Abstract
Objective
To evaluate the performance of two machine learning models in predicting the long-term complete pain resolution in patients undergoing ultrasound-guided percutaneous irrigation of calcific tendinopathy (US-PICT).
Materials and methods
Within a 3-year period, 100 consecutive patients who underwent US-PICT for rotator cuff disease were prospectively enrolled. The location, maximum diameter, and type of each calcification were recorded. The degree of calcium retrieval was graded as complete or incomplete. Shoulder pain was assessed with the visual analogue scale (VAS) at baseline, 1-week, 1-month, and 1-year post-treatment. Measurements related to procedural details, patient, and calcification characteristics were used to construct a machine learning model for the prediction of pain at 1-year post-US-PICT. Two distinct models were built, one including VAS data at 1 week and another additionally including pain data at 1-month post-treatment. Variable importance analysis was performed for the 1-week model. Model performance was evaluated by using receiver operating characteristics (ROC) curves and the respective areas under the curve (AUC).
Results
The model exhibited an AUC of 69.2% for the prediction of complete pain resolution at 1 year. The addition of VAS scores at 1 month did not significantly alter the performance of the algorithm. Age and baseline VAS scores were the most important variables for classification performance.
Conclusion
The presented machine learning model exhibited an AUC of almost 70% in predicting complete pain resolution at 1 year. Pain data at 1 month do not appear to improve the performance of the algorithm.
Similar content being viewed by others
References
Speed CA, Hazleman BL. Calcific tendinitis of the shoulder. N Engl J Med. 1999;340:1582–4.
Louwerens JK, Sierevelt IN, van Hove RP, van den Bekerom MP, van Noort A. Prevalence of calcific deposits within the rotator cuff tendons in adults with and without subacromial pain syndrome: clinical and radiologic analysis of 1219 patients. J Shoulder Elbow Surg. 2015;24:1588–93.
Oliva F, Via AG, Maffulli N. Calcific tendinopathy of the rotator cuff tendons. Sport Med Arthrosc Rev. 2011;19:237–43.
Chianca V, Albano D, Messina C, et al. Rotator cuff calcific tendinopathy: from diagnosis to treatment. Acta Biomed. 2018;89:186–96.
Merolla G, Bhat MG, Paladini P, Porcellini G. Complications of calcific tendinitis of the shoulder: a concise review. J Orthop Traumatol. 2015;16:175–83.
Klontzas ME, Vassalou EE, Karantanas AH. Calcific tendinopathy of the shoulder with intraosseous extension: outcomes of ultrasound-guided percutaneous irrigation. Skeletal Radiol. 2017;46:201–8.
Lanza E, Banfi G, Serafini G, et al. Ultrasound-guided percutaneous irrigation in rotator cuff calcific tendinopathy: what is the evidence? A systematic review with proposals for future reporting. Eur Radiol. 2015;25:2176–83.
Messina C, Sconfienza LM. Ultrasound-guided percutaneous irrigation of calcific tendinopathy. Semin Musculoskelet Radiol. 2016;20:409–13.
Vassalou EE, Klontzas ME, Plagou AP, Karantanas AH. Ultrasound-guided percutaneous irrigation of calcific tendinopathy: redefining predictors of treatment outcome. Eur Radiol. 2021;31:2634–43.
Orlandi D, Mauri G, Lacelli F, et al. Rotator cuff calcific tendinopathy: randomized comparison of US-guided percutaneous treatments by using one or two needles. Radiology. 2017;285:518–27.
del Cura JL, Torre I, Zabala R, Legórburu A. Sonographically guided percutaneous needle lavage in calcific tendinitis of the shoulder: short- and long-term results. AJR Am J Roentgenol. 2007;189:W128–34.
Oudelaar BW, Huis In ‘t Veld R, Schepers-Bok R, Schepers-Bok R, Nelissen RGHH, Vochteloo AJH. Prognostic factors for the outcome of needle aspiration of calcific deposits for rotator cuff calcific tendinitis. Eur Radiol. 2020;30:4082–90.
Pasquotti G, Faccinetto A, Marchioro U, et al. US-guided percutaneous treatment and physical therapy in rotator cuff calcific tendinopathy of the shoulder: outcome at 3 and 12 months. Eur Radiol. 2016;26:2819–27.
Gyftopoulos S, Lin D, Knoll F, Doshi AM, Rodrigues TC, Recht MP. Artificial intelligence in musculoskeletal imaging: current status and future directions. AJR Am J Roentgenol. 2019;213:506–13.
Klontzas ME, Papadakis GZ, Marias K, Karantanas AH. Musculoskeletal trauma imaging in the era of novel molecular methods and artificial intelligence. Injury. 2020;51:2748–56.
Pesapane F, Codari M, Sardanelli F. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. Eur Radiol Exp. 2018;2:35.
Bentejac C, Csörgő A, Martínez-Muñoz G. A comparative analysis of XGboost, arXiv 2019;1911.01914
Chen T, Guestrin C, XGBoost: A scalable tree boosting system, arXiv 2016; 1603.02754
Wang Y, Ni XS. A XGBoost risk model via feature selection and Bayesian hyper-parameter optimization, arXiv 2019; 1901.08433
Bazzocchi A, Pelotti P, Serraino S, et al. Ultrasound imaging-guided percutaneous treatment of rotator cuff calcific tendinitis: success in short-term outcome. Br J Radiol. 2016;89:20150407.
Uhthoff HK, Loehr JW. Calcific tendinopathy of the rotator cuff: pathogenesis, diagnosis, and management. J Am Acad Orthop Surg. 1997;5:183–91.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
256_2021_3893_MOESM1_ESM.png
Supplementary figure 1 Receiver operating characteristics (ROC) curves and the respective area under the curve (AUC) for a logistic regression model built and trained with the inclusion of visual analogue scale (VAS) scores at 1 week (PNG 188 KB)
Rights and permissions
About this article
Cite this article
Vassalou, E.E., Klontzas, M.E., Marias, K. et al. Predicting long-term outcomes of ultrasound-guided percutaneous irrigation of calcific tendinopathy with the use of machine learning. Skeletal Radiol 51, 417–422 (2022). https://doi.org/10.1007/s00256-021-03893-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00256-021-03893-7