Top

BMC Medical Informatics and Decision Making

Published in:

Open Access 01-07-2020 | Research

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Authors: Ming Cheng, Xiaolei Zhao, Xianfei Ding, Jianbo Gao, Shufeng Xiong, Yafeng Ren

Published in: BMC Medical Informatics and Decision Making | Special Issue 3/2020

Abstract

Background

Blood cultures are often performed to detect patients who has a serious illness without infections and patients with bloodstream infections. Early positive blood culture prediction is important, as bloodstream infections may cause inflammation of the body, even organ failure or death. However, existing work mainly adopts statistical models with laboratory indicators, and fails to make full use of textual description information from EHRs.

Methods

We study the problem of positive blood culture prediction by using neural network model. Specifically, we first construct dataset from raw EHRs. Then we propose a hybrid neural network which incorporates attention based Bi-directional Long Short-Term Memory and Autoencoder networks to fully capture the information in EHRs.

Results

In order to evaluate the proposed method, we constructe a dataset which consists of totally 5963 patients who had one or more blood cultures tests during hospitalization. Experimental results show that the proposed neural model gets 91.23% F-measure for this task.

Conclusions

The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models.

Cheng M, Li L, Ren Y, Lou Y, Gao J. A hybrid method to extract clinical information from chinese electronic medical records. IEEE Access. 2019; 7:70624–33. https://doi.org/10.1109/ACCESS.2019.2919121.CrossRef

Zhao C, Jiang J, Guan Y, Guo X, He B. Emr-based medical knowledge representation and inference via markov random fields and distributed representation learning. Artif Intell Med. 2018; 87:49–59. https://doi.org/10.1016/j.artmed.2018.03.005.CrossRef

Pereboom M, Mulder IJ, Verweij SL, van der Hoeven RTM, Becker ML. A clinical decision support system to improve adequate dosing of gentamicin and vancomycin. I J Med Inform. 2019; 124:1–5. https://doi.org/10.1016/j.ijmedinf.2019.01.002.CrossRef

Raita Y, Goto T, Faridi MK, Brown DFM, Camargo CA, Hasegawa K. Emergency department triage prediction of clinical outcomes using machine learning models. Crit Care. 2019; 23(1).

Matthew Clark. Prediction of clinical risks by analysis of preclinical and clinical adverse events. J Biomed Informa. 2015; 54(C):167–73.

Buchan K, Filannino M, Uzuner z. Automatic prediction of coronary artery disease from clinical narratives. J Biomed Inform. 2017; 72:23.CrossRef

Yang CC, Veltri P. Intelligent healthcare informatics in big data era. Artif Intell Med. 2015; 65(2):75–7. https://doi.org/10.1016/j.artmed.2015.08.002.CrossRef

Hu Y., Duan K., Zhang Y., Hossain M. S., Rahman S. M. M., Alelaiwi A.Simultaneously aided diagnosis model for outpatient departments via healthcare big data analytics. Multimedia Tools Appl. 2018; 77(3):3729–43. https://doi.org/10.1007/s11042-016-3719-1.CrossRef

Yang Z, Huang Y, Jiang Y, Sun Y, Zhang Y, Luo P. Clinical assistant diagnosis for electronic medical record based on convolutional neural network. Sci Rep. 2018; 8:6329. https://doi.org/10.1038/s41598-018-24389-w.CrossRef

10.

Jabbar MA, Deekshatulu BL, Chandra P. Prediction of heart disease using random forest and feature subset selection. In: Innovations in Bio-Inspired Computing and Applications-Proceedings of the 6th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA 2015) Held in Kochi, India During December 16-18, 2015. Switzerland: Springer: 2015. p. 187–96. https://doi.org/10.1007/978-3-319-28031-8_16.

11.

van der Geest PJ, Mohseni M, Linssen J, Duran S, de Jonge R, Groeneveld ABJ. The intensive care infection score – a novel marker for the prediction of infection and its severity. Crit Care. 2016; 20(1):1–8.CrossRef

12.

GERDES JS, POLIN RA. Sepsis screen in neonates with evaluation of plasma fibronectin. Pediatr Infect Dis J. 1987; 6(5):443.CrossRef

13.

Wang H, Zhang W, Zeng Q, Li Z, Feng K, Liu L. Extracting important information from chinese operation notes with natural language processing methods. J Biomed Informa. 2014; 48:130–6. https://doi.org/10.1016/j.jbi.2013.12.017.CrossRef

14.

Rink B, Harabagiu SM, Roberts K. Automatic extraction of relations between medical concepts in clinical texts. JAMIA. 2011; 18(5):594–600. https://doi.org/10.1136/amiajnl-2011-000153.PubMed

15.

Hayakawa K, Mezaki K, Kobayakawa M, Yamamoto K, Ohmagari N. Impact of rapid identification of positive blood cultures using the verigene system on antibiotic prescriptions: A prospective study of community-onset bacteremia in a tertiary hospital in japan. Plos One. 2017; 12(7):0181548.CrossRef

16.

Lee JH, Kim YH. Predictive factors of true bacteremia and the clinical utility of blood cultures as a prognostic tool in patients with community-onset pneumonia. Medicine. 2016; 95(41):5058.CrossRef

17.

Matheny ME, FitzHenry F, Speroff T, Hathaway J, Murff HJ, Brown SH, Fielstein EM, Dittus RS, Elkin PL. Detection of blood culture bacterial contamination using natural language processing. In: AMIA 2009, American Medical Informatics Association Annual Symposium, November 14-18, 2009. San Francisco: AMIA: 2009.

18.

Steenkiste TV, Ruyssinck J, Baets LD, Decruyenaere J, Turck FD, Ongenae F, Dhaene T. Accurate prediction of blood culture outcome in the intensive care unit using long short-term memory neural networks. Artif Intell Med. 2019; 97:38–43. https://doi.org/10.1016/j.artmed.2018.10.008.CrossRef

19.

Ren Y, Fei H, Liang X, Ji D, Cheng M. A hybrid neural network model for predicting kidney disease in hypertension patients based on electronic health records. BMC Med Inf Decis Making. 2019; 19-S(2):131–8. https://doi.org/10.1186/s12911-019-0765-4.

20.

Flynt A, Daepp MIG. Diet-related chronic disease in the northeastern united states: a model-based clustering approach. Int J Health Geogr. 2015; 14(1):25.CrossRef

21.

Zou Q, Qu K, Luo Y, Yin D, Ju Y, Tang H. Predicting diabetes mellitus with machine learning techniques. Front Genet. 2018; 9:515.CrossRef

22.

Ding X, Li J, Liang H, Wang Z, Jiao T, Liu Z, Yi L, Bian W, Wang S, Xizhu, Sun T. Predictive model for acute respiratory distress syndrome events in ICU patients in china using machine learning algorithms: a secondary analysis of a cohort study. J Trans Med. 2019; 17:326.CrossRef

23.

Liu Y, Liu Y-H, Tan N, Chen J-Y, Zhou Y-L, Duan C-Y, Li H-L, Chen P-Y. Novel risk scoring for pre-procedural prediction of contrast-induced nephropathy and poor long-term outcomes among patients with chronic total occlusion undergoing percutaneous coronary intervention. Eur Heart J Suppl. 2015; 17(suppl C):34–41.CrossRef

24.

Ripoll VJR, Vellido A, Romero E, Ruiz-Rodríguez JC. Sepsis mortality prediction with the quotient basis kernel. Artif Intell Med. 2014; 61(1):45–52. https://doi.org/10.1016/j.artmed.2014.03.004.CrossRef

25.

Mani S, Ozdas A, Aliferis CF, Varol HA, Chen Q, Carnevale RJ, Chen Y, Romano-Keeler J, Nian H, Weitkamp J. Medical decision support using machine learning for early detection of late-onset neonatal sepsis. JAMIA. 2014; 21(2):326–36. https://doi.org/10.1136/amiajnl-2013-001854.PubMed

26.

Lukaszewski RA, Yates AM, Jackson MC, Swingler K, Scherer JM, Simpson AJ, Sadler P, McQuillan P, Titball RW, Brooks TJG. Presymptomatic prediction of sepsis in intensive care unit patients. Clin Vaccine Immunol Cvi. 2008; 15(7):1089.CrossRef

27.

Khor R, Nguyen AN, O’Dwyer J, Kothari G, Sia J, Chang D, Ng SP, Duchesne G, Foroudi F. Extracting tumour prognostic factors from a diverse electronic record dataset in genito-urinary oncology. I J Med Informas. 2019; 121:53–7. https://doi.org/10.1016/j.ijmedinf.2018.10.008.CrossRef

28.

Hu D, Dong W, Lu X, Duan H, He K, Huang Z. Evidential MACE prediction of acute coronary syndrome using electronic health records. BMC Med Inf Decis Making. 2019; 19-S(2):9–17. https://doi.org/10.1186/s12911-019-0754-7.

29.

Fan Z, Bi D, He L, Shiping M, Gao S, Li C. Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder. Neurocomputing. 2017; 243(C):12–20.CrossRef

30.

Vincent P, Larochelle H, Bengio Y, Manzagol P. Extracting and composing robust features with denoising autoencoders. In: Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008), June 5-9, 2008. Helsinki, Finland: ACM Press: 2008. p. 1096–103. https://doi.org/10.1145/1390156.1390294.

31.

Ling W, Dyer C, Black AW, Trancoso I. Two/too simple adaptations of word2vec for syntax problems. In: Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies. Denver: The Association for Computational Linguistics: 2015. p. 1299–04. https://doi.org/10.3115/v1/n15-1142.

32.

Chen R, Yang Y, Miao F, Cai Y, Li Y. 3-year risk prediction of coronary heart disease in hypertension patients: A preliminary study. In: International Conference of the IEEE Engineering in Medicine & Biology Society. Jeju Island: IEEE: 2017. p. 1182–85. https://doi.org/10.1109/embc.2017.8037041.

Title: Prediction of blood culture outcome using hybrid neural network model based on electronic health records
Authors: Ming Cheng
Xiaolei Zhao
Xianfei Ding
Jianbo Gao
Shufeng Xiong
Yafeng Ren
Publication date: 01-07-2020
Publisher: BioMed Central
Published in: BMC Medical Informatics and Decision Making / Issue Special Issue 3/2020
Electronic ISSN: 1472-6947
DOI: https://doi.org/10.1186/s12911-020-1113-4

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Abstract

Background

Methods

Results

Conclusions

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Special Issue 3/2020

A benchmark dataset and case study for Chinese medical question intent classification

Modelling clinical experience data as an evidence for patient-oriented decision support

A semi-supervised approach for extracting TCM clinical terms based on feature words

A prognostic index based on a fourteen long non-coding RNA signature to predict the recurrence-free survival for muscle-invasive bladder cancer patients

Supervised-actor-critic reinforcement learning for intelligent mechanical ventilation and sedative dosing in intensive care units

Using predictive process monitoring to assist thrombolytic therapy decision-making for ischemic stroke patients