Newly Published
Perioperative Medicine  |   April 2018
Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality
Author Notes
  • From the Department of Anesthesiology and Perioperative Care (C.K.L., M.C.)
  • Department of Computer Sciences (C.K.L., P.B.) University of California Irvine, Irvine, California
  • Department of Bioengineering (M.C.), University of California Irvine, Irvine, California
  • Department of Anesthesiology and Perioperative Medicine, University of California Los Angeles, Los Angeles, California (I.H., E.G., M.C.).
  • Supplemental Digital Content is available for this article. Direct URL citations appear in the printed text and are available in both the HTML and PDF versions of this article. Links to the digital files are provided in the HTML text of this article on the Journal’s Web site (www.anesthesiology.org).
    Supplemental Digital Content is available for this article. Direct URL citations appear in the printed text and are available in both the HTML and PDF versions of this article. Links to the digital files are provided in the HTML text of this article on the Journal’s Web site (www.anesthesiology.org).×
  • Part of this work was presented at the Society for Technology in Anesthesia Annual Meeting 2017 and received the best of show award for the best abstract presentation of the meeting.
    Part of this work was presented at the Society for Technology in Anesthesia Annual Meeting 2017 and received the best of show award for the best abstract presentation of the meeting.×
  • Submitted for publication July 15, 2017. Accepted for publication February 5, 2018.
    Submitted for publication July 15, 2017. Accepted for publication February 5, 2018.×
  • Research Support: Support was provided solely from institutional and/or departmental sources.
    Research Support: Support was provided solely from institutional and/or departmental sources.×
  • Competing Interests: Dr. Lee is an Edwards Lifesciences (Irvine, California) employee, but this work was done independently from this position and as part of her Ph.D. Dr. Cannesson has ownership interest in Sironis, a company developing closed-loop systems, and does consulting for Edwards Lifesciences and Masimo Corp. (Irvine, California). Dr. Cannesson has received research support from Edwards Lifesciences through his department and National Institutes of Health (Bethesda, Maryland) grant Nos. R01 GM117622 (“Machine Learning of Physiological Variables to Predict Diagnose and Treat Cardiorespiratory Instability”) and R01 NR013912 (“Predicting Patient Instability Noninvasively for Nursing Care-Two [PPINNC-2]”). The other authors declare no competing interests.
    Competing Interests: Dr. Lee is an Edwards Lifesciences (Irvine, California) employee, but this work was done independently from this position and as part of her Ph.D. Dr. Cannesson has ownership interest in Sironis, a company developing closed-loop systems, and does consulting for Edwards Lifesciences and Masimo Corp. (Irvine, California). Dr. Cannesson has received research support from Edwards Lifesciences through his department and National Institutes of Health (Bethesda, Maryland) grant Nos. R01 GM117622 (“Machine Learning of Physiological Variables to Predict Diagnose and Treat Cardiorespiratory Instability”) and R01 NR013912 (“Predicting Patient Instability Noninvasively for Nursing Care-Two [PPINNC-2]”). The other authors declare no competing interests.×
  • Correspondence: Address correspondence to Dr. Cannesson: Department of Anesthesiology and Perioperative Medicine, University of California Los Angeles, 757 Westwood Plaza, Los Angeles, California 90095. mcannesson@mednet.ucla.edu. Information on purchasing reprints may be found at www.anesthesiology.org or on the masthead page at the beginning of this issue. Anesthesiology’s articles are made freely accessible to all readers, for personal use only, 6 months from the cover date of the issue.
Article Information
Perioperative Medicine / Pharmacology
Perioperative Medicine   |   April 2018
Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality
Anesthesiology Newly Published on April 16, 2018. doi:10.1097/ALN.0000000000002186
Anesthesiology Newly Published on April 16, 2018. doi:10.1097/ALN.0000000000002186
Abstract

Background: The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality.

Methods: The data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index.

Results: In-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99).

Conclusions: Deep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.