You are here

Article Text

Article menu
Download PDFPDF
Special article
Machine learning research methods to predict postoperative pain and opioid use: a narrative review
  1. Dale J Langford1,2,
  2. Julia F Reichel3,
  3. Haoyan Zhong3,
  4. Benjamin H Basseri3,
  5. Marc P Koch4,
  6. Ramana Kolady5,
  7. Jiabin Liu1,2,
  8. Alexandra Sideris1,2,6,
  9. Robert H Dworkin1,6,7,
  10. Jashvant Poeran1,6 and
  11. Christopher L Wu1,2
  1. 1 Pain Prevention Research Center, Department of Anesthesiology, Critical Care & Pain Management, Hospital for Special Surgery, New York, New York, USA
  2. 2 Department of Anesthesiology, Weill Cornell Medicine, New York, New York, USA
  3. 3 Department of Anesthesiology, Critical Care & Pain Management, Hospital for Special Surgery, New York, New York, USA
  4. 4 Davidson College, Davidson, North Carolina, USA
  5. 5 University of Rochester, Rochester, New York, USA
  6. 6 Hospital for Special Surgery Research Institute, New York, New York, USA
  7. 7 Anesthesiology and Perioperative Medicine, University of Rochester, Rochester, New York, USA
  1. Correspondence to Dr Dale J Langford; langfordd{at}hss.edu

Abstract

The use of machine learning to predict postoperative pain and opioid use has likely been catalyzed by the availability of complex patient-level data, computational and statistical advancements, the prevalence and impact of chronic postsurgical pain, and the persistence of the opioid crisis. The objectives of this narrative review were to identify and characterize methodological aspects of studies that have developed and/or tested machine learning algorithms to predict acute, subacute, or chronic pain or opioid use after any surgery and to propose considerations for future machine learning studies. Pairs of independent reviewers screened titles and abstracts of 280 PubMed-indexed articles and ultimately extracted data from 61 studies that met entry criteria. We observed a marked increase in the number of relevant publications over time. Studies most commonly focused on machine learning algorithms to predict chronic postsurgical pain or opioid use, using real-world data from patients undergoing orthopedic surgery. We identified variability in sample size, number and type of predictors, and how outcome variables were defined. Patient-reported predictors were highlighted as particularly informative and important to include in such machine learning algorithms, where possible. We hope that findings from this review might inform future applications of machine learning that improve the performance and clinical utility of resultant machine learning algorithms.

  • Pain, Postoperative
  • Analgesics, Opioid
  • Methods
  • machine learning

Data availability statement

Data are available upon reasonable request. Data may be made available on reasonable written request.

https://doi.org/10.1136/rapm-2024-105603

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available upon reasonable request. Data may be made available on reasonable written request.

    View Full Text

    Footnotes

    • X @djlPAINology, @jbLiujb, @jashvant_p, @@ChrisWuMD

    • Contributors Review conception, design, conduct, oversight, analysis, writing, and guarantor (responsible for overall content): DJL. Study conduct, writing: JFR, BHB. Study design, conduct, editing: ZH. Study conduct, editing: MPK, RK. Critical editing: JL, AS, JP, RHD, CLW.

    • Funding This work was supported by HSS’ Department of Anesthesiology, Critical Care, & Pain Management’s Research & Education Fund. Data extraction via REDCap was supported by grant number UL1 TR 002384 from the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH).

    • Competing interests While there are no conflicts of interest directly related to this work, RHD, PhD, since January 1, 2021 has received research grants and contracts from the US Food and Drug Administration and the US National Institutes of Health, and compensation for serving on advisory boards or consulting on clinical trial methods from Acadia, Akigai, Allay, AM-Pharma, Analgesic Solutions, Beckley, Biogen, Biosplice, Bsense, Cardialen, Chiesi, Clexio, Collegium, CombiGene, Confo, Contineum, Eccogene, Editas, Eli Lilly, Emmes, Endo, Epizon, Ethismos (equity), Exicure, GlaxoSmithKline, Glenmark, Gloriana, JucaBio, Kriya, Mainstay, Merck, Mind Medicine (also equity), NeuroBo, Noema, OliPass, Orion, Oxford Cannabinoid Technologies, Pfizer, Q-State, Regenacy (also equity), Rho, Sangamo, Semnur, SIMR Biotech, Sinfonia, SK Biopharmaceuticals, Sparian, SPM Therapeutics, SPRIM Health, Tiefenbacher, Validae, Vertex, Viscera, and WCG.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.