skip to main content
10.1145/3437378.3437398acmotherconferencesArticle/Chapter ViewAbstractPublication PagesacswConference Proceedingsconference-collections
short-paper

A comparative analysis of sepsis digital phenotyping methods

Published: 01 February 2021 Publication History

Abstract

Health data captured in Electronic health records (EHRs) have enabled the development of computational approaches to improve patient management and treatment, including early diagnosis of severe conditions such as sepsis. The validity of these efforts, however, largely relies on which sepsis definition is used and the quality of the underlying data. Here we tested different sepsis definitions to better understand how phenotyping approaches may impact the classification accuracy of sepsis prediction algorithms.
To assess the extent to which sepsis definitions (dis)agree with each other, we have analised a large cohort of patients admitted to the ICU (over 22,000) from MIMIC-IV. Cases were classified as septic and non-septic using the Sepsis-3 definition as a standard and compared with different ICD-10-based sepsis phenotyping criteria.
Most of administrative sepsis definitions agreed with each other when identifying positive sepsis cases. At the same time, we identified considerable disagreement between Sepsis-3 and administrative definitions. This discrepancy affected machine learning algorithms’ predictive performance. Two algorithms out of three built on Sepsis-3 outperformed models based on other phenotypes. Experiments demonstrate that phenotype definitions can significantly influence a predictive model performance. This highlights the importance of consistent and validated digital phenotyping criteria.

References

[1]
Mette K Beck, Anders Boeck Jensen, Annelaura Bach Nielsen, Anders Perner, Pope L Moseley, and Søren Brunak. 2016. Diagnosis trajectories of prior multi-morbidity predict sepsis mortality. Scientific reports 6, 1 (2016), 1–9.
[2]
Jacob S Calvert, Daniel A Price, Uli K Chettipally, Christopher W Barton, Mitchell D Feldman, Jana L Hoffman, Melissa Jay, and Ritankar Das. 2016. A computational approach to early sepsis detection. Computers in biology and medicine 74 (2016), 69–73.
[3]
Seitaro Fujishima. 2016. Organ dysfunction as a new standard for defining sepsis. Inflammation and Regeneration 36, 1 (2016), 24.
[4]
Rolf Gedeborg, Mia Furebring, and Karl Michaëlsson. 2007. Diagnosis-dependent misclassification of infections using administrative data variably affected incidence and mortality estimates in ICU patients. Journal of clinical epidemiology 60, 2 (2007), 155–e1.
[5]
Ary L Goldberger, Luis AN Amaral, Leon Glass, Jeffrey M Hausdorff, Plamen Ch Ivanov, Roger G Mark, Joseph E Mietus, George B Moody, Chung-Kang Peng, and H Eugene Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. circulation 101, 23 (2000), e215–e220.
[6]
Toni Henderson, Jennie Shepheard, and Vijaya Sundararajan. 2006. Quality of diagnosis and procedure coding in ICD-10 administrative data. Medical care (2006), 1011–1019.
[7]
Irwani Ibrahim, Ian G Jacobs, Steven AR Webb, Judith Finn, 2012. Accuracy of International classification of diseases, 10th revision codes for identifying severe sepsis in patients admitted from the emergency department. Critical Care and Resuscitation 14, 2 (2012), 112.
[8]
Alistair EW Johnson, Jerome Aboab, Jesse D Raffa, Tom J Pollard, Rodrigo O Deliberato, Leo Anthony Celi, and David J Stone. 2018. A comparative analysis of sepsis identification methods in an electronic database. Critical care medicine 46, 4 (2018), 494.
[9]
Peter MC Klein Klouwenberg, Olaf L Cremer, Lonneke A van Vught, David SY Ong, Jos F Frencken, Marcus J Schultz, Marc J Bonten, and Tom van der Poll. 2015. Likelihood of infection in patients with presumed sepsis at the time of intensive care unit admission: a cohort study. Critical Care 19(2015), 319.
[10]
Vincent X Liu, Vikram Fielding-Singh, John D Greene, Jennifer M Baker, Theodore J Iwashyna, Jay Bhattacharya, and Gabriel J Escobar. 2017. The timing of early antibiotics and hospital mortality in sepsis. American journal of respiratory and critical care medicine 196, 7(2017), 856–863.
[11]
Kreesten Meldgaard Madsen, Henrik Carl Schønheyder, Brian Kristensen, Gunnar Lauge Nielsen, and Henrik Toft Sørensen. 1998. Can hospital discharge diagnosis be used for surveillance of bacteremia? A data quality study of a Danish hospital discharge registry. Infection Control & Hospital Epidemiology 19, 3 (1998), 175–180.
[12]
Hude Quan, Cathy Eastwood, Ceara Tess Cunningham, Mingfu Liu, Ward Flemons, Carolyn De Coster, William A Ghali, IMECCHI investigators, 2013. Validity of AHRQ patient safety indicators derived from ICD-10 hospital discharge abstract data (chart review study). BMJ open 3, 10 (2013).
[13]
Chanu Rhee, Shruti Gohil, and Michael Klompas. 2014. Regulatory mandates for sepsis care—reasons for caution. New England Journal of Medicine 370, 18 (2014), 1673–1676.
[14]
Kristina E Rudd, Sarah Charlotte Johnson, Kareha M Agesa, Katya Anne Shackelford, Derrick Tsoi, Daniel Rhodes Kievlan, Danny V Colombara, Kevin S Ikuta, Niranjan Kissoon, Simon Finfer, 2020. Global, regional, and national sepsis incidence and mortality, 1990–2017: analysis for the Global Burden of Disease Study. The Lancet 395, 10219 (2020), 200–211.
[15]
Yasser Sakr, Ulrich Jaschinski, Xavier Wittebole, Tamas Szakmany, Jeffrey Lipman, Silvio A Ñamendys-Silva, Ignacio Martin-Loeches, Marc Leone, Mary-Nicoleta Lupu, Jean-Louis Vincent, 2018. Sepsis in intensive care unit patients: worldwide data from the intensive care over nations audit. In Open forum infectious diseases, Vol. 5. Oxford University Press US, ofy313.
[16]
Mervyn Singer, Clifford S Deutschman, Christopher Warren Seymour, Manu Shankar-Hari, Djillali Annane, Michael Bauer, Rinaldo Bellomo, Gordon R Bernard, Jean-Daniel Chiche, Craig M Coopersmith, 2016. The third international consensus definitions for sepsis and septic shock (Sepsis-3). Jama 315, 8 (2016), 801–810.
[17]
Vijaya Sundararajan, Christopher M MacIsaac, Jeffrey J Presneill, John F Cade, and Kumar Visvanathan. 2005. Epidemiology of sepsis in Victoria, Australia. Critical care medicine 33, 1 (2005), 71–80.
[18]
Jean-Louis Vincent, Yasser Sakr, Charles L Sprung, V Marco Ranieri, Konrad Reinhart, Herwig Gerlach, Rui Moreno, Jean Carlet, Jean-Roger Le Gall, Didier Payen, 2006. Sepsis in European intensive care units: results of the SOAP study. Critical care medicine 34, 2 (2006), 344–353.

Index Terms

  1. A comparative analysis of sepsis digital phenotyping methods
          Index terms have been assigned to the content through auto-classification.

          Recommendations

          Comments

          Information & Contributors

          Information

          Published In

          cover image ACM Other conferences
          ACSW '21: Proceedings of the 2021 Australasian Computer Science Week Multiconference
          February 2021
          211 pages
          ISBN:9781450389563
          DOI:10.1145/3437378
          Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

          Publisher

          Association for Computing Machinery

          New York, NY, United States

          Publication History

          Published: 01 February 2021

          Permissions

          Request permissions for this article.

          Check for updates

          Author Tags

          1. MIMIC-IV
          2. digital phenotyping
          3. sepsis
          4. supervised learning

          Qualifiers

          • Short-paper
          • Research
          • Refereed limited

          Conference

          ACSW '21

          Acceptance Rates

          Overall Acceptance Rate 61 of 141 submissions, 43%

          Contributors

          Other Metrics

          Bibliometrics & Citations

          Bibliometrics

          Article Metrics

          • 0
            Total Citations
          • 122
            Total Downloads
          • Downloads (Last 12 months)23
          • Downloads (Last 6 weeks)0
          Reflects downloads up to 20 Jan 2025

          Other Metrics

          Citations

          View Options

          Login options

          View options

          PDF

          View or Download as a PDF file.

          PDF

          eReader

          View online with eReader.

          eReader

          HTML Format

          View this article in HTML Format.

          HTML Format

          Media

          Figures

          Other

          Tables

          Share

          Share

          Share this Publication link

          Share on social media