Assessing clinical heterogeneity in sepsis through treatment patterns and machine learning

OBJECTIVE To use unsupervised topic modeling to evaluate heterogeneity in sepsis treatment patterns contained within granular data of electronic health records. MATERIALS AND METHODS A multicenter, retrospective cohort study of 29 253 hospitalized adult sepsis patients between 2010 and 2013 in Northern California. We applied an unsupervised machine learning method, Latent Dirichlet Allocation, to the orders, medications, and procedures recorded in the electronic health record within the first 24 hours of each patient's hospitalization to uncover empiric treatment topics across the cohort and to develop computable clinical signatures for each patient based on proportions of these topics. We evaluated how these topics correlated with common sepsis treatment and outcome metrics including inpatient mortality, time to first antibiotic, and fluids given within 24 hours. RESULTS Mean age was 70 ± 17 years with hospital mortality of 9.6%. We empirically identified 42 clinically recognizable treatment topics (eg, pneumonia, cellulitis, wound care, shock). Only 43.1% of hospitalizations had a single dominant topic, and a small minority (7.3%) had a single topic comprising at least 80% of their overall clinical signature. Across the entire sepsis cohort, clinical signatures were highly variable. DISCUSSION Heterogeneity in sepsis is a major barrier to improving targeted treatments, yet existing approaches to characterizing clinical heterogeneity are narrowly defined. A machine learning approach captured substantial patient- and population-level heterogeneity in treatment during early sepsis hospitalization. CONCLUSION Using topic modeling based on treatment patterns may enable more precise clinical characterization in sepsis and better understanding of variability in sepsis presentation and outcomes.

[1]  D. Mannino,et al.  The epidemiology of sepsis in the United States from 1979 through 2000. , 2003, The New England journal of medicine.

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

[3]  G. Clermont,et al.  Epidemiology of severe sepsis in the United States: Analysis of incidence, outcome, and associated costs of care , 2001, Critical care medicine.

[4]  S. Yende,et al.  Proportion and Cost of Unplanned 30-Day Readmissions After Sepsis Compared With Other Medical Conditions , 2017, JAMA.

[5]  G. Escobar,et al.  Fluid volume, lactate values, and mortality in sepsis patients with intermediate lactate values. , 2013, Annals of the American Thoracic Society.

[6]  Theodore J Iwashyna,et al.  Identifying Patients With Severe Sepsis Using Administrative Claims: Patient-Level Validation of the Angus Implementation of the International Consensus Conference Definition of Severe Sepsis , 2014, Medical care.

[7]  Russ B. Altman,et al.  Predicting inpatient clinical order patterns with probabilistic topic models vs conventional order sets , 2016, J. Am. Medical Informatics Assoc..

[8]  Michael Bailey,et al.  Systemic inflammatory response syndrome criteria in defining severe sepsis. , 2015, The New England journal of medicine.

[9]  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.

[10]  R. Bellomo,et al.  The Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). , 2016, JAMA.

[11]  Renda Soylemez Wiener,et al.  Two Decades of Mortality Trends Among Patients With Severe Sepsis: A Comparative Meta-Analysis* , 2014, Critical care medicine.

[12]  D. Angus The lingering consequences of sepsis: a hidden public health disaster? , 2010, JAMA.

[13]  S. Opal,et al.  Sepsis: a roadmap for future research. , 2015, The Lancet. Infectious diseases.

[14]  Gabriel J Escobar,et al.  Incorporating an Early Detection System Into Routine Clinical Practice in Two Community Hospitals. , 2016, Journal of hospital medicine.

[15]  G. Escobar,et al.  The Impact of Acute Organ Dysfunction on Long-Term Survival in Sepsis* , 2018, Critical care medicine.

[16]  Jeremy C. Weiss,et al.  Derivation, Validation, and Potential Treatment Implications of Novel Clinical Phenotypes for Sepsis. , 2019, JAMA.

[17]  Shaowen Yao,et al.  An overview of topic modeling and its current applications in bioinformatics , 2016, SpringerPlus.

[18]  David W Bates,et al.  Integrating Predictive Analytics Into High-Value Care: The Dawn of Precision Delivery. , 2016, JAMA.

[19]  Roland Eils,et al.  circlize implements and enhances circular visualization in R , 2014, Bioinform..

[20]  C. Lindsell,et al.  Developing a clinically feasible personalized medicine approach to pediatric septic shock. , 2015, American journal of respiratory and critical care medicine.

[21]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[22]  Theodore J Iwashyna,et al.  Late mortality after sepsis: propensity matched cohort study , 2016, British Medical Journal.

[23]  Bruce H Fireman,et al.  Risk adjusting community-acquired pneumonia hospital outcomes using automated databases. , 2008, The American journal of managed care.

[24]  Huilong Duan,et al.  A probabilistic topic model for clinical risk stratification from electronic health records , 2015, J. Biomed. Informatics.

[25]  Stanley Lemeshow,et al.  Association Between the New York Sepsis Care Mandate and In-Hospital Mortality for Pediatric Sepsis , 2018, JAMA.

[26]  Susan Gruber,et al.  Incidence and Trends of Sepsis in US Hospitals Using Clinical vs Claims Data, 2009-2014 , 2017, JAMA.

[27]  J. Marshall Why have clinical trials in sepsis failed? , 2014, Trends in molecular medicine.

[28]  G. Schwarz Estimating the Dimension of a Model , 1978 .

[29]  Anna Rautanen,et al.  Genomic landscape of the individual host response and outcomes in sepsis: a prospective cohort study , 2016, The Lancet. Respiratory medicine.

[30]  Hsin-Min Lu,et al.  Modeling healthcare data using multiple-channel latent Dirichlet allocation , 2016, J. Biomed. Informatics.

[31]  D. Angus,et al.  Assessment of Global Incidence and Mortality of Hospital-treated Sepsis. Current Estimates and Limitations. , 2016, American journal of respiratory and critical care medicine.

[32]  Shruti Gohil,et al.  Regulatory mandates for sepsis care--reasons for caution. , 2014, The New England journal of medicine.

[33]  Gabriel J. Escobar,et al.  Risk-Adjusting Hospital Inpatient Mortality Using Automated Inpatient, Outpatient, and Laboratory Databases , 2008, Medical care.

[34]  Mitchell M. Levy,et al.  A Framework for the Development and Interpretation of Different Sepsis Definitions and Clinical Criteria , 2016, Critical care medicine.

[35]  S. Lemeshow,et al.  Time to Treatment and Mortality during Mandated Emergency Care for Sepsis , 2017, The New England journal of medicine.

[36]  Edward Abraham,et al.  New Definitions for Sepsis and Septic Shock: Continuing Evolution but With Much Still to Be Done. , 2016, JAMA.

[37]  Christopher W Seymour,et al.  Developing a New Definition and Assessing New Clinical Criteria for Septic Shock: For the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3). , 2016, JAMA.

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

[39]  Anand Kumar,et al.  Association between source of infection and hospital mortality in patients who have septic shock. , 2014, American journal of respiratory and critical care medicine.

[40]  Niranjan Kissoon,et al.  Recognizing Sepsis as a Global Health Priority - A WHO Resolution. , 2017, The New England journal of medicine.

[41]  J. Vincent,et al.  Serial evaluation of the SOFA score to predict outcome in critically ill patients. , 2001, JAMA.

[42]  Derek C Angus,et al.  Toward Smarter Lumping and Smarter Splitting: Rethinking Strategies for Sepsis and Acute Respiratory Distress Syndrome Clinical Trial Design. , 2016, American journal of respiratory and critical care medicine.

[43]  R. Hotchkiss,et al.  Getting sepsis therapy right , 2015, Science.

[44]  G. Escobar,et al.  The Timing of Early Antibiotics and Hospital Mortality in Sepsis , 2017, American journal of respiratory and critical care medicine.

[45]  Gabriel J. Escobar,et al.  Nonelective Rehospitalizations and Postdischarge Mortality , 2015, Medical care.

[46]  Patricia Kipnis,et al.  Risk-adjusting Hospital Mortality Using a Comprehensive Electronic Record in an Integrated Health Care Delivery System , 2013, Medical care.

[47]  Gerard Salton,et al.  Term-Weighting Approaches in Automatic Text Retrieval , 1988, Inf. Process. Manag..

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

[49]  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.

[50]  Derek C. Angus,et al.  Enhancing Recovery From Sepsis: A Review , 2018, JAMA.

[51]  Purvesh Khatri,et al.  A comprehensive time-course–based multicohort analysis of sepsis and sterile inflammation reveals a robust diagnostic gene set , 2015, Science Translational Medicine.

[52]  John C. Marshall,et al.  Predisposition, insult/infection, response, and organ dysfunction: A new model for staging severe sepsis , 2009, Critical care medicine.

[53]  R. Hotchkiss,et al.  Immunosuppression in patients who die of sepsis and multiple organ failure. , 2011, JAMA.

[54]  David T. Huang,et al.  A systematic review and meta-analysis of early goal-directed therapy for septic shock: the ARISE, ProCESS and ProMISe Investigators , 2015, Intensive Care Medicine.