Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jul 5;24(1):553.
doi: 10.1186/s12891-023-06667-5.

The Skeletal Oncology Research Group Machine Learning Algorithm (SORG-MLA) for predicting prolonged postoperative opioid prescription after total knee arthroplasty: an international validation study using 3,495 patients from a Taiwanese cohort

Cheng-Chen Tsai #  1 , Chuan-Ching Huang #  2 , Ching-Wei Lin #  3   4 , Paul T Ogink  5 , Chih-Chi Su  1   2 , Shin-Fu Chen  1   2 , Mao-Hsu Yen  6 , Jorrit-Jan Verlaan  5 , Joseph H Schwab  7 , Chen-Ti Wang  2 , Olivier Q Groot  5   7 , Ming-Hsiao Hu  8   9 , Hongsen Chiang  10   11
Affiliations

The Skeletal Oncology Research Group Machine Learning Algorithm (SORG-MLA) for predicting prolonged postoperative opioid prescription after total knee arthroplasty: an international validation study using 3,495 patients from a Taiwanese cohort

Cheng-Chen Tsai et al. BMC Musculoskelet Disord. .

Abstract

Background: Preoperative prediction of prolonged postoperative opioid use (PPOU) after total knee arthroplasty (TKA) could identify high-risk patients for increased surveillance. The Skeletal Oncology Research Group machine learning algorithm (SORG-MLA) has been tested internally while lacking external support to assess its generalizability. The aims of this study were to externally validate this algorithm in an Asian cohort and to identify other potential independent factors for PPOU.

Methods: In a tertiary center in Taiwan, 3,495 patients receiving TKA from 2010-2018 were included. Baseline characteristics were compared between the external validation cohort and the original developmental cohorts. Discrimination (area under receiver operating characteristic curve [AUROC] and precision-recall curve [AUPRC]), calibration, overall performance (Brier score), and decision curve analysis (DCA) were applied to assess the model performance. A multivariable logistic regression was used to evaluate other potential prognostic factors.

Results: There were notable differences in baseline characteristics between the validation and the development cohort. Despite these variations, the SORG-MLA ( https://sorg-apps.shinyapps.io/tjaopioid/ ) remained its good discriminatory ability (AUROC, 0.75; AUPRC, 0.34) and good overall performance (Brier score, 0.029; null model Brier score, 0.032). The algorithm could bring clinical benefit in DCA while somewhat overestimating the probability of prolonged opioid use. Preoperative acetaminophen use was an independent factor to predict PPOU (odds ratio, 2.05).

Conclusions: The SORG-MLA retained its discriminatory ability and good overall performance despite the different pharmaceutical regulations. The algorithm could be used to identify high-risk patients and tailor personalized prevention policy.

Keywords: Acetaminophen use; Asian group; Machine learning; Prediction model; Prolonged opioid use; Total knee arthroplasty.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Study flowchart showing the enrolled patients in the validation cohort. TKA, total knee arthroplasty
Fig. 2
Fig. 2
Patient-specific explanation for prediction generated by the online SORG-MLA model at https://sorg-apps.shinyapps.io/tjaopioid/
Fig. 3
Fig. 3
Area under A the receiver operating characteristic curve (AUROC) and B precision-recall curve (AUPRC) for SORG-MLA model
Fig. 4
Fig. 4
A Calibration plot and B decision curve analysis with standardized net benefit by threshold probability for SORG-MLA model
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. McGrory BJ, Weber KL, Jevsevar DS, Sevarino K. Surgical Management of Osteoarthritis of the Knee: Evidence-based Guideline. J Am Acad Orthop Surg. 2016;24(8):e87–93. doi: 10.5435/JAAOS-D-16-00159. - DOI - PubMed
    1. Chrenka EA, Solberg LI, Asche SE, Dehmer SP, Ziegenfuss JY, Whitebird RR, Norton CK, Reams M, Johnson PG, Elwyn G. Is Shared Decision-making Associated with Better Patient-reported Outcomes? A Longitudinal Study of Patients Undergoing Total Joint Arthroplasty. Clin Orthop Relat Res. 2022;480(1):82–91. - PMC - PubMed
    1. Li JW, Ma YS, Xiao LK. Postoperative Pain Management in Total Knee Arthroplasty. Orthop Surg. 2019;11(5):755–761. doi: 10.1111/os.12535. - DOI - PMC - PubMed
    1. Zhuang Q, Tao L, Lin J, Jin J, Qian W, Bian Y, Li Y, Dong Y, Peng H, Li Y, et al. Postoperative intravenous parecoxib sodium followed by oral celecoxib post total knee arthroplasty in osteoarthritis patients (PIPFORCE): a multicentre, double-blind, randomised, placebo-controlled trial. BMJ Open. 2020;10(1):e030501. doi: 10.1136/bmjopen-2019-030501. - DOI - PMC - PubMed
    1. Szeto CC, Sugano K, Wang JG, Fujimoto K, Whittle S, Modi GK, Chen CH, Park JB, Tam LS, Vareesangthip K, et al. Non-steroidal anti-inflammatory drug (NSAID) therapy in patients with hypertension, cardiovascular, renal or gastrointestinal comorbidities: joint APAGE/APLAR/APSDE/APSH/APSN/PoA recommendations. Gut. 2020;69(4):617–629. doi: 10.1136/gutjnl-2019-319300. - DOI - PubMed

Substances