Skip to main content

Advertisement

SpringerLink
Log in

Knowledge and data-driven prediction of organ failure in critical care patients

  • Research
  • Published:
Health Information Science and Systems Aims and scope Submit manuscript

Abstract

Purpose

The early detection of organ failure mitigates the risk of post-intensive care syndrome and long-term functional impairment. The aim of this study is to predict organ failure in real-time for critical care patients based on a data-driven and knowledge-driven machine learning method (DKM) and provide explanations for the prediction by incorporating a medical knowledge graph.

Methods

The cohort of this study was a subset of the 4,386 adult Intensive Care Unit (ICU) patients from the MIMIC-III dataset collected between 2001 and 2012, and the primary outcome was the Delta Sequential Organ Failure Assessment (SOFA) score. A real-time Delta SOFA score prediction model was developed with two key components: an improved deep learning temporal convolutional network (S-TCN) and a graph-embedding feature extraction method based on a medical knowledge graph. Entities and relations related to organ failure were extracted from the Unified Medical Language System to build the medical knowledge graph, and patient data were mapped onto the graph to extract the embeddings. We measured the performance of our DKM approach with cross-validation to avoid the formation of biased assessments.

Results

An area under the receiver operating characteristic curve (AUC) of 0.973, a precision of 0.923, a NPV of 0.989, and an F1 score of 0.927 were achieved using the DKM approach, which significantly outperformed the baseline methods. Additionally, the performance remained stable following external validation on the eICU dataset, which consists of 2,816 admissions (AUC = 0.981, precision = 0.860, NPV = 0.984). Visualization of feature importance for the Delta SOFA score and their relationships on the basic clinical medical (BCM) knowledge graph provided a model explanation.

Conclusion

The use of an improved TCN model and a medical knowledge graph led to substantial improvement in prediction accuracy, providing generalizability and an independent explanation for organ failure prediction in critical care patients. These findings show the potential of incorporating prior domain knowledge into machine learning models to inform care and service planning.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Carrico CJ, Meakins JL, Marshall J, et al. Multiple-organ-failure syndrome. Arch Surg. 1986;121(2):196–208.

    Article  Google Scholar 

  2. Lambden S, Laterre PF, Levy MM, et al. The SOFA score—development, utility and challenges of accurate assessment in clinical trials. Crit Care. 2019;23(1):1–9.

    Article  Google Scholar 

  3. Kim HI, Park S. Sepsis: early recognition and optimized treatment. Crit Care Med. 2019;82(1):6–14.

    Google Scholar 

  4. Lauritsen SM, Kristensen M, Olsen MV, Larsen MS, Lauritsen KM, Jørgensen MJ, Lange J, Thiesson B. Explainable artificial intelligence model to predict acute critical illness from electronic health records. Nat Commun. 2020;11(1):1–11.

    Article  Google Scholar 

  5. Yang M, Liu C, Wang X, et al. An explainable artificial intelligence predictor for early detection of sepsis. Crit Care Med. 2020;48(11):e1091–6.

    Article  Google Scholar 

  6. Chen W, Wang S, Long G, et al. Dynamic illness severity prediction via multi-task rnns for intensive care unit. In: IEEE International Conference on Data Mining (ICDM)IEEE, pp. 917–922; 2018

  7. Zhang X, Zhao Y, Callcut R, et al. Multiple Organ Failure Prediction with Classifier-Guided Generative Adversarial Imputation Networks. 2021, p^pp arXiv:2106.11878

  8. Antoniadi AM, Du Y, Guendouz Y, et al. Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Appl Sci. 2021;11(11):5088.

    Article  Google Scholar 

  9. Feldmann C, Philipps M, Bajorath J. Explainable machine learning predictions of dual-target compounds reveal characteristic structural features. Sci Rep. 2021;11(1):1–11.

    Google Scholar 

  10. Durán JM. Dissecting scientific explanation in AI (sXAI): a case for medicine and healthcare. Artif Intell. 2021;297:103498.

    Article  MathSciNet  Google Scholar 

  11. Rotmensch M, Halpern Y, Tlimat A, et al. Learning a health knowledge graph from electronic medical records. Sci Rep. 2017;7(1):1–11.

    Article  Google Scholar 

  12. Li L, Wang P, Yan J, et al. Real-world data medical knowledge graph: construction and applications. Artif Intell Med. 2020;103:101817.

    Article  Google Scholar 

  13. Collins GS, Reitsma JB, Altman DG, et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. J Br Surg. 2015;102(3):148–58.

    Article  Google Scholar 

  14. Vincent J-L, Moreno R, Takala J, et al. The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure. Intens Care Med. 1996;22:707–10.

    Article  Google Scholar 

  15. Quan H, Sundararajan V, Halfon P, et al. Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data. Med Care. 2005;43(11):1130–9.

    Article  Google Scholar 

  16. Benesty J, Chen J, Huang Y, et al. Pearson correlation coefficient. In: Noise reduction in speech processing

  17. Lipton ZC, Kale D, Wetzel R. Directly modeling missing data in sequences with rnns: Improved classification of clinical time series. In: Machine learning for healthcare conferencePMLR, pp. 253–270; 2016

  18. McCray AT, Razi AM, Bangalore AK, et al., The UMLS Knowledge Source Server: a versatile Internet-based research tool. In: Proceedings of the AMIA Annual Fall SymposiumAmerican Medical Informatics Association, pp. 164–168; 1996

  19. Donnelly K. SNOMED-CT: the advanced terminology and coding system for eHealth. Stud Health Technol Inform. 2006;121:279.

    Google Scholar 

  20. Brown EG, Wood L. Wood SJDs: the medical dictionary for regulatory activities (MedDRA). Drug Saf. 1999;20(2):109–17.

    Article  Google Scholar 

  21. Liu S, Ma W, Moore R, et al. RxNorm: prescription for electronic drug information exchange. IT Prof. 2005;7(5):17–23.

    Article  Google Scholar 

  22. Fragoso G, de Coronado S, Haber M, et al. Overview and utilization of the NCI thesaurus. Compar Funct Genomics. 2004;5(8):648–54.

    Article  Google Scholar 

  23. Abbreviations Used in Data Elements-2021AB Release. Available at: https://www.nlm.nih.gov/research/umls/knowledge_sources/metathesaurus/release/abbreviations.html. Accessed 12 Oct 2021

  24. Bordes A, Usunier N, Garcia-Duran A, et al: Translating embeddings for modeling multi-relational data. In: Advances in neural information processing systems; 2013

  25. Lea C, Vidal R, Reiter A, et al., Temporal convolutional networks: a unified approach to action segmentation. In: European Conference on Computer Vision (ECCV). Springer, Cham, pp. 47–54; 2016

  26. He K, Zhang X, Ren S, et al., Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770–778; 2016

  27. Tarjan R. Depth-first search and linear graph algorithms. SIAM J Comput. 1972;1(2):146–60.

    Article  MathSciNet  Google Scholar 

  28. Wijnberge M, Geerts BF, Hol L, et al. Effect of a machine learning–derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA. 2020;323(11):1052–60.

    Article  Google Scholar 

  29. Deng S, Zhang N, Zhang W, et al., Knowledge-driven stock trend prediction and explanation via temporal convolutional network. In: Proceedings of the World Wide Web Conference (WWW), pp. 678–685; 2019

  30. Wang M, Zhang J, Liu J, et al., Pdd graph: Bridging electronic medical records and biomedical knowledge graphs via entity linking. In: International Semantic Web Conference (ISWC). Springer, pp. 219–227; 2017

  31. Gong F, Wang M, Wang H, et al., SMR: Medical Knowledge Graph Embedding for Safe Medicine Recommendation. 2017, p^pp arXiv:1710.05980

  32. Sharma S, Santra B, Jana A, et al., Incorporating Domain Knowledge into Medical NLI using Knowledge Graphs. 2019, p^pp arXiv:1909.00160

  33. Ma F, Gao J, Suo Q, et al., Risk prediction on electronic health records with prior medical knowledge. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD), pp. 1910–1919; 2018

  34. Bai T, Vucetic S. Improving medical code prediction from clinical text via incorporating online knowledge sources. In: Proceedings of the World Wide Web Conference (WWW), pp 72–82; 2019

  35. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–58.

    Article  Google Scholar 

  36. Shickel B, Tighe PJ, Bihorac A, et al. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE J Biomed Health Inform. 2017;22(5):1589–604.

    Article  Google Scholar 

  37. Chen P, Dong W, Wang J, et al. Interpretable clinical prediction via attention-based neural network. BMC Med Inform Decis Mak. 2020;20(3):1–9.

    Google Scholar 

  38. Rajabi E, Etminani K. Towards a knowledge graph-based explainable decision support hystem in Healthcare. Stud Health Technol Inform. 2021;281:502–3.

    Google Scholar 

  39. Wang Q, Mao Z, Wang B, et al. Knowledge graph embedding: a survey of approaches and applications. IEEE Trans Knowl Data Eng. 2017;29(12):2724–43.

    Article  Google Scholar 

  40. Fleuren LM, Klausch TL, Zwager CL, et al. Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy. Intens Care Med. 2020;46(3):383–400.

    Article  Google Scholar 

Download references

Funding

The study was supported by the National Key Research and Development Program of China (No. 2022YFF0712400), the National Natural Science Foundation of China (81901842, 61906037, 62276063), Natural Science Foundation of Hunan Province (2021JJ40936), and China Primary Health Care Foundation (YLGX-WS-2020003).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Southeast University, Nanjing, 211189, People’s Republic of China

    Xinyu Ma, Meng Wang & Yanjian Zhang

  2. Department of Anesthesiology, Third Xiangya Hospital, Central South University, Changsha, 410013, People’s Republic of China

    Sihan Lin, Wen Ouyang & Xing Liu

  3. School of Computer Science and Engineering, The University of Hong Kong, Hong Kong, 999077, People’s Republic of China

    Yuhao Zhang

Authors
  1. Xinyu Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Meng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sihan Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuhao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yanjian Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wen Ouyang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xing Liu.

Ethics declarations

Conflict of interest

None.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Electronic supplementary material 1 (DOCX 117 kb)

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

Ma, X., Wang, M., Lin, S. et al. Knowledge and data-driven prediction of organ failure in critical care patients. Health Inf Sci Syst 11, 7 (2023). https://doi.org/10.1007/s13755-023-00210-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13755-023-00210-5

Keywords

Search

Navigation