Septic shock prediction for ICU patients via coupled HMM walking on sequential contrast patterns

BACKGROUND AND OBJECTIVE Critical care patient events like sepsis or septic shock in intensive care units (ICUs) are dangerous complications which can cause multiple organ failures and eventual death. Preventive prediction of such events will allow clinicians to stage effective interventions for averting these critical complications. METHODS It is widely understood that physiological conditions of patients on variables such as blood pressure and heart rate are suggestive to gradual changes over a certain period of time, prior to the occurrence of a septic shock. This work investigates the performance of a novel machine learning approach for the early prediction of septic shock. The approach combines highly informative sequential patterns extracted from multiple physiological variables and captures the interactions among these patterns via coupled hidden Markov models (CHMM). In particular, the patterns are extracted from three non-invasive waveform measurements: the mean arterial pressure levels, the heart rates and respiratory rates of septic shock patients from a large clinical ICU dataset called MIMIC-II. EVALUATION AND RESULTS For baseline estimations, SVM and HMM models on the continuous time series data for the given patients, using MAP (mean arterial pressure), HR (heart rate), and RR (respiratory rate) are employed. Single channel patterns based HMM (SCP-HMM) and multi-channel patterns based coupled HMM (MCP-HMM) are compared against baseline models using 5-fold cross validation accuracies over multiple rounds. Particularly, the results of MCP-HMM are statistically significant having a p-value of 0.0014, in comparison to baseline models. Our experiments demonstrate a strong competitive accuracy in the prediction of septic shock, especially when the interactions between the multiple variables are coupled by the learning model. CONCLUSIONS It can be concluded that the novelty of the approach, stems from the integration of sequence-based physiological pattern markers with the sequential CHMM model to learn dynamic physiological behavior, as well as from the coupling of such patterns to build powerful risk stratification models for septic shock patients.

[1]  S. Roberts,et al.  Estimation of coupled hidden Markov models with application to biosignal interaction modelling , 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

[2]  Yuval Shahar,et al.  Classification-driven temporal discretization of multivariate time series , 2014, Data Mining and Knowledge Discovery.

[3]  Roberta Capp,et al.  Predictors of Patients Who Present to the Emergency Department With Sepsis and Progress to Septic Shock Between 4 and 48 Hours of Emergency Department Arrival* , 2015, Critical care medicine.

[4]  E. Ivers,et al.  Early Goal-Directed Therapy in the Treatment of Severe Sepsis and Septic Shock , 2001 .

[5]  Yu. F. Kabatov,et al.  Tendencies in the development of medical engineering products (a review of the international specialized exhibition “Public Health-74”) , 1975 .

[6]  Franco Turini,et al.  Time-Annotated Sequences for Medical Data Mining , 2007 .

[7]  Riccardo Bellazzi,et al.  Analyzing complex patients' temporal histories: new frontiers in temporal data mining. , 2015, Methods in molecular biology.

[8]  Nigel H Lovell,et al.  Non-invasive classification of severe sepsis and systemic inflammatory response syndrome using a nonlinear support vector machine: a preliminary study , 2010, Physiological measurement.

[9]  Mohammad B. Shamsollahi,et al.  Early detection of apnea-bradycardia episodes in preterm infants based on coupled hidden Markov model , 2013, IEEE International Symposium on Signal Processing and Information Technology.

[10]  Milos Hauskrecht,et al.  Mining recent temporal patterns for event detection in multivariate time series data , 2012, KDD.

[11]  James Bailey,et al.  Mining Minimal Distinguishing Subsequence Patterns with Gap Constraints , 2005, ICDM.

[12]  Naren Ramakrishnan,et al.  Experiences with mining temporal event sequences from electronic medical records: initial successes and some challenges , 2011, KDD.

[13]  Dewang Shavdia,et al.  Septic shock : providing early warnings through multivariate logistic regression models , 2007 .

[14]  Joydeep Ghosh,et al.  HMMs and Coupled HMMs for multi-channel EEG classification , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[15]  Jian Pei,et al.  A brief survey on sequence classification , 2010, SKDD.

[16]  Milos Hauskrecht,et al.  A temporal pattern mining approach for classifying electronic health record data , 2013, ACM Trans. Intell. Syst. Technol..

[17]  Philip S. Yu,et al.  Coupled Behavior Analysis with Applications , 2012, IEEE Transactions on Knowledge and Data Engineering.

[18]  Jinyan Li,et al.  Efficient mining of emerging patterns: discovering trends and differences , 1999, KDD '99.

[19]  P. Pronovost,et al.  A targeted real-time early warning score (TREWScore) for septic shock , 2015, Science Translational Medicine.

[20]  M. J. Pearce,et al.  Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients , 2008, Clinical and Vaccine Immunology.

[21]  Tudor Toma,et al.  Learning predictive models that use pattern discovery - A bootstrap evaluative approach applied in organ functioning sequences , 2010, J. Biomed. Informatics.

[22]  Milos Hauskrecht,et al.  An efficient pattern mining approach for event detection in multivariate temporal data , 2015, Knowledge and Information Systems.

[23]  Dmitriy Fradkin,et al.  Under Consideration for Publication in Knowledge and Information Systems Mining Sequential Patterns for Classification , 2022 .

[24]  Carlo Combi,et al.  Data mining with Temporal Abstractions: learning rules from time series , 2007, Data Mining and Knowledge Discovery.

[25]  Mohammed J. Zaki,et al.  Learning sequential classifiers from long and noisy discrete-event sequences efficiently , 2014, Data Mining and Knowledge Discovery.

[26]  Ameen Abu-Hanna,et al.  Clinical prognostic methods: trends and developments. , 2014, Journal of biomedical informatics.

[27]  W. Knaus,et al.  Definitions for sepsis and organ failure and guidelines for the use of innovative therapies in sepsis. The ACCP/SCCM Consensus Conference Committee. American College of Chest Physicians/Society of Critical Care Medicine. , 1992, Chest.

[28]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[29]  Jürgen Paetz.  Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions , 2003, Artif. Intell. Medicine.

[30]  Osonde Osoba,et al.  Noisy hidden Markov models for speech recognition , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[31]  Chi Lap Yip,et al.  Mining emerging substrings , 2003, Eighth International Conference on Database Systems for Advanced Applications, 2003. (DASFAA 2003). Proceedings..

[32]  Caleb W. Hug,et al.  Detecting hazardous intensive care patient episodes using real-time mortality models , 2009 .

[33]  João Miguel da Costa Sousa,et al.  Predicting Outcomes of Septic Shock Patients Using Feature Selection Based on Soft Computing Techniques , 2010, IPMU.

[34]  Jure Leskovec,et al.  Finding progression stages in time-evolving event sequences , 2014, WWW.

[35]  R. Mark,et al.  An investigation of patterns in hemodynamic data indicative of impending hypotension in intensive care , 2010, Biomedical engineering online.

[36]  Johannes Gehrke,et al.  Sequential PAttern mining using a bitmap representation , 2002, KDD.

[37]  T. H. Kyaw,et al.  Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database* , 2011, Critical care medicine.

[38]  Tudor Toma,et al.  Discovery and inclusion of SOFA score episodes in mortality prediction , 2007, J. Biomed. Informatics.

[39]  Joshua A. Doherty,et al.  Early prediction of septic shock in hospitalized patients. , 2010, Journal of hospital medicine.

[40]  Hung T. Nguyen,et al.  Risk Prediction for Acute Hypotensive Patients by Using Gap Constrained Sequential Contrast Patterns , 2014, AMIA.

[41]  Philip S. Yu,et al.  Direct Discriminative Pattern Mining for Effective Classification , 2008, 2008 IEEE 24th International Conference on Data Engineering.

[42]  Jiawei Han,et al.  Discriminative Frequent Pattern Analysis for Effective Classification , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[43]  Fei Wang,et al.  A Framework for Mining Signatures from Event Sequences and Its Applications in Healthcare Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Elena Baralis,et al.  Analysis of Medical Pathways by Means of Frequent Closed Sequences , 2010, KES.

[45]  T. van der Poll,et al.  Severe sepsis and septic shock. , 2013, The New England journal of medicine.

[46]  Femida Gwadry-Sridhar,et al.  Comparison of Analytic Approaches for Determining Variables - A Case Study in Predicting the Likelihood of Sepsis , 2009, HEALTHINF.

[47]  Uzay Kaymak,et al.  Predicting septic shock outcomes in a database with missing data using fuzzy modeling: Influence of pre-processing techniques on real-world data-based classification , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[48]  João Miguel da Costa Sousa,et al.  Modified binary PSO for feature selection using SVM applied to mortality prediction of septic patients , 2013, Appl. Soft Comput..

[49]  Jin Chen,et al.  Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model , 2016 .

[50]  Giuseppe Baselli,et al.  Mortality prediction in septic shock patients: Towards new personalized models in critical care , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[51]  C. Torio,et al.  National Inpatient Hospital Costs: The Most Expensive Conditions by Payer, 2011 , 2013 .

[52]  Sebastian Peter,et al.  Temporal interval pattern languages to characterize time flow , 2014, WIREs Data Mining Knowl. Discov..

[53]  Evert de Jonge,et al.  Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit , 2010, J. Biomed. Informatics.

[54]  Fei Wang,et al.  Outcomes Prediction via Time Intervals Related Patterns , 2015, 2015 IEEE International Conference on Data Mining.

[55]  Joydeep Ghosh,et al.  Septic Shock Prediction for Patients with Missing Data , 2014, TMIS.

[56]  Cheng H. Lee,et al.  Imputation-Enhanced Prediction of Septic Shock in ICU Patients , 2012 .

[57]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[58]  Olga Stepánková,et al.  Sequential Data Mining: A Comparative Case Study in Development of Atherosclerosis Risk Factors , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[59]  Brendan J. Frey,et al.  Event-coupled hidden Markov models , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[60]  Alan S. Go,et al.  Population trends in the incidence and outcomes of acute myocardial infarction. , 2010, The New England journal of medicine.

[61]  Hung T. Nguyen,et al.  Hypotension Risk Prediction via Sequential Contrast Patterns of ICU Blood Pressure , 2016, IEEE Journal of Biomedical and Health Informatics.

[62]  Jian Pei,et al.  CMAR: accurate and efficient classification based on multiple class-association rules , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[63]  Yuanxi Li,et al.  Modelling and analysing the dynamics of disease progression from cross-sectional studies , 2013, J. Biomed. Informatics.

[64]  Piotr Indyk,et al.  Motif discovery in physiological datasets: A methodology for inferring predictive elements , 2010, TKDD.