Natural Language Processing of Clinical Notes for Improved Early Prediction of Septic Shock in the ICU

Sepsis and septic shock are major concerns in public health as the leading contributors to hospital mortality and cost of treatment in the United States. Early treatment is instrumental for improving patient outcome; to this end, algorithmic methods for early prediction of septic shock have been developed using electronic health record data, with the goal of decreasing treatment delay. We extend a previously-developed method, using a gradient boosting algorithm (XG-Boost) to compute a time-evolving risk of impending transition into septic shock, by combining physiological data from the electronic health record with features obtained from natural language processing of clinical note data. We compare two different methods for generating natural language processing features, with the best method obtaining improved performance of 0.92 AUC, 84% sensitivity, 82% specificity, 49% positive predictive value, and a median early warning time of 7.0 hours. This degree of early warning is sufficient to enable intervention many hours in advance of septic shock onset, with the improved prediction performance of this method resulting in fewer false alarms and thus more actionable predictions.

[1]  Antonio Artigas,et al.  Management of severe sepsis: advances, challenges, and current status , 2015, Drug design, development and therapy.

[2]  K. Wood,et al.  Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock* , 2006, Critical care medicine.

[3]  Xin Sun,et al.  Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence , 2019, Nature Medicine.

[4]  M. Levy,et al.  Surviving Sepsis Campaign: International guidelines for management of severe sepsis and septic shock: 2008 , 2007, Intensive Care Medicine.

[5]  M. Levy,et al.  Empiric Antibiotic Treatment Reduces Mortality in Severe Sepsis and Septic Shock From the First Hour: Results From a Guideline-Based Performance Improvement Program* , 2014, Critical care medicine.

[6]  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.

[7]  J. Chiche,et al.  Timing and causes of death in septic shock , 2015, Annals of Intensive Care.

[8]  Ben J. Marafino,et al.  Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data , 2018, JAMA network open.

[9]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[10]  Kavishwar B. Wagholikar,et al.  Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach , 2017, BMC Medical Informatics and Decision Making.

[11]  Mohammed Saeed,et al.  Risk Stratification of ICU Patients Using Topic Models Inferred from Unstructured Progress Notes , 2012, AMIA.

[12]  Alan E. Jones,et al.  Surviving Sepsis Campaign: International Guidelines for Management of Sepsis and Septic Shock: 2016 , 2017, Intensive Care Medicine.

[13]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[14]  M. Levy,et al.  2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference , 2003, Intensive care medicine.

[15]  S. Orfanos,et al.  Validation of the new Sepsis-3 definitions: proposal for improvement in early risk identification. , 2017, Clinical Microbiology and Infection.

[16]  Richard Beale,et al.  The Surviving Sepsis Campaign: results of an international guideline-based performance improvement program targeting severe sepsis , 2010, Intensive Care Medicine.

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

[18]  Joseph L Greenstein,et al.  Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU , 2019, Scientific Reports.

[19]  R. Bellomo,et al.  Mortality related to severe sepsis and septic shock among critically ill patients in Australia and New Zealand, 2000-2012. , 2014, JAMA.

[20]  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.

[21]  G. Escobar,et al.  Hospital deaths in patients with sepsis from 2 independent cohorts. , 2014, JAMA.

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

[23]  Quoc V. Le,et al.  Document Embedding with Paragraph Vectors , 2015, ArXiv.

[24]  C. Sprung,et al.  Surviving Sepsis Campaign: International Guidelines for Management of Severe Sepsis and Septic Shock 2012 , 2013, Critical care medicine.

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

[26]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[27]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[28]  Kevin J. Tracey,et al.  Sepsis definitions: time for change , 2013, The Lancet.