Abstract
Sepsis is among the leading causes of morbidity, mortality and high costs in the ICU. The early prediction and intervention of sepsis is a challenging task under strict time and cost constraints. In this paper, a novel High-order Markov Dynamic Bayesian Network (HMDBN) classifier with discrete features is presented for early prediction of sepsis at a high-order time point. The model structure is learned from the unrolled DBN by performing the K2 algorithm, and the features ‘disappeared’ in the prediction are eliminated using the VE method. Based on a few vital signs and laboratory results, an intuitive causal graph and indicating system are constructed to realize continuous prediction and probabilistic interpretation in real-time. Compared with other ten classical machine learning classifiers on evaluation metrics, HMDBN models have the highest AUROC scores on both internal tests and external validations for sepsis early prediction, and provide identifiable and interpretable results that allowing clinicians to immediately understand the reason for the prediction.
Similar content being viewed by others
Data availability
The datasets that support the findings of the current study are available from the corresponding author on reasonable request.
References
Hotchkiss R, Moldawer L, Opal S et al (2016) Sepsis and septic shock. Nat Rev Dis Primers 2:16045. https://doi.org/10.1038/nrdp.2016.45
Rello J, Valenzuela-Sánchez F, Ruiz-Rodriguez M, Moyano S (2017) Sepsis: A Review of Advances in Management. Adv Ther 34:2393–2411. https://doi.org/10.1007/s12325-017-0622-8
Fleischmann-Struzek C, Goldfarb DM, Schlattmann P, Schlapbach LJ, Reinhart K, Kissoon N (2018) The global burden of paediatric and neonatal sepsis: a systematic review. Lancet Respir Med 6(3):223–230. https://doi.org/10.1016/S2213-2600(18)30063-8
Dai T, Tayur S (2018) Handbook of Healthcare Analytics: Theoretical Minimum for Conducting 21st Century Research on Healthcare Operations, 1st edn. Wiley, New York, p 414
Subbe CP, Slater A, Menon D, Gemmell L (2006) Validation of physiological scoring systems in the accident and emergency department. Emerg Med J 23:841–845. https://doi.org/10.1136/emj.2006.035816
Singer M, Deutschman CS, Seymour CW, Shankar-Hari M, Annane D, Bauer M et al (2016) The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). JAMA 315(8):801–810. https://doi.org/10.1001/jama.2016.0287
Qin Q, Xia YQ, Cao Y (2017) Clinical study of a new Modified Early Warning System scoring system for rapidly evaluating shock in adults. J Crit Care 37:50–55. https://doi.org/10.1016/j.jcrc.2016.08.025
Sande DVD, Genderen MEV, Huiskens J, Gommers D, Bommel JV (2021) Moving from bytes to bedside: a systematic review on the use of artificial intelligence in the intensive care unit. Intensive Care Med 47:750–760. https://doi.org/10.1007/s00134-021-06446-7
Zohar Y, Itskovich SZ, Koren S, Zaidenstein R, Marchaim D, Koren R (2021) The association of diabetes and hyperglycemia with sepsis outcomes: a population-based cohort analysis. Intern Emerg Med 16:719–728. https://doi.org/10.1007/s11739-020-02507-9
Lai H, Wu G, Zhong Y, Chen G, Zhang W, Shi S, Xia Z (2023) Red blood cell distribution width improves the prediction of 28-day mortality for patients with sepsis-induced acute kidney injury: A retrospective analysis from MIMIC-IV database using propensity score matching. J Intensive Med 3:275–282. https://doi.org/10.1016/j.jointm.2023.02.005
Calvert JS, Price DA, Chettipally UK, Barton CW, Feldman MD, Hoffman JL, Jay M, Das R (2016) A computational approach to early sepsis detection. Comput Biol Med 74:69–73. https://doi.org/10.1016/j.compbiomed.2016.05.003
Harutyunyan H, Khachatrian H, Kale DC, Steeg GV, Galstyan A (2019) Multitask learning and benchmarking with clinical time series data. Sci Data 6(96). https://doi.org/10.1038/s41597-019-0103-9
Fagerstrom J, Bang M, Wilhelms D, Chew MS (2019) LiSep LSTM: A Machine Learning Algorithm for Early Detection of Septic Shock. Sci Rep 9:15132. https://doi.org/10.1038/s41598-019-51219-4
Scherpf M, Gräßer F, Malberg H, Zaunseder S (2019) Predicting sepsis with a recurrent neural network using the MIMIC III database. Comput Biol Med 113:103395. https://doi.org/10.1016/j.compbiomed.2019.103395
Shashikumar SP, Josef CS, Sharma A, Nemati S (2021) DeepAISE - An interpretable and recurrent neural survival model for early prediction of sepsis. Artif Intell Med 113:102036. https://doi.org/10.1016/j.artmed.2021.102036
Kaji DA, Zech JR, Kim JS, Cho SK, Dangayach NS, Costa AB, Oermann EK (2019) An attention based deep learning model of clinical events in the intensive care unit. PLoS One 14(2):e0211057. https://doi.org/10.1371/journal.pone.0211057
Javan SL, Sepehri MM, Javan ML, Khatibi T (2019) An intelligent warning model for early prediction of cardiac arrest in sepsis patients. Comput Methods Prog Biomed 178:47–58. https://doi.org/10.1016/j.cmpb.2019.06.010
Duan Y, Huo J, Chen M, Hou F, Yan G, Li S, Wang H (2023) Early prediction of sepsis using double fusion of deep features and handcrafted features. Appl Intell 53:17903–17919. https://doi.org/10.1007/s10489-022-04425-z
Friedman N, Murphy K, Russell S (1998) Learning the structure of dynamic probabilistic networks. In: Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998). https://doi.org/10.48550/arXiv.1301.7374
Murphy K, Russell S (2002) Dynamic Bayesian Networks: Representation, Inference and Learning. Dissertation, University of California, Berkeley
Friedman N (1997) Learning Belief Networks in the Presence of Missing Values and Hidden Variables. Int Conf Mach Learn ICML-97:125–133. https://doi.org/10.5555/645526.657145
Peelen L, Keizer NF, Jonge E, Bosman RJ, Abu-Hanna A, Peek N (2010) Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit. J Biomed Inform 43(2):273–286. https://doi.org/10.1016/j.jbi.2009.10.002
Friedman N (2013) The Bayesian Structural EM Algorithm. The Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI1998). https://doi.org/10.48550/arXiv.1301.7373
Dabrowski JJ, Beyers C, Villiers JP (2016) Systemic banking crisis early warning systems using dynamic Bayesian networks. Expert Syst Appl 62:225–242. https://doi.org/10.1016/j.eswa.2016.06.024
Nachimuthu SK, Haug PJ (2012) Early detection of sepsis in the emergency department using Dynamic Bayesian Networks. AMIA Ann Symp Proc 2012:653–662. https://www.researchgate.net/publication/234099960. Accessed 2022-12-08
Johnson A, Pollard TJ, Shen L et al (2016) MIMIC-III, a freely accessible critical care database. Sci Data 3:160035. https://doi.org/10.1038/sdata.2016.35
Griffin JE, Łatuszyński KG, Steel MF (2021) In search of lost mixing time: adaptive Markov chain Monte Carlo schemes for Bayesian variable selection with very large p. Biometrika 108(1):53–69. https://doi.org/10.1093/biomet/asaa055
Kumari T, Guleria V, Syal P, Aggarwal AK (2021) A Feature Cum Intensity Based SSIM Optimised Hybrid Image Registration Technique. 2021 International Conference on Computing, Communication and Green Engineering (CCGE), IEEE. https://doi.org/10.1109/CCGE50943.2021.9776407
Levy MM, Fink MP, Marshall JC et al (2003) 2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference. Intensive Care Med 29:530–538. https://doi.org/10.1007/s00134-003-1662-x
Shavdia D (2007) Septic shock: providing early warnings through multivariate logistic regression models. Dissertation, Harvard University, MIT Division of Health Sciences and Technology. https://dspace.mit.edu/handle/1721.1/42338. Accessed 27 Oct 2021
Schamoni S, Lindner HA, Schneider-Lindner V, Thiel M, Riezler S (2019) Leveraging implicit expert knowledge for non-circular machine learning in sepsis prediction. Artif Intell Med 100:101725. https://doi.org/10.1016/j.artmed.2019.101725
Elreedy D, Atiya AF (2019) A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance. Inf Sci 505:32–64. https://doi.org/10.1016/j.ins.2019.07.070
Koller D, Friedman N (2009) Probabilistic Graphical Models: Principles and Techniques, 1st edn. MIT Press, Cambridge, MA
Cooper GF, Herskovits E (1992) A Bayesian Method for the Induction of Probabilistic Networks from Data. Mach Learn 9:309–347. https://doi.org/10.1007/BF00994110
Wang S, Zhang S, Wu T, Duan Y, Zhou L, Lei H (2020) FMDBN: A first-order Markov dynamic Bayesian network classifier with continuous attributes. Knowl-Based Syst 195:105638. https://doi.org/10.1016/j.knosys.2020.105638
Ye Y, Li L, Lin Q, Wong KC, Li J, Ming Z (2022) Knowledge guided Bayesian classification for dynamic multi-objective optimization. Knowl-Based Syst 250:109173. https://doi.org/10.1016/j.knosys.2022.109173
Miller A, Panneerselvam J, Liu L (2022) A review of regression and classification techniques for analysis of common and rare variants and gene-environmental factors. Neurocomputing 489:466–485. https://doi.org/10.1016/j.neucom.2021.08.150
Lu D, Yue Y, Hu Z, Xu M, Tong Y, Ma H (2023) Effective detection of Alzheimer's disease by optimizing fuzzy K-nearest neighbors based on salp swarm algorithm. Comput Biol Med 159:106930. https://doi.org/10.1016/j.compbiomed.2023.106930
Breiman L, Friedman J, Stone CJ, Olshen RA (2017) Classification and Regression Trees, 1st edn. CRC press, New York
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Shahraki A, Abbasi M, Haugen Ø (2020) Boosting algorithms for network intrusion detection: A comparative evaluation of Real AdaBoost, Gentle AdaBoost and Modest AdaBoost. Eng Appl Artif Intell 94:103770. https://doi.org/10.1016/j.engappai.2020.103770
Ghosh A, SahaRay R, Chakrabarty S, Bhadra S (2021) Robust generalised quadratic discriminant analysis. Pattern Recogn 117:107981. https://doi.org/10.1016/j.patcog.2021.107981
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. https://doi.org/10.1007/BF00994018
Xiao J, Suab SA, Chen X, Singh CK, Singh D, Aggarwal AK et al (2023) Enhancing assessment of corn growth performance using unmanned aerial vehicles (UAVs) and deep learning. Measurement 214:112764. https://doi.org/10.1016/j.measurement.2023.112764
Wang S, Zhang S, Wu T, Duan Y, Zhou L (2022) Research on a dynamic full Bayesian classifier for time-series data with insufficient information. Appl Intell 52:1059–1075. https://doi.org/10.1007/s10489-021-02448-6
Acknowledgements
This work is supported by the National Natural Science Foundation of China [Grant numbers 72171176, 72021002, 82072228].
Author information
Authors and Affiliations
Contributions
Siwen Zhang and Yongrui Duan conceived and designed this study. Material preparation, data collection and analysis were performed by Siwen Zhang, Yongrui Duan, Fenggang Hou, Guoliang Yan, Shufang Li, Haihui Wang and Liang Zhou. The first draft of the manuscript was written by Siwen Zhang and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical standard
The authors state that this research complies with ethical standards. This research does not involve either human participants or animals.
Conflict of interests
The authors declare that there is no conflict of interests regarding the publication of this article.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
ESM 1
(PDF 148 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.
About this article
Cite this article
Zhang, S., Duan, Y., Hou, F. et al. Early prediction of sepsis using a high-order Markov dynamic Bayesian network (HMDBN) classifier. Appl Intell 53, 26384–26399 (2023). https://doi.org/10.1007/s10489-023-04920-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04920-x