Feature engineering combined with 1-D convolutional neural network for improved mortality prediction

• Autorzy: Verma Rohit , Maheshwari Saumil , Shukla Anupam

Identyfikatory

DOI

10.1515/bams-2020-0056

• Języki publikacji: EN

Abstrakty

EN

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 LSTMattention 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.

Słowa kluczowe

EN

1-D CNN; feature engineering; LSTM; mortality prediction; random forest; XGBoost

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2020
• Tom: Vol. 16, no. 4
• Strony: art. no. 20200056
• Opis fizyczny: Bibliogr. 31 poz., rys., tab.

Twórcy

autor

Verma Rohit

• Atal Bihari Vajpayee- Indian Institute of Information Technology and Management, Gwalior, Madhya Pradesh, India, Phone: [phone]

autor

Maheshwari Saumil

• Bennett University, Greater Noida, Uttar Pradesh, India

autor

Shukla Anupam

• Indian Institute of Information Technology, Pune, Maharashtra, India

Bibliografia

• 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.
• 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.
• 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.
• 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.
• 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.
• 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.
• 7. Knaus WA, Draper EA, Wagner DP, Zimmerman JE. APACHE II: a severity of disease classification system. Crit Care Med 1985;13: 818-29.
• 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.
• 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.
• 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.
• 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.
• 12. Nassar AP Jr., 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.
• 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.
• 14. Nguile-Makao M, Zahar JR, Français A, Tabah A, Garrouste-Orgeas M, Allaouchiche B, et al. Attributable mortality of ventilatorassociated 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.
• 15. Rosenberg AL. Recent innovations in intensive care unit riskprediction models. Curr Opin Crit Care 2002;8:321-30.
• 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.
• 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.
• 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.
• 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.
• 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.
• 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.
• 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.
• 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.
• 24. BUN to Creatinine ratio. Wikipedia. Available from: https://en.wikipedia.org/wiki/BUN-to-creatinine_ratio [Accessed: 24 Oct 2018].
• 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.
• 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.
• 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.
• 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.
• 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.
• 30. Che Z, Kale D, Li W, Bahadori MT, Liu Y. Deep computational phenotyping.In: Proceedings of the 21th ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining. Sydney: Association for Computing Machinery; 2015:507-16 pp.
• 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.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).