CaltechAUTHORS
  A Caltech Library Service

An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data

Hill, Brian L. and Brown, Robert and Gabel, Eilon and Rakocz, Nadav and Lee, Christine and Cannesson, Maxime and Baldi, Pierre and Loohuis, Loes Olde and Johnson, Ruth and Jew, Brandon and Maoz, Uri and Mahajan, Aman and Sankararaman, Sriram and Hofer, Ira and Halperin, Eran (2019) An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data. British Journal of Anaesthesia, 123 (6). pp. 877-886. ISSN 0007-0912. https://resolver.caltech.edu/CaltechAUTHORS:20191016-074401056

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20191016-074401056

Abstract

Background: Rapid, preoperative identification of patients with the highest risk for medical complications is necessary to ensure that limited infrastructure and human resources are directed towards those most likely to benefit. Existing risk scores either lack specificity at the patient level or utilise the American Society of Anesthesiologists (ASA) physical status classification, which requires a clinician to review the chart. Methods: We report on the use of machine learning algorithms, specifically random forests, to create a fully automated score that predicts postoperative in-hospital mortality based solely on structured data available at the time of surgery. Electronic health record data from 53 097 surgical patients (2.01% mortality rate) who underwent general anaesthesia between April 1, 2013 and December 10, 2018 in a large US academic medical centre were used to extract 58 preoperative features. Results: Using a random forest classifier we found that automatically obtained preoperative features (area under the curve [AUC] of 0.932, 95% confidence interval [CI] 0.910–0.951) outperforms Preoperative Score to Predict Postoperative Mortality (POSPOM) scores (AUC of 0.660, 95% CI 0.598–0.722), Charlson comorbidity scores (AUC of 0.742, 95% CI 0.658–0.812), and ASA physical status (AUC of 0.866, 95% CI 0.829–0.897). Including the ASA physical status with the preoperative features achieves an AUC of 0.936 (95% CI 0.917–0.955). Conclusions: This automated score outperforms the ASA physical status score, the Charlson comorbidity score, and the POSPOM score for predicting in-hospital mortality. Additionally, we integrate this score with a previously published postoperative score to demonstrate the extent to which patient risk changes during the perioperative period.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1016/j.bja.2019.07.030DOIArticle
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6883494/PubMed CentralArticle
ORCID:
AuthorORCID
Maoz, Uri0000-0002-7899-1241
Additional Information:© 2019 British Journal of Anaesthesia. Published by Elsevier Ltd. Accepted 29 July 2019, Available online 15 October 2019.
Subject Keywords:electronic health record; hospital mortality; machine learning; perioperative outcome; risk assessment
Issue or Number:6
Record Number:CaltechAUTHORS:20191016-074401056
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20191016-074401056
Official Citation:Brian L. Hill, Robert Brown, Eilon Gabel, Nadav Rakocz, Christine Lee, Maxime Cannesson, Pierre Baldi, Loes Olde Loohuis, Ruth Johnson, Brandon Jew, Uri Maoz, Aman Mahajan, Sriram Sankararaman, Ira Hofer, Eran Halperin, An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data, British Journal of Anaesthesia, Volume 123, Issue 6, 2019, Pages 877-886, ISSN 0007-0912, https://doi.org/10.1016/j.bja.2019.07.030. (http://www.sciencedirect.com/science/article/pii/S0007091219306464)
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:99287
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:16 Oct 2019 15:03
Last Modified:05 Mar 2020 00:09

Repository Staff Only: item control page