ABSTRACT
In this paper we describe the application of machine learning techniques to the prediction of hospital Intensive Care Unit (ICU) patient mortality. A large dataset of over 58,000 ICU admissions from the MIMIC III database was used in the development, training and evaluation of a number of all-condition patient mortality predictive models. Evaluation results are presented, showing favorable performance comparing with existing studies, in the specific context that this work presents models making predictions for patients of all conditions as opposed to restricting to patients with a given condition or group of conditions, and the models are developed using only input attributes that are patient administrative data available at time of hospital admission. In this way, our models provide a unique utility for ICU mortality prediction in terms of their being applicable to all patients and at the earliest point in time of admission and utilizing a minimal and routinely collected set of patient administrative data.
- Manish Motwani, Damini Dey, Daniel S. Berman, Guido Germano, Stephan Achenbach, Mouaz H. Al-Mallah, Daniele Andreini, Matthew J. Budoff, Filippo Cademartiri, Tracy Q. Callister, Hyuk-Jae Chang, Kavitha Chinnaiyan, Benjamin J.W. Chow, Ricardo C. Cury, Augustin Delago, Millie Gomez, Heidi Gransar, Martin Hadamitzky, Joerg Hausleiter, Niree Hindoyan, Gudrun Feuchtner, Philipp A. Kaufmann, Yong-Jin Kim, Jonathon Leipsic, Fay Y. Lin, Erica Maffei, Hugo Marques, Gianluca Pontone, Gilbert Raff, Ronen Rubinshtein, Leslee J. Shaw, Julia Stehli, Todd C. Villines, Allison Dunning, James K. Min, Piotr J. Slomka; Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis, European Heart Journal, Volume 38, Issue 7, 14 February 2017, Pages 500--507.Google Scholar
- Pirracchio R, Petersen ML, Carone M, Rigon MR, Chevret S, van der Laan MJ. Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study. The Lancet Respiratory Medicine. 2015 Jan 1;3(1):42--52.Google Scholar
- Mayaud L, Lai PS, Clifford GD, Tarassenko L, Celi LAG, Annane D. Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension. Critical care medicine. 2013;41(4):954--962.Google Scholar
- Taylor, R.A., Pare, J.R., Venkatesh, A.K., Mowafi, H., Melnick, E.R., Fleischman, W., Hall, M.K., 2016. Prediction of in-hospital mortality in emergency department patients with sepsis: a local big data-driven, machine learning approach. Academic Emergency Medicine 23, 269--278.Google Scholar
- Allyn J, Allou N, Augustin P, Philip I, Martinet O, et al. (2017) A Comparison of a Machine Learning Model with EuroSCORE II in Predicting Mortality after Elective Cardiac Surgery: A Decision Curve Analysis. PLOS ONE 12(1): e0169772.Google Scholar
- Le Gall J, Lemeshow S, Saulnier F. A New Simplified Acute Physiology Score (SAPS II) Based on a European/North American Multicenter Study. JAMA. 1993;270(24):2957--2963.Google Scholar
- Hanley, JA, McNeil, BJ, The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982 143:1, 29--36.Google Scholar
- Eibe Frank, Mark A. Hall, and Ian H. Witten (2016). The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques", Morgan Kaufmann, Fourth Edition, 2016. Google ScholarDigital Library
- Steele R, Min K, Lo A. Personal health record architectures: technology infrastructure implications and dependencies. Journal of the Association for Information Science and Technology. 2012 Jun 1;63(6):1079--91. Google ScholarDigital Library
- Johnson, A. E. W. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3:160035Google Scholar
- Zimmerman, Jack E., Andrew A. Kramer, and William A. Knaus. "Changes in hospital mortality for United States intensive care unit admissions from 1988 to 2012." Critical care 17.2 (2013): R81.Google ScholarCross Ref
- Steele R, Lo A. Future personal health records as a foundation for computational health. In International Conference on Computational Science and Its Applications 2009 Jun 29 (pp. 719--733). Springer, Berlin, Heidelberg. Google ScholarDigital Library
- Steele R, Lo A, Secombe C, Wong YK. Elderly persons' perception and acceptance of using wireless sensor networks to assist healthcare. International journal of medical informatics. 2009 Dec 1;78(12):788--801.Google Scholar
Index Terms
- Machine Learning-based Prediction of ICU Patient Mortality at Time of Admission
Recommendations
Mortality Prediction of ICU patients using Machine Leaning: A survey
ICCDA '17: Proceedings of the International Conference on Compute and Data AnalysisRecently health care researchers are working a lot on outcome prediction on Intensive Care Unit (ICU) and trauma. Outcome prediction in intensive care is a difficult process. Accurate synthesis of quality data and application of prior experience to the ...
An explainable machine learning algorithm for risk factor analysis of in-hospital mortality in sepsis survivors with ICU readmission
Highlights- Comprehensive analysis of risk factors of sepsis survivors during ICU readmission within one year.
- Application of machine learning algorithm and SHAP value based on MIMIC-III database to visualize the quantitative relationship between ...
Abstract Background and objectivePatients who survive sepsis in the intensive care unit (ICU) (sepsis survivors) have an increased risk of long-term mortality and ICU readmission. We aim to identify the risk factors for in-hospital mortality in sepsis ...
Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care: A retrospective cohort analysis using machine learning and unstructured big data
Abstract BackgroundClinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies.
ObjectiveTo determine the predictive value of clinical ...
Graphical abstractDisplay Omitted
Highlights- Clinical text-based machine learning yielded high prognostic ability for predicting mortality of diabetes patients.
Comments