Mortality prediction in intensive care units (ICUs) using a deep rule-based fuzzy classifier

Electronic health records (EHRs) contain critical information useful for clinical studies. Early assessment of patients' mortality in intensive care units is of great importance. In this paper, a Deep Rule-Based Fuzzy System (DRBFS) was proposed to develop an accurate in-hospital mortality prediction in the intensive care unit (ICU) patients employing a large number of input variables. Our main contribution is proposing a system, which is capable of dealing with big data with heterogeneous mixed categorical and numeric attributes. In DRBFS, the hidden layer in each unit is represented by interpretable fuzzy rules. Benefiting the strength of soft partitioning, a modified supervised fuzzy k-prototype clustering has been employed for fuzzy rule generation. According to the stacked approach, the same input space is kept in every base building unit of DRBFS. The training set in addition to random shifts, obtained from random projections of prediction results of the current base building unit is presented as the input of the next base building unit. A cohort of 10,972 adult admissions was selected from Medical Information Mart for Intensive Care (MIMIC-III) data set, where 9.31% of patients have died in the hospital. A heterogeneous feature set of first 48 h from ICU admissions, were extracted for in-hospital mortality rate. Required preprocessing and appropriate feature extraction were applied. To avoid biased assessments, performance indexes were calculated using holdout validation. We have evaluated our proposed method with several common classifiers including naïve Bayes (NB), decision trees (DT), Gradient Boosting (GB), Deep Belief Networks (DBN) and D-TSK-FC. The area under the receiver operating characteristics curve (AUROC) for NB, DT, GB, DBN, D-TSK-FC and our proposed method were 73.51%, 61.81%, 72.98%, 70.07%, 66.74% and 73.90% respectively. Our results have demonstrated that DRBFS outperforms various methods, while maintaining interpretable rule bases. Besides, benefiting from specific clustering methods, DRBFS can be well scaled up for large heterogeneous data sets.

[1]  Qingcai Chen,et al.  Fuzzy deep belief networks for semi-supervised sentiment classification , 2014, Neurocomputing.

[2]  D. E. Lawrence,et al.  APACHE—acute physiology and chronic health evaluation: a physiologically based classification system , 1981, Critical care medicine.

[3]  Chuen-Tsai Sun,et al.  Neuro-fuzzy And Soft Computing: A Computational Approach To Learning And Machine Intelligence [Books in Brief] , 1997, IEEE Transactions on Neural Networks.

[4]  Le Song,et al.  GRAM: Graph-based Attention Model for Healthcare Representation Learning , 2016, KDD.

[5]  Robert Fullér,et al.  Introduction to neuro-fuzzy systems , 1999, Advances in soft computing.

[6]  Lipika Dey,et al.  A k-mean clustering algorithm for mixed numeric and categorical data , 2007, Data Knowl. Eng..

[7]  Xiao Han,et al.  A fuzzy k-prototype clustering algorithm for mixed numeric and categorical data , 2012, Knowl. Based Syst..

[8]  J. L. Gall,et al.  A simplified acute physiology score for ICU patients , 1984, Critical care medicine.

[9]  Fariborz Haghighat,et al.  Multiobjective optimization of building design using TRNSYS simulations, genetic algorithm, and Artificial Neural Network , 2010 .

[10]  M. Soares,et al.  ICU severity of illness scores: APACHE, SAPS and MPM , 2014, Current opinion in critical care.

[11]  Youyong Kong,et al.  A Hierarchical Fused Fuzzy Deep Neural Network for Data Classification , 2017, IEEE Transactions on Fuzzy Systems.

[12]  Pan Wang,et al.  A Review of Soft Computing Based on Deep Learning , 2016, 2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII).

[13]  Ren Zhang,et al.  A model with Fuzzy Granulation and Deep Belief Networks for exchange rate forecasting , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[14]  J. Vincent,et al.  The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure , 1996, Intensive Care Medicine.

[15]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[16]  Peter Szolovits,et al.  Predicting intervention onset in the ICU with switching state space models , 2017, CRI.

[17]  Zhiqiang Ma,et al.  An Initialization Method for Clustering Mixed Numeric and Categorical Data Based on the Density and Distance , 2015, Int. J. Pattern Recognit. Artif. Intell..

[18]  Yu-Jun Zheng,et al.  Airline Passenger Profiling Based on Fuzzy Deep Machine Learning , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Chunguang Zhou,et al.  An improved k-prototypes clustering algorithm for mixed numeric and categorical data , 2013, Neurocomputing.

[20]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[21]  Franck Dernoncourt,et al.  De-identification of patient notes with recurrent neural networks , 2016, J. Am. Medical Informatics Assoc..

[22]  Uli K. Chettipally,et al.  Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach , 2016, JMIR medical informatics.

[23]  Yuichi Motai,et al.  Intra- and Inter-Fractional Variation Prediction of Lung Tumors Using Fuzzy Deep Learning , 2016, IEEE Journal of Translational Engineering in Health and Medicine.

[24]  Joshua Zhexue Huang,et al.  Extensions to the k-Means Algorithm for Clustering Large Data Sets with Categorical Values , 1998, Data Mining and Knowledge Discovery.

[25]  Hongyan Li,et al.  A review of modeling methods for predicting in-hospital mortality of patients in intensive care unit , 2017 .

[26]  L. Zadeh.  Probability measures of Fuzzy events , 1968 .

[27]  Shitong Wang,et al.  Deep TSK Fuzzy Classifier With Stacked Generalization and Triplely Concise Interpretability Guarantee for Large Data , 2017, IEEE Transactions on Fuzzy Systems.

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