About this item:

47 Views | 14 Downloads

Author Notes:

Andre Holder, MD MSc, Assistant Professor, Division of Pulmonary, Allergy, Critical Care and Sleep Medicine, Emory University School of Medicine, Grady Memorial Hospital, 49 Jesse Hill Jr. Drive, Atlanta, GA 30303, Office: (404) 251-8821, Fax: (404) 251-8999. Email: andre.holder@emory.edu

Dr. Holder conceptualized and contributed to the study design and data interpretation, and drafted the manuscript. Dr. Nemati contributed to the study design, acquired the data and led the analysis, and contributed to data interpretation and draft revision with critical intellectual content. Dr. Wardi contributed to the data interpretation and to draft revision with intellectual content. Dr. Shashikumar contributed to the study design, analysis, and draft revision. Dr. Buchman contributed to data interpretation and draft revision with intellectual content. All authors gave final approval of the manuscript submitted for publication and agreed to be accountable for all aspects of the work.

Dr. Holder is supported by the National Institute of General Medical Sciences of the National Institutes of Health (K23GM37182). Dr. Nemati is funded by the National Institutes of Health (#K01ES025445) and the Gordon and Betty Moore Foundation (#GBMF9052). Dr. Wardi is supported by the National Foundation of Emergency Medicine and funding from the Gordon and Betty Moore Foundation (#GBMF9052). He has received speakers’ fees from Thermo-Fisher and consulting fees from General Electric. "Dr. Buchman’s institution received funding from the Henry M. Jackson Foundation for his role as site director in Surgical Critical Care Institute, www.sc2i.org, funded through the Department of Defense’s Health Program – Joint Program Committee 6/Combat Casualty Care (USUHS HT9404-13-1-0032 and HU0001- 15-2-0001) and from Society of Critical Care Medicine for his role as Editor-in-Chief of Critical Care Medicine. Dr. Buchman is a 0.5 FTE under an IPA between Emory University and HHS/ASPR/BARDA. Funders played no role in study design, collection of data, analysis, reporting or interpretation of results.

Drs. Holder and Nemati’s institutions received funding from the National Institutes of Health (NIH). Dr. Holder received funding from the Gordon and Betty Moore Foundation, Thermo-Fisher, and General Electric, and he received support for article research from the NIH. Dr. Wardi’s institution received funding from the National Foundation of Emergency Medicine, he received funding from Thermo-Fisher and Roche/GE, and he received grants from the Gordon and Betty Moore Foundation. Dr. Buchman’s institution received funding from the Henry M. Jackson Foundation and the Society of Critical Care Medicine (SCCM), and he received funding from the Department of Defense and from SCCM. Dr. Nemati received support for article research from the NIH. Dr. Shashikumar has disclosed that he has no potential conflicts of interest.

Subject:

Keywords:

  • Science & Technology
  • Life Sciences & Biomedicine
  • Critical Care Medicine
  • General & Internal Medicine
  • artificial intelligence
  • clinical decision support
  • disease progression
  • intensive care units
  • sepsis
  • septic shock
  • INTERNATIONAL CONSENSUS DEFINITIONS
  • SEPTIC SHOCK
  • EXTERNAL VALIDATION
  • CLINICAL-CRITERIA
  • PROGRESSION

A Locally Optimized Data-Driven Tool to Predict Sepsis-Associated Vasopressor Use in the ICU

Tools:

Journal Title:

CRITICAL CARE MEDICINE

Volume:

Volume 49, Number 12

Publisher:

, Pages E1196-E1205

Type of Work:

Article | Post-print: After Peer Review

Abstract:

OBJECTIVES: To train a model to predict vasopressor use in ICU patients with sepsis and optimize external performance across hospital systems using domain adaptation, a transfer learning approach. DESIGN: Observational cohort study. SETTING: Two academic medical centers from January 2014 to June 2017. PATIENTS: Data were analyzed from 14,512 patients (9,423 at the development site and 5,089 at the validation site) who were admitted to an ICU and met Center for Medicare and Medicaid Services definition of severe sepsis either before or during the ICU stay. Patients were excluded if they never developed sepsis, if the ICU length of stay was less than 8 hours or more than 20 days or if they developed shock up to the first 4 hours of ICU admission. MEASUREMENTS AND MAIN RESULTS: Forty retrospectively collected features from the electronic medical records of adult ICU patients at the development site (four hospitals) were used as inputs for a neural network Weibull-Cox survival model to derive a prediction tool for future need of vasopressors. Domain adaptation updated parameters to optimize model performance in the validation site (two hospitals), a different healthcare system over 2,000 miles away. The cohorts at both sites were randomly split into training and testing sets (80% and 20%, respectively). When applied to the test set in the development site, the model predicted vasopressor use 4-24 hours in advance with an area under the receiver operator characteristic curve, specificity, and positive predictive value ranging from 0.80 to 0.81, 56.2% to 61.8%, and 5.6% to 12.1%, respectively. Domain adaptation improved performance of the model to predict vasopressor use within 4 hours at the validation site (area under the receiver operator characteristic curve 0.81 [CI, 0.80-0.81] from 0.77 [CI, 0.76-0.77], p < 0.01; specificity 59.7% [CI, 58.9-62.5%] from 49.9% [CI, 49.5-50.7%], p < 0.01; positive predictive value 8.9% [CI, 8.5-9.4%] from 7.3 [7.1-7.4%], p < 0.01). CONCLUSIONS: Domain adaptation improved performance of a model predicting sepsis-associated vasopressor use during external validation.

Copyright information:

This is an Open Access work distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (https://creativecommons.org/licenses/by-nc/4.0/).
Export to EndNote