Length of stay prediction for ICU patients using individualized single classification algorithm

BACKGROUND AND OBJECTIVE In intensive care units (ICUs), length of stay (LOS) prediction is critical to help doctors and nurses select appropriate treatment options and predict patients' condition. Considering that most hospitals use universal models to predict patients' condition, which cannot meet the individual needs of special ICU patients. Our goal is to create a personalized model for patients to determine the number of hospital stays. METHODS In this study, a new combination of just-in-time learning (JITL) and one-class extreme learning machine (one-class ELM) is proposed to predict the number of days a patient stays in hospital. This combination is shortened as one-class JITL-ELM, where JITL is used to search for personalized cases for a new patient and one-class ELM is used to determine whether the patient can be discharged within 10 days. RESULTS The experimental results show that the one-class JITL-ELM model has an area under the curve (AUC) index of 0.8510, lift value of 2.1390, precision of 1, and G-mean is 0.7842. Its accuracy, specificity, and sensitivity were found as 0.82, 1, and 0.6150, respectively. Moreover, a novel simple mortality risk level estimation system that can determine the mortality rate of a patient by combining LOS and age is proposed. It has an accuracy rate of 66% and the miss rate of only 6.25%. CONCLUSIONS Overall, the one-class JITL-ELM can accurately predict hospitalization days and mortality using early physiological parameters. Moreover, a simple mortality risk level estimation system based on a combination of LOS and age is proposed; the system is simple, highly interpretable, and has strong application value.

[1]  Patrick L. Purdon,et al.  Electroencephalogram Based Detection of Deep Sedation in ICU Patients Using Atomic Decomposition , 2018, IEEE Transactions on Biomedical Engineering.

[2]  XuanLong Nguyen,et al.  Identification of the Dynamic Operating Envelope of HCCI Engines Using Class Imbalance Learning , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Peter Szolovits,et al.  MIMIC-III, a freely accessible critical care database , 2016, Scientific Data.

[4]  Mohammad Bagher Shamsollahi,et al.  Life-Threatening Arrhythmia Verification in ICU Patients Using the Joint Cardiovascular Dynamical Model and a Bayesian Filter , 2011, IEEE Transactions on Biomedical Engineering.

[5]  S. Lemeshow,et al.  A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study. , 1993, JAMA.

[6]  S. Lemeshow,et al.  Mortality Probability Models (MPM II) based on an international cohort of intensive care unit patients. , 1993, JAMA.

[7]  Rachid Benlamri,et al.  Application of Data Mining Techniques to Predict the Length of Stay of Hospitalized Patients with Diabetes , 2018, 2018 4th International Conference on Big Data Innovations and Applications (Innovate-Data).

[8]  Benjamin H. Brinkmann,et al.  SVM-Based System for Prediction of Epileptic Seizures From iEEG Signal , 2017, IEEE Transactions on Biomedical Engineering.

[9]  Charles E. Taylor,et al.  Development of an adaptive pulmonary simulator for in vitro analysis of patient populations and patient-specific data , 2018, Comput. Methods Programs Biomed..

[10]  Ahmad Taher Azar,et al.  Performance analysis of support vector machines classifiers in breast cancer mammography recognition , 2013, Neural Computing and Applications.

[11]  Youqing Wang,et al.  Mortality prediction for ICU patients using just-in-time learning and extreme learning machine , 2016, 2016 12th World Congress on Intelligent Control and Automation (WCICA).

[12]  Andrew A Kramer.  Are ICU Length of Stay Predictions Worthwhile? , 2017, Critical care medicine.

[13]  Youqing Wang,et al.  Multimode Continuous Processes Monitoring Based on Hidden Semi-Markov Model and Principal Component Analysis , 2017 .

[14]  Wellington Pinheiro dos Santos,et al.  Detection and classification of mammary lesions using artificial neural networks and morphological wavelets , 2018 .

[15]  Xu Jiang,et al.  Intelligent Closed-Loop Insulin Delivery Systems for ICU Patients , 2014, IEEE Journal of Biomedical and Health Informatics.

[16]  Alfredo Vellido,et al.  Sepsis mortality prediction with the Quotient Basis Kernel , 2014, Artif. Intell. Medicine.

[17]  A. Okasha,et al.  The FOUR Score Predicts Mortality, Endotracheal Intubation and ICU Length of Stay After Traumatic Brain Injury , 2014, Neurocritical Care.

[18]  C. Lilly,et al.  ICU Telemedicine Comanagement Methods and Length of Stay. , 2016, Chest.

[19]  Jeffrey G. Chipman,et al.  Stuck in the Unit: Three-Year Outcomes Following Prolonged Stay in the Surgical Intensive Care Unit , 2014 .

[20]  Youqing Wang,et al.  Prediction of blood glucose concentration for type 1 diabetes based on echo state networks embedded with incremental learning , 2020, Neurocomputing.

[21]  Eiichi Watanabe,et al.  Mortality Prediction in Severe Congestive Heart Failure Patients With Multifractal Point-Process Modeling of Heartbeat Dynamics , 2018, IEEE Transactions on Biomedical Engineering.

[22]  Youqing Wang,et al.  Fault estimation based on sliding mode observer for Takagi-Sugeno fuzzy systems with digital communication constraints , 2020, J. Frankl. Inst..

[23]  Anders Perner,et al.  Performance of SAPS II according to ICU length of stay: Protocol for an observational study , 2018, Acta anaesthesiologica Scandinavica.

[24]  W. Knaus,et al.  APACHE II: a severity of disease classification system. , 1985 .

[25]  Badong Chen,et al.  Extreme Learning Machine With Affine Transformation Inputs in an Activation Function , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Peng Chen,et al.  An improved SVM classifier based on double chains quantum genetic algorithm and its application in analogue circuit diagnosis , 2016, Neurocomputing.

[27]  Diego Klabjan,et al.  Predicting ICU readmission using grouped physiological and medication trends , 2019, Artif. Intell. Medicine.

[28]  Shahla Siddiqui,et al.  A comparison of pre ICU admission SIRS, EWS and q SOFA scores for predicting mortality and length of stay in ICU , 2017, Journal of critical care.

[29]  Donghua Zhou,et al.  Mortality prediction for ICU patients combining just-in-time learning and extreme learning machine , 2017, Neurocomputing.

[30]  Aggelos K. Katsaggelos,et al.  ECG-Based Classification of Resuscitation Cardiac Rhythms for Retrospective Data Analysis , 2017, IEEE Transactions on Biomedical Engineering.

[31]  Joachim Dudeck,et al.  A data model for managing drug therapy within a patient data management system for intensive care units , 2003, Comput. Methods Programs Biomed..

[32]  Xin Ma,et al.  Health status monitoring for ICU patients based on locally weighted principal component analysis , 2018, Comput. Methods Programs Biomed..

[33]  Qiao Li,et al.  Ventricular Fibrillation and Tachycardia Classification Using a Machine Learning Approach , 2014, IEEE Transactions on Biomedical Engineering.

[34]  I. Rubinfeld,et al.  ICU mortality prediction using time series motifs , 2012, 2012 Computing in Cardiology.

[35]  Khalid Rashid,et al.  Availability and use of in-patient electronic health records in low resource setting , 2018, Comput. Methods Programs Biomed..

[36]  Anastasia Bezerianos,et al.  Comparing Similarity Perception in Time Series Visualizations , 2019, IEEE Transactions on Visualization and Computer Graphics.

[37]  Youqing Wang,et al.  Fault Diagnosis Observer and Fault-Tolerant Control Design for Unmanned Surface Vehicles in Network Environments , 2019, IEEE Access.

[38]  Federico Rotolo,et al.  surrosurv: An R package for the evaluation of failure time surrogate endpoints in individual patient data meta-analyses of randomized clinical trials , 2018, Comput. Methods Programs Biomed..

[39]  Zhi-Hua Zhou,et al.  Isolation Forest , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[40]  J. Geoffrey Chase,et al.  Generalisability of a Virtual Trials Method for Glycaemic Control in Intensive Care , 2018, IEEE Transactions on Biomedical Engineering.