loading
Documents

Research.Publish.Connect.

Paper

Authors: Erin Teeple 1 ; Thomas Hartvigsen 1 ; Cansu Sen 2 ; Kajal Claypool 3 and Elke Rundensteiner 4

Affiliations: 1 Data Science Program, Worcester Polytechnic Institute, Worcester, MA, U.S.A. ; 2 Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA, U.S.A. ; 3 Harvard Medical School, Boston, MA, U.S.A. ; 4 Data Science Program, Worcester Polytechnic Institute, Worcester, MA, U.S.A., Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA, U.S.A.

ISBN: 978-989-758-398-8

ISSN: 2184-4305

Keyword(s): Electronic Health Record (EHR), Healthcare, Machine Learning, Clostridium Difficile Infection (CDI), Hospital-Acquired Infection (HAI).

Abstract: Clostridium difficile infection (CDI) is a common and often serious hospital-acquired infection. The CDI Risk Estimation System (CREST) was developed to apply machine learning methods to predict a patient’s daily hospital-acquired CDI risk using information from the electronic health record (EHR). In recent years, several systems have been developed to predict patient health risks based on electronic medical record information. How to interpret the outputs of such systems and integrate them with healthcare work processes remains a challenge, however. In this paper, we explore the clinical interpretation of CDI Risk Scores assigned by the CREST framework for an L1-regularized Logistic Regression classifier trained using EHR data from the publicly available MIMIC-III Database. Predicted patient CDI risk is used to calculate classifier system output sensitivity, specificity, positive and negative predictive values, and diagnostic odds ratio using EHR data from five days and one day befor e diagnosis. We identify features which are strongly predictive of evolving infection by comparing coefficient weights for our trained models and consider system performance in the context of potential clinical applications. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.170.78.142

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Teeple, E.; Hartvigsen, T.; Sen, C.; Claypool, K. and Rundensteiner, E. (2020). Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired Clostridium Difficile Infection.In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5 HEALTHINF: HEALTHINF, ISBN 978-989-758-398-8, ISSN 2184-4305, pages 656-663. DOI: 10.5220/0009157406560663

@conference{healthinf20,
author={Erin Teeple. and Thomas Hartvigsen. and Cansu Sen. and Kajal Claypool. and Elke Rundensteiner.},
title={Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired Clostridium Difficile Infection},
booktitle={Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5 HEALTHINF: HEALTHINF,},
year={2020},
pages={656-663},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009157406560663},
isbn={978-989-758-398-8},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5 HEALTHINF: HEALTHINF,
TI - Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired Clostridium Difficile Infection
SN - 978-989-758-398-8
AU - Teeple, E.
AU - Hartvigsen, T.
AU - Sen, C.
AU - Claypool, K.
AU - Rundensteiner, E.
PY - 2020
SP - 656
EP - 663
DO - 10.5220/0009157406560663

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.