CaltechAUTHORS
  A Caltech Library Service

Prediction of Mortality in Surgical Intensive Care Unit Patients Using Machine Learning Algorithms

Yun, Kyongsik and Oh, Jihoon and Hong, Tae Ho and Kim, Eun Young (2021) Prediction of Mortality in Surgical Intensive Care Unit Patients Using Machine Learning Algorithms. Frontiers in Medicine, 8 . Art. No. 621861. ISSN 2296-858X. PMCID PMC8044535. doi:10.3389/fmed.2021.621861. https://resolver.caltech.edu/CaltechAUTHORS:20210505-082417501

[img] PDF - Published Version
Creative Commons Attribution.

1MB
[img] Image (PNG) - Supplemental Material
Creative Commons Attribution.

252kB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210505-082417501

Abstract

Objective: Predicting prognosis of in-hospital patients is critical. However, it is challenging to accurately predict the life and death of certain patients at certain period. To determine whether machine learning algorithms could predict in-hospital death of critically ill patients with considerable accuracy and identify factors contributing to the prediction power. Materials and Methods: Using medical data of 1,384 patients admitted to the Surgical Intensive Care Unit (SICU) of our institution, we investigated whether machine learning algorithms could predict in-hospital death using demographic, laboratory, and other disease-related variables, and compared predictions using three different algorithmic methods. The outcome measurement was the incidence of unexpected postoperative mortality which was defined as mortality without pre-existing not-for-resuscitation order that occurred within 30 days of the surgery or within the same hospital stay as the surgery. Results: Machine learning algorithms trained with 43 variables successfully classified dead and live patients with very high accuracy. Most notably, the decision tree showed the higher classification results (Area Under the Receiver Operating Curve, AUC = 0.96) than the neural network classifier (AUC = 0.80). Further analysis provided the insight that serum albumin concentration, total prenatal nutritional intake, and peak dose of dopamine drug played an important role in predicting the mortality of SICU patients. Conclusion: Our results suggest that machine learning algorithms, especially the decision tree method, can provide information on structured and explainable decision flow and accurately predict hospital mortality in SICU hospitalized patients.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.3389/fmed.2021.621861DOIArticle
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8044535PubMed CentralArticle
ORCID:
AuthorORCID
Yun, Kyongsik0000-0002-6103-7187
Additional Information:© 2021 Yun, Oh, Hong and Kim. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Received: 27 October 2020; Accepted: 12 March 2021; Published: 31 March 2021. Data Availability Statement: The data analyzed in this study is subject to the restrictions. Data can be shared with permission from the institutional review board of the Catholic University of Korea. Requests to access these datasets should be directed to Eun Young Kim, freesshs@naver.com. The studies involving human participants were reviewed and approved by The Catholic University of Korea. Written informed consent for participation was not required for this study in accordance with the national legislation and the institutional requirements. Author Contributions: KY and EK build research design and collected. KY, JO, and TH analyzed and interpreted the patient data. JO and KY were a major contributor in writing the manuscript. All authors read and approved the final manuscript. The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Subject Keywords:anesthesia and intensive care, informatics, intensive care, surgery, machine learning
PubMed Central ID:PMC8044535
DOI:10.3389/fmed.2021.621861
Record Number:CaltechAUTHORS:20210505-082417501
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210505-082417501
Official Citation:Yun K, Oh J, Hong TH and Kim EY (2021) Prediction of Mortality in Surgical Intensive Care Unit Patients Using Machine Learning Algorithms. Front. Med. 8:621861. doi: 10.3389/fmed.2021.621861
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108973
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 May 2021 17:29
Last Modified:05 May 2021 17:29

Repository Staff Only: item control page