Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study

This paper presents a novel method for hierarchical analysis of machine learning algorithms to improve predictions of at risk patients, thus further enabling prompt therapy. Specifically, we develop a multi-layer machine learning approach to analyze continuous, high-frequency data. We illustrate the capabilities of this approach for early identification of patients at risk of sepsis, a potentially life-threatening complication of an infection, using high-frequency (minute-by-minute) physiological data collected from bedside monitors. In our analysis of a cohort of 586 patients, the model obtained from analyzing the output of a previously developed sepsis prediction model resulted in improved outcomes. Specifically, the original model failed to predict 11.76 ± 4.26% of sepsis patients earlier than Systemic Inflammatory Response Syndrome (SIRS) criteria, commonly used to identify patients at risk for rapid physiological deterioration resulting from sepsis. In contrast, the multi-layer model only failed to predict 3.21 ± 3.11% of sepsis patients earlier than SIRS. In addition, sepsis patients were predicted on average 204.87 ± 7.90 minutes earlier than SIRS criteria using the multi-layer model, which can potentially help reduce mortality and morbidity if implemented in the ICU.

[1]  Anahita Khojandi,et al.  Prediction of Sepsis and In-Hospital Mortality Using Electronic Health Records , 2018, Methods of Information in Medicine.

[2]  Hien Nguyen,et al.  From vital signs to clinical outcomes for patients with sepsis: a machine learning basis for a clinical decision support system , 2014, J. Am. Medical Informatics Assoc..

[3]  Pertti Koskinen,et al.  Pentraxin 3 (PTX3) Is Associated with Severe Sepsis and Fatal Disease in Emergency Room Patients with Suspected Infection: A Prospective Cohort Study , 2013, PloS one.

[4]  Ricard Ferrer,et al.  SIRS, qSOFA, and organ failure for assessing sepsis at the emergency department. , 2017, Journal of thoracic disease.

[5]  R. Hotchkiss,et al.  Apoptosis and caspases regulate death and inflammation in sepsis , 2006, Nature Reviews Immunology.

[6]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[7]  Anahita Khojandi,et al.  Physiomarkers in Real-Time Physiological Data Streams Predict Adult Sepsis Onset Earlier Than Clinical Practice , 2018, bioRxiv.

[8]  Matthew D. Stanley,et al.  Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics. , 2017, Journal of electrocardiology.

[9]  Yefeng Wang,et al.  Cascading Classifiers for Named Entity Recognition in Clinical Notes , 2009, BiomedicalIE@RANLP.

[10]  Ji-Hyun Kim,et al.  Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap , 2009, Comput. Stat. Data Anal..

[11]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[12]  M. Cvach.  Monitor alarm fatigue: an integrative review. , 2012, Biomedical instrumentation & technology.

[13]  Kok Kiong Tan,et al.  Automatic identification of blood vessel cross-section for central venous catheter placement using a cascading classifier , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[14]  R. Bellomo,et al.  Prognostic Accuracy of the SOFA Score, SIRS Criteria, and qSOFA Score for In-Hospital Mortality Among Adults With Suspected Infection Admitted to the Intensive Care Unit , 2017, JAMA.

[15]  Shamim Nemati,et al.  How much data should we collect? A case study in sepsis detection using deep learning , 2017, 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT).

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

[17]  B. Drew,et al.  Insights into the Problem of Alarm Fatigue with Physiologic Monitor Devices: A Comprehensive Observational Study of Consecutive Intensive Care Unit Patients , 2014, PloS one.

[18]  Gustavo Carneiro,et al.  Automated Mass Detection in Mammograms Using Cascaded Deep Learning and Random Forests , 2015, 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[19]  Adil Rafiq Rather,et al.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) , 2015 .

[20]  Viju Raghupathi,et al.  Big data analytics in healthcare: promise and potential , 2014, Health Information Science and Systems.

[21]  M. Funk,et al.  Alarm fatigue: a patient safety concern. , 2013, AACN advanced critical care.

[22]  Anahita Khojandi,et al.  A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier , 2019, Int. J. Medical Informatics.

[23]  S. Haydar,et al.  Comparison of QSOFA score and SIRS criteria as screening mechanisms for emergency department sepsis , 2017, The American journal of emergency medicine.

[24]  A. Salcedo-Bernal,et al.  Clinical Data Analysis: An Opportunity to Compare Machine Learning Methods , 2016 .

[25]  H. Ahn,et al.  Decision threshold adjustment in class prediction , 2006, SAR and QSAR in environmental research.

[26]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[27]  R. Gutierrez-Rivas,et al.  Real-time early detection of allergic reactions based on heart rate variability , 2016 .

[28]  Walter F. Stewart,et al.  Doctor AI: Predicting Clinical Events via Recurrent Neural Networks , 2015, MLHC.

[29]  T. Rea,et al.  Assessment of Clinical Criteria for Sepsis: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). , 2016, JAMA.

[30]  Milos Miljanovic,et al.  Comparative analysis of Recurrent and Finite Impulse Response Neural Networks in Time Series Prediction Author , 2012 .

[31]  Yixin Chen,et al.  An integrated data mining approach to real-time clinical monitoring and deterioration warning , 2012, KDD.

[32]  Julie Mackenhauer,et al.  Site of infection and mortality in patients with severe sepsis or septic shock. A cohort study of patients admitted to a Danish general intensive care unit , 2016, Infectious diseases.

[33]  Shamim Nemati,et al.  An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU , 2017, Critical care medicine.

[34]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[35]  Uli K. Chettipally,et al.  Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU , 2018, BMJ Open.

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

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  Faria Hossain,et al.  Real-time PCR in detection and quantitation of Leishmania donovani for the diagnosis of Visceral Leishmaniasis patients and the monitoring of their response to treatment , 2017, PloS one.

[39]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

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