour C (2017) A million variables and more: the fast greedy equivalence search algorithm for learning high-dimensional graphical causal models, with an application to functional magnetic resonance images. Int J Data Sci Anal 3:121–129

    Article  MATH  Google Scholar 

  18. Jaber A, Zhang J, Bareinboim E (2019) Causal identification under markov equivalence: Completeness results. In International Conference on Machine Learning, pages 2981–2989. PMLR

  19. Ni Y L, Zhang K, Yuan C (2021) Improving causal discovery by optimal Bayesian network learning. In Proceedings of the AAAI Conference on Artificial Intelligence 35:8741–8748

  20. Wang YS, Drton M (2023) Causal discovery with unobserved confounding and non-gaussian data. J Mach Learn Res 24(271):1–61

    MathSciNet  MATH  Google Scholar 

  21. Westland JC (2015) Structural equation models. Stud Syst Decis Control 22(5):152

    MathSciNet  MATH  Google Scholar 

  22. Ben-Gal I (2008) Bayesian networks. Encyclopedia of statistics in quality and reliability

  23. Pearl J (2009) Causality. Cambridge university press, Cambridge

    Book  MATH  Google Scholar 

  24. Xingyu W, Jiang B, Zhong Y, Chen H (2022) Multi-target markov boundary discovery: Theory, algorithm, and application. IEEE Trans Pattern Anal Mach Intell 45(4):4964–4980

    MATH  Google Scholar 

  25. Wu X, Jiang B, Wang X, Ban T, Chen H (2023) Feature selection in the data stream based on incremental markov boundary learning. IEEE Transactions on Neural Networks and Learning Systems

  26. Waldmann MR, Martignon L (2022) A bayesian network model of causal learning. In Proceedings of the twentieth annual conference of the Cognitive Science Society, pages 1102–1107. Routledge

  27. Entner D, Hoyer PO (2010) On causal discovery from time series data using fci. Probabilistic graphical models, pages 121–128

  28. Li A, Beek P (2018) Bayesian network structure learning with side constraints. In International conference on probabilistic graphical models, pages 225–236. PMLR

  29. Tsamardinos I, Brown LE, Aliferis CF (2006) The max-min hill-climbing Bayesian network structure learning algorithm. Mach Learn 65:31–78

    Article  MATH  Google Scholar 

  30. Zhu J, Xingyu W, Usman M, Wang X, Chen H (2022) Link prediction in continuous-time dynamic heterogeneous graphs with causality of event types. Int J Crowd Sci 6(2):80–91

    Article  MATH  Google Scholar 

  31. Zarebavani B, Jafarinejad F, Hashemi M, Salehkaleybar S (2019) cupc: Cuda-based parallel pc algorithm for causal structure learning on gpu. IEEE Trans Parallel Distrib Syst 31(3):530–542

    Article  Google Scholar 

  32. Le TD, Hoang T, Li J, Liu L, Liu H, Shu H (2016) A fast pc algorithm for high dimensional causal discovery with multi-core pcs. IEEE/ACM Trans Comput Biol Bioinf 16(5):1483–1495

    Article  MATH  Google Scholar 

  33. Huang B, Zhang K, Lin Y, Schölkopf Bernhard, Glymour Clark (2018) Generalized score functions for causal discovery. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1551–1560

  34. Neath AA, Cavanaugh JE (2012) The bayesian information criterion: background, derivation, and applications. Wiley Interdisciplinary Rev: Comput Stat 4(2):199–203

    Article  MATH  Google Scholar 

  35. Amirkhani H, Rahmati M, Lucas PJF, Hommersom A (2016) Exploiting experts’ knowledge for structure learning of Bayesian networks. IEEE Trans Pattern Anal Mach Intell 39(11):2154–2170

    Article  MATH  Google Scholar 

  36. Ban T, Chen L, Wang X, Chen H (2023) From query tools to causal architects: Harnessing large language models for advanced causal discovery from data. arXiv preprint arXiv:2306.16902

  37. Wang X, Ban T, Chen L, Usman M, Guan Y, Lyu D, Cheng J, Chen H, Leung C, Miao C (2023) Decentralised knowledge graph evolution via blockchain. IEEE Transactions on Services Computing

  38. Ban T, Wang X, Wang X, Zhu J, Chen L, Fan Y (2023) Knowledge extraction from national standards for natural resources: a method for multi-domain texts. J Database Manage (JDM) 34(1):1–23

    Article  MATH  Google Scholar 

  39. Chen L, Ban T, Wang X, Lyu D, Chen H (2023) Mitigating prior errors in causal structure learning: towards llm driven prior knowledge. arXiv preprint arXiv:2306.07032

  40. Ban T, Chen L, Lyu D, Wang X, Chen H (2023) Causal structure learning supervised by large language model. arXiv preprint arXiv:2311.11689

  41. Wang X, Ban T, Chen L, Wu X, Lyu D, Chen H (2022) Knowledge verification from data. IEEE Transactions on Neural Networks and Learning Systems, pages 1–15,

  42. Ban T, Wang X, Chen L, Wu X, Chen Q, Chen H (2022) Quality evaluation of triples in knowledge graph by incorporating internal with external consistency. IEEE Transactions on Neural Networks and Learning Systems

  43. Wang X, Ban T, Chen L, Usman M, Wu T, Chen Q, Chen H (2023) A distribution-based representation of knowledge quality. Knowledge-Based Systems, page 111054

  44. Wang Z, Xiaoguang Gao Yu, Yang XT, Chen D (2021) Learning Bayesian networks based on order graph with ancestral constraints. Knowl-Based Syst 211:106515

    Article  MATH  Google Scholar 

  45. Patrício M, Pereira JA Lobo, Crisóstomo J, Matafome P, Gomes MM, Seiça R, Caramelo F (2018) Using resistin, glucose, age and bmi to predict the presence of breast cancer. BMC Cancer, 18

  46. Alldredge J, Leaf MC, Patel P, Coakley K, Longoria T, McLaren C, Randall Leslie M (2020) Prevalence and predictors of hiv screening in invasive cervical cancer: a 10 year cohort study. International J Gynecol Cancer 30(6)

  47. Chickering DM (2002) Optimal structure identification with greedy search. J Mach Learn Res 3(Nov):507–554

    MathSciNet  MATH  Google Scholar 

  48. Gámez José A, Mateo Juan L, Puerta José M (2007) A fast hill-climbing algorithm for bayesian networks structure learning. In Symbolic and Quantitative Approaches to Reasoning with Uncertainty: 9th European Conference, ECSQARU 2007, Hammamet, Tunisia, October 31-November 2, 2007. Proceedings 9, pages 585–597. Springer

Download references

Funding

This research was supported by the Scientific Research Project of Anhui Provincial Health Commission (No. AHWJ2022b058, AHWJ2023A10102), Joint Fund for Medical Artificial Intelligence of the First Affiliated Hospital of USTC (No. MAI2022Q009), USTC Research Funds of the Double First-Class Initiative (No. YD9110002085), and the National Natural Science Foundation of China (No. 32271176).

Author information

Authors and Affiliations

  1. School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, 230026, Anhui, China

    Zhenchao Tao

  2. Department of Radiation Oncology, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, 230031, Anhui, China

    Zhenchao Tao

  3. Department of Endocrinology, Anhui Provincial Hospital Affiliated to Anhui Medical University, Hefei, 230001, Anhui, China

    Meiyan Chi & Wei Wang

  4. Department of Endocrinology, Centre for Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China

    Meiyan Chi & Wei Wang

  5. School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, Anhui, China

    Lyuzhou Chen & Taiyu Ban

  6. Department of Information, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, 230031, Anhui, China

    Qiang Tu

  7. Department of Radiology, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, 230026, Anhui, China

    Fei Gao

Authors
  1. Zhenchao Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Meiyan Chi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lyuzhou Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Taiyu Ban
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qiang Tu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Fei Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Z.T. and M.C. curated the data and conducted the experiments. L.C., T.B., Q.T, and F.G. developed the methodology and performed the analysis. W.W. conceptualized and designed the study. Z.T., M.C., L.C. and T.B. wrote the main manuscript text. Q.T., F.G. and W.W. prepared all figures and tables. All authors reviewed the manuscript and approved the final version for submission.

Corresponding author

Correspondence to Wei Wang.

Ethics declarations

Conflict of interest

The authors declare no Conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tao, Z., Chi, M., Chen, L. et al. Clinical causal analysis via iterative active structure learning. Memetic Comp. 17, 7 (2025). https://doi.org/10.1007/s12293-025-00439-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12293-025-00439-5

Keywords