Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec 13;14(12):e0226272.
doi: 10.1371/journal.pone.0226272. eCollection 2019.

Predicting the occurrence of surgical site infections using text mining and machine learning

Daniel A da Silva  1 , Carla S Ten Caten  1 , Rodrigo P Dos Santos  2 , Flavio S Fogliatto  1 , Juliana Hsuan  3
Affiliations

Predicting the occurrence of surgical site infections using text mining and machine learning

Daniel A da Silva et al. PLoS One. .

Abstract

In this study we propose the use of text mining and machine learning methods to predict and detect Surgical Site Infections (SSIs) using textual descriptions of surgeries and post-operative patients' records, mined from the database of a high complexity University hospital. SSIs are among the most common adverse events experienced by hospitalized patients; preventing such events is fundamental to ensure patients' safety. Knowledge on SSI occurrence rates may also be useful in preventing future episodes. We analyzed 15,479 surgery descriptions and post-operative records testing different preprocessing strategies and the following machine learning algorithms: Linear SVC, Logistic Regression, Multinomial Naive Bayes, Nearest Centroid, Random Forest, Stochastic Gradient Descent, and Support Vector Classification (SVC). For prediction purposes, the best result was obtained using the Stochastic Gradient Descent method (79.7% ROC-AUC); for detection, Logistic Regression yielded the best performance (80.6% ROC-AUC).

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Overview of the proposed method.
Fig 2
Fig 2. ROC-AUC performance of algorithms in predicting SSIs.
Fig 3
Fig 3. Precision-recall percentages and boxplots for surgical descriptions.
Fig 4
Fig 4. Precision-recall curves of methods tested for predicting SSIs.
Fig 5
Fig 5. ROC-AUC performance of algorithms in detecting SSIs.
Fig 6
Fig 6. Precision-recall percentages and boxplots for post-operative notes.
Fig 7
Fig 7. Precision-recall curves of methods tested for detecting SSIs.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Anvisa/Brasil. Infection Diagnostic Criteria Related to Healthcare. In: Agência Nacional de Vigilância Sanitária [Internet]. 2017. p. 13–88. Available from: www.anvisa.gov.br
    1. Wachter RM. Understanding Patient Safety. In: AMGH Editora. 2013. 479 p.
    1. Stone PW, Kunches L, Hirschhorn L. Cost of hospital-associated infections in Massachusetts. Am J Infect Control. 2009;37(3):210–214. 10.1016/j.ajic.2008.07.011 - DOI - PubMed
    1. Bouzbid S, Gicquel Q, Gerbier S, Chomarat M, Pradat E, Fabry J, et al. Automated detection of nosocomial infections: Evaluation of different strategies in an intensive care unit 2000–2006. J Hosp Infect [Internet]. 2011;79(1):38–43. Available from: http://ovidsp.ovid.com/ovidweb.cgi?T=JS&PAGE=reference&D=emed10&NEWS=N&A... 10.1016/j.jhin.2011.05.006 - DOI - PubMed
    1. Michelson JD, Pariseau JS, Paganelli WC. Assessing surgical site infection risk factors using electronic medical records and text mining. Am J Infect Control [Internet]. 2014;42(3):333–336. Available from: http://www.scopus.com/inward/record.url?eid=2-s2.0-84896735530&partnerID... 10.1016/j.ajic.2013.09.007 - DOI - PubMed