Feature engineering combined with 1-D convolutional neural network for improved mortality prediction
-
Rohit Verma
,
Saumil Maheshwari
Abstract
Objectives
The appropriate care for patients admitted in Intensive care units (ICUs) is becoming increasingly prominent, thus recognizing the use of machine learning models. The real-time prediction of mortality of patients admitted in ICU has the potential for providing the physician with the interpretable results. With the growing crisis including soaring cost, unsafe care, misdirected care, fragmented care, chronic diseases and evolution of epidemic diseases in the domain of healthcare demands the application of automated and real-time data processing for assuring the improved quality of life. The intensive care units (ICUs) are responsible for generating a wealth of useful data in the form of Electronic Health Record (EHR). This data allows for the development of a prediction tool with perfect knowledge backing.
Method
We aimed to build the mortality prediction model on 2012 Physionet Challenge mortality prediction database of 4,000 patients admitted in ICU. The challenges in the dataset, such as high dimensionality, imbalanced distribution and missing values, were tackled with analytical methods and tools via feature engineering and new variable construction. The objective of the research is to utilize the relations among the clinical variables and construct new variables which would establish the effectiveness of 1-Dimensional Convolutional Neural Network (1-D CNN) with constructed features.
Results
Its performance with the traditional machine learning algorithms like XGBoost classifier, Light Gradient Boosting Machine (LGBM) classifier, Support Vector Machine (SVM), Decision Tree (DT), K-Neighbours Classifier (K-NN), and Random Forest Classifier (RF) and recurrent models like Long Short-Term Memory (LSTM) and LSTM-attention is compared for Area Under Curve (AUC). The investigation reveals the best AUC of 0.848 using 1-D CNN model.
Conclusion
The relationship between the various features were recognized. Also, constructed new features using existing ones. Multiple models were tested and compared on different metrics.
Research funding: None declared.
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Competing interests: The authors declare no conflict of interest.
Ethical approval: T he conducted research is not related to either human or animal use.
References
1. Maheshwari, S, Verma, R, Shukla, A, Tiwari, R. Feature engineering combined with 1 D convolutional neural network for improved mortality prediction; 2019. arXiv preprint arXiv:1912.03789.Suche in Google Scholar
2. Ding, Y, Wang, Y, Zhou, D. Mortality prediction for ICU patients combining just-in-time learning and extreme learning machine. Neurocomputing 2018;281:12–9. https://doi.org/10.1016/j.neucom.2017.10.044.Suche in Google Scholar
3. Berger, JT, Holubkov, R, Reeder, R, Wessel, DL, Meert, K, Berg, RA, et al.. Eunice Kennedy Shriver National Institute of Child health and human development Collaborative pediatric critical care research network. Morbidity and mortality prediction in pediatric heart surgery: physiological profiles and surgical complexity. J Thorac Cardiovasc Surg 2017;154:620–8. https://doi.org/10.1016/j.jtcvs.2017.01.050.Suche in Google Scholar
4. Le Gall, JR, Loirat, P, Alperovitch, A, Glaser, P, Granthil, C, Mathieu, D, et al.. A simplified acute physiology score for ICU patients. Crit Care Med 1984;12:975–7. https://doi.org/10.1097/00003246-198411000-00012.Suche in Google Scholar
5. Knaus, WA, Zimmerman, JE, Wagner, DP, Draper, EA, Lawrence, DE. APACHE-acute physiology and chronic health evaluation: a physiologically based classification system. Crit Care Med 1981;9:591–7. https://doi.org/10.1097/00003246-198108000-00008.Suche in Google Scholar
6. Le Gall, JR, Lemeshow, S, Saulnier, F. A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study. Jama 1993;270:2957–63. https://doi.org/10.1001/jama.1993.03510240069035.Suche in Google Scholar
7. Knaus, WA, Draper, EA, Wagner, DP, Zimmerman, JE. APACHE II: a severity of disease classification system. Crit Care Med 1985;13:818–29. https://doi.org/10.1097/00003246-198510000-00009.Suche in Google Scholar
8. Knaus, WA, Wagner, DP, Draper, EA, Zimmerman, JE, Bergner, M, Bastos, PG, et al.. The APACHE III prognostic system: risk prediction of hospital mortality for critically III hospitalized adults. Chest 1991;100:1619–36. https://doi.org/10.1378/chest.100.6.1619.Suche in Google Scholar
9. Poole, D, Rossi, C, Anghileri, A, Giardino, M, Latronico, N, Radrizzani, D, et al.. External validation of the Simplified Acute Physiology Score (SAPS) 3 in a cohort of 28,357 patients from 147 Italian intensive care units. Intensive Care Med 2009;35:1916. https://doi.org/10.1007/s00134-009-1615-0.Suche in Google Scholar
10. Katsaragakis, S, Papadimitropoulos, K, Antonakis, P, Strergiopoulos, S, Konstadoulakis, MM, Androulakis, G. Comparison of acute physiology and chronic health evaluation II (APACHE II) and simplified acute physiology score II (SAPS II) scoring systems in a single Greek intensive care unit. Crit Care Med 2000;28:426–32. https://doi.org/10.1097/00003246-200002000-00023.Suche in Google Scholar
11. Beck, DH, Smith, GB, Pappachan, JV, Millar, B. External validation of the SAPS II, APACHE II and APACHE III prognostic models in South England: a multicentre study. Intensive Care Med 2003;29:249–56. https://doi.org/10.1007/s00134-002-1607-9.Suche in Google Scholar
12. Nassar, APJr, Mocelin, AO, Nunes, AL, Giannini, FP, Brauer, L, Andrade, FM, et al.. Caution when using prognostic models: a prospective comparison of 3 recent prognostic models. J Crit Care 2012;27:423–e1. https://doi.org/10.1016/j.jcrc.2011.08.016.Suche in Google Scholar
13. De Lange, DW, Brinkman, S, Flaatten, H, Boumendil, A, Morandi, A, Andersen, FH, et al.. Cumulative prognostic score predicting mortality in patients older than 80 years admitted to the ICU. J Am Geriatr Soc 2019;67:1263–7. https://doi.org/10.1111/jgs.15888.Suche in Google Scholar
14. Nguile-Makao, M, Zahar, JR, Français, A, Tabah, A, Garrouste-Orgeas, M, Allaouchiche, B, et al.. Attributable mortality of ventilator-associated pneumonia: respective impact of main characteristics at ICU admission and VAP onset using conditional logistic regression and multi-state models. Intensive Care Med 2010;36:781–9. https://doi.org/10.1007/s00134-010-1824-6.Suche in Google Scholar
15. Rosenberg, AL. Recent innovations in intensive care unit risk-prediction models. Curr Opin Crit Care 2002;8:321–30. https://doi.org/10.1097/00075198-200208000-00009.Suche in Google Scholar
16. Xu, J, Zhang, Y, Zhang, P, Mahmood, A, Li, Y, Khatoon, S. Data mining on ICU mortality prediction using early temporal data: a survey. Int J Inf Technol Deci Mak 2017;16:117–59.10.1142/S0219622016300020Suche in Google Scholar
17. Delen, D, Walker, G, Kadam, A. Predicting breast cancer survivability: a comparison of three data mining methods. Artif Intell Med 2005;34:113–27. https://doi.org/10.1016/j.artmed.2004.07.002.Suche in Google Scholar
18. Sierra, B, Serrano, N, LarrañAga, P, Plasencia, EJ, Inza, I, JiméNez, JJ, et al.. Using Bayesian networks in the construction of a bi-level multi-classifier. A case study using intensive care unit patients data. Artif Intell Med 2001;22:233–48. https://doi.org/10.1016/s0933-3657(00)00111-1.Suche in Google Scholar
19. Vieira, SM, Mendonça, LF, Farinha, GJ, Sousa, JM. Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients. Appl Soft Comput 2013;13:3494–504. https://doi.org/10.1016/j.asoc.2013.03.021.Suche in Google Scholar
20. Liu, J, Chen, XX, Fang, L, Li, JX, Yang, T, Zhan, Q, et al.. Mortality prediction based on imbalanced high-dimensional ICU big data. Comput Ind 2018;98:218–25. https://doi.org/10.1016/j.compind.2018.01.017.Suche in Google Scholar
21. Greff, K, Srivastava, RK, Koutník, J, Steunebrink, BR, Schmidhuber, J. LSTM: a search space odyssey. IEEE Trans Neur Netw Learn Syst 2016;28:2222–32.10.1109/TNNLS.2016.2582924Suche in Google Scholar PubMed
22. Awad, A, Bader-El-Den, M, McNicholas, J, Briggs, J, El-Sonbaty, Y. Predicting hospital mortality for intensive care unit patients: time-series analysis. Health Inf J 2020;26:1043–59. https://doi.org/10.1177/1460458219850323.Suche in Google Scholar
23. Goldberger, AL, Amaral, LA, Glass, L, Hausdorff, JM, Ivanov, PC, Mark, RG, et al.. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 2000;101:e215–20. https://doi.org/10.1161/01.cir.101.23.e215.Suche in Google Scholar
24. BUN to Creatinine ratio. Wikipedia. Available from: https://en.wikipedia.org/wiki/BUN-to-creatinine_ratio [Accessed: 24 Oct 2018].Suche in Google Scholar
25. Jha, BK, Sharma, MR. Correlation between serum albumin and initial GCS in patient with head injury in a tertiary hospital. J Soc Surg Nepal 2015;18:63.10.3126/jssn.v18i3.15335Suche in Google Scholar
26. Bernard, F, Al-Tamimi, YZ, Chatfield, D, Lynch, AG, Matta, BF, Menon, DK. Serum albumin level as a predictor of outcome in traumatic brain injury: potential for treatment. J Trauma Acute Care Surg 2008;64:872–5. https://doi.org/10.1097/ta.0b013e31803428cc.Suche in Google Scholar
27. Pandey, MK, Baranwal, SK, Panwar, DS, Saha, SK, Roy, K, Ghosh, S, et al.. Serial estimation of serum albumin and its role in traumatic brain injury patients. Asian J Med Sci 2016;7:31–8. https://doi.org/10.3126/ajms.v7i4.14124.Suche in Google Scholar
28. Ince, T, Kiranyaz, S, Eren, L, Askar, M, Gabbouj, M. Real-time motor fault detection by 1-D convolutional neural networks. IEEE Trans Ind Electron 2016;63:7067–75. https://doi.org/10.1109/tie.2016.2582729.Suche in Google Scholar
29. Ghose, S, Mitra, J, Khanna, S, Dowling, J. An improved patient-specific mortality risk prediction in ICU in a random Forest classification framework. Stud Health Technol Inform 2015;214:56–61.Suche in Google Scholar
30. Che, Z, Kale, D, Li, W, Bahadori, MT, Liu, Y. Deep computational phenotyping. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney: Association for Computing Machinery; 2015:507–16 pp.10.1145/2783258.2783365Suche in Google Scholar
31. Bhattacharya, S, Rajan, V, Shrivastava, H. Icu mortality prediction: a classification algorithm for imbalanced datasets In: Thirty-First AAAI Conference on Artificial Intelligence. San Francisco: AAAI Press; 2017.10.1609/aaai.v31i1.10721Suche in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Research Article
- Robust controller for cancer chemotherapy dosage using nonlinear kernel-based error function
- Review
- Deep learning of the role of interleukin IL-17 and its action in promoting cancer
- Research Articles
- An empirical survey of electroencephalography-based brain-computer interfaces
- Analysis of brain waves changes in stressful situations based on horror game with the implementation of virtual reality and brain-computer interface system: a case study
- Jaya Spider Monkey Optimization-driven Deep Convolutional LSTM for the prediction of COVID’19
- Feature engineering combined with 1-D convolutional neural network for improved mortality prediction
- On the mutation model used in the fingerprinting DNA
Artikel in diesem Heft
- Research Article
- Robust controller for cancer chemotherapy dosage using nonlinear kernel-based error function
- Review
- Deep learning of the role of interleukin IL-17 and its action in promoting cancer
- Research Articles
- An empirical survey of electroencephalography-based brain-computer interfaces
- Analysis of brain waves changes in stressful situations based on horror game with the implementation of virtual reality and brain-computer interface system: a case study
- Jaya Spider Monkey Optimization-driven Deep Convolutional LSTM for the prediction of COVID’19
- Feature engineering combined with 1-D convolutional neural network for improved mortality prediction
- On the mutation model used in the fingerprinting DNA
