[01] Carol Anne Hargreaves, Department of Statistics and Applied Probability, National University of Singapore, Singapore. [02] Tan Hui Ling Juliet, Department of Statistics and Applied Probability, National University of Singapore, Singapore. [03] Dinesh Kumar Srinivasan, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.

In this paper, we focus on the classification of high mortality risk patients for Intensive Care Units (ICUs). Classification algorithms for identifying ICU mortality are necessary for measuring and improving ICU performance. Mortality risk severity scores are an essential part of hospital management and clinical decision-making. Proper application of classification models can help in decision making to lower hospital costs. In fact, classification high mortality risk models have become a necessary tool to explain differences in mortality risk. Purpose of Study: The purpose of this study is to develop and evaluate a new algorithm which more accurately predicts patient mortality in ICU, using patient information of vital signs and laboratory results only in the first 24 hours of ICU admission. We convert continuous variables into categorical variables and identify optimal threshold cut points for stabilizing the coefficients of the classification mortality risk model. In this paper, an optimal set of 3 threshold values were derived, that partitioned the data into 4 groups, resulting in the patient mortality risk scores being more distinguishable across the 4 partitioned groups. The most important variables for the ICU Mortality Risk was PO2 (120¬ 125), followed by Cardiac Arrest (Yes), Bilirubin (0.75 – 1), Vasopressors (Yes), SPO2 (< 66), Bilirubin (>7.75), Foley (<6), Severe COPD (Yes), WBC (> 19.5) and BUN (> 49). Our proposed optimal threshold cut point model performed substantially better (AUC=0.944) in identifying ICU patients with high mortality risk compared to the current scoring systems commonly used in hospitals, such as the SAPS 11 (AUC =0.771), APACHE 11 (AUC=0.736) and SOFA (AUC=0.699). This accuracy is at least 30% (1.35 times) better than current mortality risk scoring systems. SAPS 11, APACHE 11 and SOFA are static algorithms whereas our new optimal threshold algorithm is a data-driven algorithm which predicts mortality in ICU patients in real-time and may be useful for the timely identification of deteriorating patients. Our new binary classification algorithm will allow clinicians to accurately identify high-mortality risk patients early within 24 hours so that they can be given prompt treatment to reduce their risks of deteriorating or dying.

Intensive Care Units (ICU), Critical Care, Mortality Risk, Classification Algorithm, Optimal Threshold Cut Points, SAPS11, APACHE11, SOFA

[01] Jiankang Liu, Xian Xiang Chen, Lipeng Fang, et. al. Mortality prediction based on imbalanced high-dimensional ICU big data. Science Direct, Computers in Industry, (2018), 98, pp: 218-225. [02] Knaus WA, et al. The APACHE III prognostic system: risk prediction of hospital mortality for critically ill hospitalized adults. Chest 1991; 100(6): 1619-1636. [03] Zimmeman JE, Kramer AA, McNair DS, Malila FM. Acute Physiology and Chronic Health Evaluations (APACHE) IV: hospital mortality assessment for today’s critically ill patients. Crit Care Med 2006; 34(5): 1297-1310. [04] Le Gall JR, Lemeshow S, Saulneir F. A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study. JAMA 1993; 270(24): 2957-63. [05] Moreno RP, Metnitz PGH, Almeida E, et al. SAPS 3 – from evaluation of the patient to evaluation of the intensive care unit. Intensive Care Med 2005; 31: 1336-1355. [06] Vincent JL, et al. The SOFA (sepsis-related organ failure assessment) score to describe organ dysfunction/failure. Intensive Care Med 1996; 22:707-710. [07] Minne L, Abu-Hanna A, de Jonge E. Evaluation of SOFA-based models for predicting mortality in the ICU: A systematic review. Crit Care 2008; 12: R161. [08] Mayr VD, Dunser MW, Greil V, et. al. Causes of death and determinants of outcome in critically ill patients. BioMed Central Ltd, Critical Care (2006), 10(6): R154. [09] Orban JC, Walrave Y, Mongardon N, et. al. Causes and Characteristics of Death in Intensive Care Units: A Prospective Multicenter Study. Pubmed (2017), 126(5), pp 882-889. [10] Nasser Abdullah Alghamdi, Munni Begum. Identification of the Risk Factors Associated with ICU Mortality. Biom Biostat Int J 2017, 6(1): pp. 278-287. DOI: 10.15406/bbij.2017.06. 00157. [11] Martina, M. L. V. Todini, E. A. Libralaon. A Bayesian decision approach to rainfall threshold-based flood warning. Hydrology and Earth System Sciences, 2006, 10:413-426. [12] Meng Hsuen Hsieh, Meng Ju Hsieh, Chin-Ming Chen, et. al. Scientific Reports 8, Comparison of machine learning models for the prediction of mortality of patients with unplanned extubation in intensive care units, 2018. Article Number:17116. [13] Meng, C., Sanjay, P., Che, Z., & Liu, Y. Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets. Journal of Biomedical Informatics (2017). [14] Jacob, C., Qingqing, M., Jana, L. H., et. al. Ritankar, D. Using electronic health record collected clinical variables to predict medical intensive care unit mortality. Annals of Medicine and Surgery, 2016, Volume 11, Pages 52-57. [15] Sheth, M. Predicting Mortality for Patients in Critical Care: A Univariate Flagging Approach. MASSACHUSETTS INSTITUTE OF TECHNOLOGY (2015). [16] Johnson, A. E., Pollard, T. J., Shen, L., et. al. MIMIC-III, a freely accessible critical care database, Sci. Data. 3 (2016). [17] http://julietthl.shinyapps.io/rshiny