Literature DB >> 22958457

Use of machine-learning classifiers to predict requests for preoperative acute pain service consultation.

Patrick J Tighe1, Stephen D Lucas, David A Edwards, André P Boezaart, Haldun Aytug, Azra Bihorac.   

Abstract

OBJECTIVE: The purpose of this project was to determine whether machine-learning classifiers could predict which patients would require a preoperative acute pain service (APS) consultation.
DESIGN: Retrospective cohort.
SETTING: University teaching hospital.
SUBJECTS: The records of 9,860 surgical patients posted between January 1 and June 30, 2010 were reviewed. OUTCOME MEASURES: Request for APS consultation. A cohort of machine-learning classifiers was compared according to its ability or inability to classify surgical cases as requiring a request for a preoperative APS consultation. Classifiers were then optimized utilizing ensemble techniques. Computational efficiency was measured with the central processing unit processing times required for model training. Classifiers were tested using the full feature set, as well as the reduced feature set that was optimized using a merit-based dimensional reduction strategy.
RESULTS: Machine-learning classifiers correctly predicted preoperative requests for APS consultations in 92.3% (95% confidence intervals [CI], 91.8-92.8) of all surgical cases. Bayesian methods yielded the highest area under the receiver operating curve (0.87, 95% CI 0.84-0.89) and lowest training times (0.0018 seconds, 95% CI, 0.0017-0.0019 for the NaiveBayesUpdateable algorithm). An ensemble of high-performing machine-learning classifiers did not yield a higher area under the receiver operating curve than its component classifiers. Dimensional reduction decreased the computational requirements for multiple classifiers, but did not adversely affect classification performance.
CONCLUSIONS: Using historical data, machine-learning classifiers can predict which surgical cases should prompt a preoperative request for an APS consultation. Dimensional reduction improved computational efficiency and preserved predictive performance. Wiley Periodicals, Inc.

Entities:  

Mesh:

Year:  2012        PMID: 22958457      PMCID: PMC4012229          DOI: 10.1111/j.1526-4637.2012.01477.x

Source DB:  PubMed          Journal:  Pain Med        ISSN: 1526-2375            Impact factor:   3.750


  14 in total

1.  Clinical decision support: progress and opportunities.

Authors:  Jason A Lyman; Wendy F Cohn; Meryl Bloomrosen; Don E Detmer
Journal:  J Am Med Inform Assoc       Date:  2010 Sep-Oct       Impact factor: 4.497

Review 2.  ROC analysis in medical imaging: a tutorial review of the literature.

Authors:  Charles E Metz
Journal:  Radiol Phys Technol       Date:  2007-10-27

Review 3.  Prediction of postoperative pain: a systematic review of predictive experimental pain studies.

Authors:  Mads U Werner; Helena N Mjöbo; Per R Nielsen; Asa Rudin
Journal:  Anesthesiology       Date:  2010-06       Impact factor: 7.892

4.  Increasing operating room efficiency through parallel processing.

Authors:  David M Friedman; Suzanne M Sokal; Yuchiao Chang; David L Berger
Journal:  Ann Surg       Date:  2006-01       Impact factor: 12.969

5.  Prediction of chronic post-operative pain: pre-operative DNIC testing identifies patients at risk.

Authors:  David Yarnitsky; Yonathan Crispel; Elon Eisenberg; Yelena Granovsky; Alon Ben-Nun; Elliot Sprecher; Lael-Anson Best; Michal Granot
Journal:  Pain       Date:  2008-01-08       Impact factor: 6.961

Review 6.  Organization, function, and implementation of acute pain service.

Authors:  Narinder Rawal
Journal:  Anesthesiol Clin North Am       Date:  2005-03

7.  Use of machine learning theory to predict the need for femoral nerve block following ACL repair.

Authors:  Patrick Tighe; Sarah Laduzenski; David Edwards; Neal Ellis; Andre P Boezaart; Haldun Aygtug
Journal:  Pain Med       Date:  2011-09-07       Impact factor: 3.750

8.  Anesthesia-controlled time and turnover time for ambulatory upper extremity surgery performed with regional versus general anesthesia.

Authors:  Edward R Mariano; Larry F Chu; Christopher R Peinado; William J Mazzei
Journal:  J Clin Anesth       Date:  2009-06-06       Impact factor: 9.452

9.  Brachial plexus anesthesia compared to general anesthesia when a block room is available.

Authors:  Kevin P J Armstrong; Richard A Cherry
Journal:  Can J Anaesth       Date:  2004-01       Impact factor: 5.063

10.  Preoperative prediction of severe postoperative pain.

Authors:  J C Kalkman; K Visser; J Moen; J G Bonsel; E D Grobbee; M K G Moons
Journal:  Pain       Date:  2003-10       Impact factor: 6.961

View more
  6 in total

1.  Artificial Intelligence and Machine Learning in Anesthesiology.

Authors:  Christopher W Connor
Journal:  Anesthesiology       Date:  2019-12       Impact factor: 7.892

Review 2.  Primer on machine learning: utilization of large data set analyses to individualize pain management.

Authors:  Parisa Rashidi; David A Edwards; Patrick J Tighe
Journal:  Curr Opin Anaesthesiol       Date:  2019-10       Impact factor: 2.706

3.  Of rough starts and smooth finishes: correlations between post-anesthesia care unit and postoperative days 1-5 pain scores.

Authors:  Patrick James Tighe; Christopher A Harle; Andre Pierre Boezaart; Haldun Aytug; Roger Fillingim
Journal:  Pain Med       Date:  2013-12-05       Impact factor: 3.750

Review 4.  Artificial intelligence and anesthesia: a narrative review.

Authors:  Valentina Bellini; Emanuele Rafano Carnà; Michele Russo; Fabiola Di Vincenzo; Matteo Berghenti; Marco Baciarello; Elena Bignami
Journal:  Ann Transl Med       Date:  2022-05

Review 5.  Machine learning in pain research.

Authors:  Jörn Lötsch; Alfred Ultsch
Journal:  Pain       Date:  2018-04       Impact factor: 6.961

6.  Data science and machine learning in anesthesiology.

Authors:  Dongwoo Chae
Journal:  Korean J Anesthesiol       Date:  2020-03-25
  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.