Diagnostic and prognostic capabilities of a biomarker and EMR-based machine learning algorithm for sepsis

• Authors: Ishan Taneja, Prenosis Inc; Gregory L Damhorst, Prenosis Inc; Carlos Lopez-Espina, Prenosis Inc; Sihai D Zhao, University of Illinois at Urbana‐Champaign; Ruoqing Zhu, University of Illinois at Urbana‐Champaign; Shah Khan, Prenosis Inc; Karen White, Carle Foundation Hospital; James Kumar, Carle Foundation Hospital; Andrew Vincent, OSF Saint Francis Medical Center; Leon Yeh, OSF Saint Francis Medical Center; Shirin Majdizadeh, Carle Foundation Hospital; William Weir, Carle Foundation Hospital; Scott Isbell, Saint Louis University School of Medicine; James Skinner, Carle Foundation Hospital; Manubolo Devanand, Carle Foundation Hospital; Syed Azharuddin, Carle Foundation Hospital; Rajamurugan Meenakshisundaram, Carle Foundation Hospital; Riddhi Upadhyay, Carle Foundation Hospital; Anwaruddin Syed, OSF Saint Francis Medical Center; Thomas Bauman, OSF Saint Francis Medical Center; Joseph Devito, OSF Saint Francis Medical Center; Charles Heinzmann, OSF Saint Francis Medical Center; Gregory Podolej, OSF Saint Francis Medical Center; Lanxin Shen, Prenosis Inc; Sanjay Sharma Timilsina, Prenosis Inc; Lucas Quinlan, Prenosis Inc; Setareh Manafirasi, Prenosis Inc; Enrique Valera, University of Illinois at Urbana‐Champaign; Bobby Reddy, Prenosis Inc; Rashid Bashir, University of Illinois at Urbana‐Champaign
• Journal Title: CTS-CLINICAL AND TRANSLATIONAL SCIENCE
• Volume: Volume 14, Number 4
• Publisher: WILEY | 2021-05-02, Pages 1578-1589
• Type of Work: Article | Final Publisher PDF
• Publisher DOI: http://doi.org/10.1111/cts.13030
• Subjects: Statistics; Health Sciences, Pathology
• Keywords: Science & Technology; Life Sciences & Biomedicine; Medicine, Research & Experimental; Research & Experimental Medicine; INTERNATIONAL CONSENSUS DEFINITIONS; SEPTIC SHOCK; MORTALITY; PROCALCITONIN; ANTIBIOTICS; SURVIVAL; THERAPY

Abstract

Sepsis is a major cause of mortality among hospitalized patients worldwide. Shorter time to administration of broad-spectrum antibiotics is associated with improved outcomes, but early recognition of sepsis remains a major challenge. In a two-center cohort study with prospective sample collection from 1400 adult patients in emergency departments suspected of sepsis, we sought to determine the diagnostic and prognostic capabilities of a machine-learning algorithm based on clinical data and a set of uncommonly measured biomarkers. Specifically, we demonstrate that a machine-learning model developed using this dataset outputs a score with not only diagnostic capability but also prognostic power with respect to hospital length of stay (LOS), 30-day mortality, and 3-day inpatient re-admission both in our entire testing cohort and various subpopulations. The area under the receiver operating curve (AUROC) for diagnosis of sepsis was 0.83. Predicted risk scores for patients with septic shock were higher compared with patients with sepsis but without shock (p < 0.0001). Scores for patients with infection and organ dysfunction were higher compared with those without either condition (p < 0.0001). Stratification based on predicted scores of the patients into low, medium, and high-risk groups showed significant differences in LOS (p < 0.0001), 30-day mortality (p < 0.0001), and 30-day inpatient readmission (p < 0.0001). In conclusion, a machine-learning algorithm based on electronic medical record (EMR) data and three nonroutinely measured biomarkers demonstrated good diagnostic and prognostic capability at the time of initial blood culture.