Literature DB >> 29286945

An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU.

Shamim Nemati1, Andre Holder2, Fereshteh Razmi1, Matthew D Stanley3, Gari D Clifford1,4, Timothy G Buchman3,5.   

Abstract

OBJECTIVES: Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop and validate an Artificial Intelligence Sepsis Expert algorithm for early prediction of sepsis.
DESIGN: Observational cohort study.
SETTING: Academic medical center from January 2013 to December 2015. PATIENTS: Over 31,000 admissions to the ICUs at two Emory University hospitals (development cohort), in addition to over 52,000 ICU patients from the publicly available Medical Information Mart for Intensive Care-III ICU database (validation cohort). Patients who met the Third International Consensus Definitions for Sepsis (Sepsis-3) prior to or within 4 hours of their ICU admission were excluded, resulting in roughly 27,000 and 42,000 patients within our development and validation cohorts, respectively.
INTERVENTIONS: None.
MEASUREMENTS AND MAIN RESULTS: High-resolution vital signs time series and electronic medical record data were extracted. A set of 65 features (variables) were calculated on hourly basis and passed to the Artificial Intelligence Sepsis Expert algorithm to predict onset of sepsis in the proceeding T hours (where T = 12, 8, 6, or 4). Artificial Intelligence Sepsis Expert was used to predict onset of sepsis in the proceeding T hours and to produce a list of the most significant contributing factors. For the 12-, 8-, 6-, and 4-hour ahead prediction of sepsis, Artificial Intelligence Sepsis Expert achieved area under the receiver operating characteristic in the range of 0.83-0.85. Performance of the Artificial Intelligence Sepsis Expert on the development and validation cohorts was indistinguishable.
CONCLUSIONS: Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4-12 hours prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed sepsis prediction model.

Entities:  

Mesh:

Year:  2018        PMID: 29286945      PMCID: PMC5851825          DOI: 10.1097/CCM.0000000000002936

Source DB:  PubMed          Journal:  Crit Care Med        ISSN: 0090-3493            Impact factor:   7.598


  24 in total

1.  Multiscale entropy analysis of complex physiologic time series.

Authors:  Madalena Costa; Ary L Goldberger; C-K Peng
Journal:  Phys Rev Lett       Date:  2002-07-19       Impact factor: 9.161

2.  Computer-assisted decision support for changing practice in severe sepsis and septic shock.

Authors:  S Tafelski; I Nachtigall; M Deja; A Tamarkin; T Trefzer; E Halle; K D Wernecke; C Spies
Journal:  J Int Med Res       Date:  2010 Sep-Oct       Impact factor: 1.671

3.  Prediction of severe sepsis using SVM model.

Authors:  Shu-Li Wang; Fan Wu; Bo-Hang Wang
Journal:  Adv Exp Med Biol       Date:  2010       Impact factor: 2.622

4.  Time to Treatment and Mortality during Mandated Emergency Care for Sepsis.

Authors:  Christopher W Seymour; Foster Gesten; Hallie C Prescott; Marcus E Friedrich; Theodore J Iwashyna; Gary S Phillips; Stanley Lemeshow; Tiffany Osborn; Kathleen M Terry; Mitchell M Levy
Journal:  N Engl J Med       Date:  2017-05-21       Impact factor: 91.245

5.  The outcome of patients with sepsis and septic shock presenting to emergency departments in Australia and New Zealand.

Authors: 
Journal:  Crit Care Resusc       Date:  2007-03       Impact factor: 2.159

6.  Clinician blood pressure documentation of stable intensive care patients: an intelligent archiving agent has a higher association with future hypotension.

Authors:  Caleb W Hug; Gari D Clifford; Andrew T Reisner
Journal:  Crit Care Med       Date:  2011-05       Impact factor: 7.598

7.  A physiological time series dynamics-based approach to patient monitoring and outcome prediction.

Authors:  Li-wei H Lehman; Ryan P Adams; Louis Mayaud; George B Moody; Atul Malhotra; Roger G Mark; Shamim Nemati
Journal:  IEEE J Biomed Health Inform       Date:  2014-06-30       Impact factor: 5.772

8.  A targeted real-time early warning score (TREWScore) for septic shock.

Authors:  Katharine E Henry; David N Hager; Peter J Pronovost; Suchi Saria
Journal:  Sci Transl Med       Date:  2015-08-05       Impact factor: 17.956

9.  Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning.

Authors:  Steven Horng; David A Sontag; Yoni Halpern; Yacine Jernite; Nathan I Shapiro; Larry A Nathanson
Journal:  PLoS One       Date:  2017-04-06       Impact factor: 3.240

10.  Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach.

Authors:  Thomas Desautels; Jacob Calvert; Jana Hoffman; Melissa Jay; Yaniv Kerem; Lisa Shieh; David Shimabukuro; Uli Chettipally; Mitchell D Feldman; Chris Barton; David J Wales; Ritankar Das
Journal:  JMIR Med Inform       Date:  2016-09-30
View more
  130 in total

1.  The Respiratory Signature: A Novel Concept to Leverage Continuous Positive Airway Pressure Therapy as an Early Warning System for Exacerbations of Common Diseases such as Heart Failure.

Authors:  Christopher N Schmickl; Eric Heckman; Robert L Owens; Robert J Thomas
Journal:  J Clin Sleep Med       Date:  2019-06-15       Impact factor: 4.062

2.  Predicting Volume Responsiveness Among Sepsis Patients Using Clinical Data and Continuous Physiological Waveforms.

Authors:  Rishikesan Kamaleswaran; Jiaoying Lian; Dong-Lien Lin; Himasagar Molakapuri; SriManikanth Nunna; Parth Shah; Shiv Dua; Rema Padman
Journal:  AMIA Annu Symp Proc       Date:  2021-01-25

3.  Contextual Embeddings from Clinical Notes Improves Prediction of Sepsis.

Authors:  Fatemeh Amrollahi; Supreeth P Shashikumar; Fereshteh Razmi; Shamim Nemati
Journal:  AMIA Annu Symp Proc       Date:  2021-01-25

4.  Artificial intelligence in intensive care: are we there yet?

Authors:  Matthieu Komorowski
Journal:  Intensive Care Med       Date:  2019-06-24       Impact factor: 17.440

Review 5.  Insights into Computational Drug Repurposing for Neurodegenerative Disease.

Authors:  Manish D Paranjpe; Alice Taubes; Marina Sirota
Journal:  Trends Pharmacol Sci       Date:  2019-07-17       Impact factor: 14.819

Review 6.  Big Data and Data Science in Critical Care.

Authors:  L Nelson Sanchez-Pinto; Yuan Luo; Matthew M Churpek
Journal:  Chest       Date:  2018-05-09       Impact factor: 9.410

Review 7.  Applying machine learning to continuously monitored physiological data.

Authors:  Barret Rush; Leo Anthony Celi; David J Stone
Journal:  J Clin Monit Comput       Date:  2018-11-11       Impact factor: 2.502

8.  Clinical management of sepsis can be improved by artificial intelligence: no.

Authors:  José Garnacho-Montero; Ignacio Martín-Loeches
Journal:  Intensive Care Med       Date:  2020-02-03       Impact factor: 17.440

9.  Temporal convolutional networks allow early prediction of events in critical care.

Authors:  Finneas J R Catling; Anthony H Wolff
Journal:  J Am Med Inform Assoc       Date:  2020-03-01       Impact factor: 4.497

Review 10.  A Review of Predictive Analytics Solutions for Sepsis Patients.

Authors:  Andrew K Teng; Adam B Wilcox
Journal:  Appl Clin Inform       Date:  2020-05-27       Impact factor: 2.342

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.