Literature DB >> 35090725

Continuous real-time prediction of surgical case duration using a modular artificial neural network.

York Jiao1, Bing Xue2, Chenyang Lu2, Michael S Avidan3, Thomas Kannampallil4.   

Abstract

BACKGROUND: Real-time prediction of surgical duration can inform perioperative decisions and reduce surgical costs. We developed a machine learning approach that continuously incorporates preoperative and intraoperative information for forecasting surgical duration.
METHODS: Preoperative (e.g. procedure name) and intraoperative (e.g. medications and vital signs) variables were retrieved from anaesthetic records of surgeries performed between March 1, 2019 and October 31, 2019. A modular artificial neural network was developed and compared with a Bayesian approach and the scheduled surgical duration. Continuous ranked probability score (CRPS) was used as a measure of time error to assess model accuracy. For evaluating clinical performance, accuracy for each approach was assessed in identifying cases that ran beyond 15:00 (commonly scheduled end of shift), thus identifying opportunities to avoid overtime labour costs.
RESULTS: The analysis included 70 826 cases performed at eight hospitals. The modular artificial neural network had the lowest time error (CRPS: mean=13.8; standard deviation=35.4 min), which was significantly better (mean difference=6.4 min [95% confidence interval: 6.3-6.5]; P<0.001) than the Bayesian approach. The modular artificial neural network also had the highest accuracy in identifying operating theatres that would overrun 15:00 (accuracy at 1 h prior=89%) compared with the Bayesian approach (80%) and a naïve approach using the scheduled duration (78%).
CONCLUSIONS: A real-time neural network model using preoperative and intraoperative data had significantly better performance than a Bayesian approach or scheduled duration, offering opportunities to avoid overtime labour costs and reduce the cost of surgery by providing superior real-time information for perioperative decision support.
Copyright © 2022 British Journal of Anaesthesia. Published by Elsevier Ltd. All rights reserved.

Entities:  

Keywords:  artificial neural network; economics; healthcare costs; machine learning; operating theatre efficiency; procedure duration; statistical model; surgery

Mesh:

Year:  2022        PMID: 35090725      PMCID: PMC9074795          DOI: 10.1016/j.bja.2021.12.039

Source DB:  PubMed          Journal:  Br J Anaesth        ISSN: 0007-0912            Impact factor:   11.719


  7 in total

1.  A strategy for deciding operating room assignments for second-shift anesthetists.

Authors:  F Dexter; A Macario; L O'Neill
Journal:  Anesth Analg       Date:  1999-10       Impact factor: 5.108

Review 2.  Making management decisions on the day of surgery based on operating room efficiency and patient waiting times.

Authors:  Franklin Dexter; Richard H Epstein; Rodney D Traub; Yan Xiao
Journal:  Anesthesiology       Date:  2004-12       Impact factor: 7.892

3.  Validity and usefulness of a method to monitor surgical services' average bias in scheduled case durations.

Authors:  Franklin Dexter; Alex Macario; Richard H Epstein; Johannes Ledolter
Journal:  Can J Anaesth       Date:  2005-11       Impact factor: 5.063

4.  Method to assist in the scheduling of add-on surgical cases--upper prediction bounds for surgical case durations based on the log-normal distribution.

Authors:  J Zhou; F Dexter
Journal:  Anesthesiology       Date:  1998-11       Impact factor: 7.892

5.  Prospective trial of thoracic and spine surgeons' updating of their estimated case durations at the start of cases.

Authors:  Elisabeth U Dexter; Franklin Dexter; Danielle Masursky; Kimberly A Kasprowicz
Journal:  Anesth Analg       Date:  2010-02-09       Impact factor: 5.108

6.  Understanding Costs of Care in the Operating Room.

Authors:  Christopher P Childers; Melinda Maggard-Gibbons
Journal:  JAMA Surg       Date:  2018-04-18       Impact factor: 14.766

7.  A strategy to decide whether to move the last case of the day in an operating room to another empty operating room to decrease overtime labor costs.

Authors:  F Dexter
Journal:  Anesth Analg       Date:  2000-10       Impact factor: 5.108

  7 in total
  1 in total

1.  Operating Room Usage Time Estimation with Machine Learning Models.

Authors:  Justin Chu; Chung-Ho Hsieh; Yi-Nuo Shih; Chia-Chun Wu; Anandakumar Singaravelan; Lun-Ping Hung; Jia-Lien Hsu
Journal:  Healthcare (Basel)       Date:  2022-08-12
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.