journal article·2020-02-08Open access

Prediction of Post-Intubation Tachycardia Using Machine-Learning Models

Hanna Kim, Young-Seob Jeong, Ah Reum Kang, Woohyun Jung, Yang Hoon Chung, Bon Sung Koo, Sang Hyun Kim

Applied Sciences· Volume 10· Issue 3

Abstract

Tachycardia is defined as a heart rate greater than 100 bpm for more than 1 min. Tachycardia often occurs after endotracheal intubation and can cause serious complication in patients with cardiovascular disease. The ability to predict post-intubation tachycardia would help clinicians by notifying a potential event to pre-treat. In this paper, we predict the potential post-intubation tachycardia. Given electronic medical record and vital signs collected before tracheal intubation, we predict whether post-intubation tachycardia will occur within 10 min. Of 1931 available patient datasets, 257 remained after filtering those with inappropriate data such as outliers and inappropriate annotations. Three feature sets were designed using feature selection algorithms, and two additional feature sets were defined by statistical inspection or manual examination. The five feature sets were compared with various machine learning models such as naïve Bayes classifiers, logistic regression, random forest, support vector machines, extreme gradient boosting, and artificial neural networks. Parameters of the models were optimized for each feature set. By 10-fold cross validation, we found that an logistic regression model with eight-dimensional hand-crafted features achieved an accuracy of 80.5%, recall of 85.1%, precision of 79.9%, an F1 score of 79.9%, and an area under the receiver operating characteristic curve of 0.85.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Atrial Fibrillation Management and Outcomes · Phonocardiography and Auscultation Techniques · Airway Management and Intubation Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

SCH Media Labs, Soonchunhyang University, Asan 31538, Korea

Department of Anesthesiology and Pain Medicine, Soonchunhyang University Bucheon Hospital, Soonchunhyang University College of Medicine, Bucheon 14584, Korea

References (31)

Show source-provided references
1. Acute hypertension during induction of anaesthesia and endotracheal intubation in normotensive man10.1093/bja/42.7.618 ↗
2. Crisis management during anaesthesia: Tachycardia10.1136/qshc.2002.004432 ↗
3. Crisis management during anaesthesia: Hypertension10.1136/qshc.2002.004127 ↗
4. Beta-blocker use and survival in patients with ventricular fibrillation or symptomatic ventricular tachycardia: The Antiarrhythmics Versus Implantable Defibrillators (AVID) trial10.1016/S0735-1097(99)00234-X ↗
5. Landiolol and esmolol prevent tachycardia without altering cerebral blood flow10.1007/BF03021600 ↗
6. Cardiac effects of opioid therapy10.1111/pme.12915 ↗
7. Jeong, Y.S., Kang, A.R., Jung, W., Lee, S.J., Lee, S., Lee, M., Chung, Y.H., Koo, B.S., and Kim, S.H. (2019). Prediction of Blood Pressure after Induction of Anesthesia Using Deep Learning: A Feasibility Study. Appl. Sci., 9.10.3390/app9235135 ↗
8. Evaluating and comparing performance of feature combinations of heart rate variability measures for cardiac rhythm classification10.1016/j.bspc.2011.10.001 ↗
9. Ehtiati, N., Attarodi, G., Dabanloo, N.J., Sedehi, J.F., and Nasrabadi, A.M. (2017, January 24–27). Prediction of ventricular tachycardia using nonlinear features of heart rate variability signal such as poincare plot, approximate and sample entropy, recurrence plot. Proceedings of the 2017 Computing in Cardiology (CinC), Rennes, France.10.22489/CinC.2017.099-274 ↗
10. Shashikant, R., and Chetankumar, P. (2019). Predictive model of cardiac arrest in smokers using machine learning technique based on Heart Rate Variability parameter. Appl. Comput. Inform.10.1016/j.aci.2019.06.002 ↗
11. Joo, S., Choi, K.J., and Huh, S.J. (2010, January 26–29). Prediction of ventricular tachycardia by a neural network using parameters of heart rate variability. Proceedings of the 2010 Computing in Cardiology, Belfast, UK.
12. Riasi, A., and Mohebbi, M. (2015, January 3–5). Prediction of ventricular tachycardia using morphological features of ECG signal. Proceedings of the 2015 The International Symposium on Artificial Intelligence and Signal Processing (AISP), Mashhad, Iran.10.1109/AISP.2015.7123515 ↗
13. Classification of cardiac abnormalities using reduced features of heart rate variability signal
14. Vital Recorder—A free research tool for automatic recording of high-resolution time-synchronised physiological data from multiple anaesthesia devices10.1038/s41598-018-20062-4 ↗
15. Hira, Z.M., and Gillies, D.F. (2015). A review of feature selection and feature extraction methods applied on microarray data. Adv. Bioinform., 2015.10.1155/2015/198363 ↗
16. Scikit-learn: Machine learning in Python
17. Random forests10.1023/A:1010933404324 ↗
18. The use and interpretation of logistic regression in higher education journals: 1988–199910.1023/A:1014858517172 ↗
19. The optimality of naive Bayes
20. A tutorial on support vector machines for pattern recognition10.1023/A:1009715923555 ↗
21. Chen, T., and Guestrin, C. (2016, January 13–17). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, San Francisco, CA, USA.10.1145/2939672.2939785 ↗
22. Haykin, S. (2010). Neural Networks and Learning Machines, 3/E, Pearson Education.
23. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation
24. Sex differences in cardiac electrophysiology and clinical arrhythmias: Epidemiology, therapeutics, and mechanisms10.1016/j.cjca.2014.03.032 ↗
25. Gender and cardiac arrhythmias
26. Yoon, J.H., Mu, L., Chen, L., Dubrawski, A., Hravnak, M., Pinsky, M.R., and Clermont, G. (2019). Predicting tachycardia as a surrogate for instability in the intensive care unit. J. Clin. Monit. Comput., 1–13.10.1007/s10877-019-00277-0 ↗
27. Haemodynamic effects of remifentanil in children with and without intravenous atropine. An echocardiographic study10.1093/bja/aeh293 ↗
28. Effect of remifentanil on the haemodynamic response to orotracheal intubation10.1093/bja/80.4.467 ↗
29. A multicenter evaluation of total intravenous anesthesia with remifentanil and propofol for elective inpatient surgery10.1213/00000539-199608000-00014 ↗
30. Bispectral index (BIS) helps predicting bad neurological outcome in comatose survivors after cardiac arrest and induced therapeutic hypothermia10.1016/j.resuscitation.2009.01.008 ↗
31. Prediction of ventricular tachycardia one hour before occurrence using artificial neural networks10.1038/srep32390 ↗