Evangelia E Vassalou1,2, Michail E Klontzas1,3,4,5, Kostas Marias4,6, Apostolos H Karantanas7,8,9. 1. Department of Medical Imaging, University Hospital, Heraklion, 71110, Voutes, Crete, Greece. 2. Department of Medical Imaging, General Hospital of Sitia, 72300, Xerokamares, Crete, Greece. 3. Advanced Hybrid Imaging Systems, Institute of Computer Science, Foundation for Research and Technology (FORTH), N. Plastira 100, 70013, Heraklion, Crete, Greece. 4. Computational Biomedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology (FORTH), N. Plastira 100, 70013, Heraklion, Crete, Greece. 5. Department of Radiology, School of Medicine, University of Crete, Voutes Campus, 71110, Heraklion, Greece. 6. Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Estavromenos, 71410, Heraklion, Crete, Greece. 7. Department of Medical Imaging, University Hospital, Heraklion, 71110, Voutes, Crete, Greece. akarantanas@gmail.com. 8. Advanced Hybrid Imaging Systems, Institute of Computer Science, Foundation for Research and Technology (FORTH), N. Plastira 100, 70013, Heraklion, Crete, Greece. akarantanas@gmail.com. 9. Department of Radiology, School of Medicine, University of Crete, Voutes Campus, 71110, Heraklion, Greece. akarantanas@gmail.com.
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.
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.
Authors: Vito Chianca; Domenico Albano; Carmelo Messina; Federico Midiri; Giovanni Mauri; Alberto Aliprandi; Michele Catapano; Lorenzo Carlo Pescatori; Cristian Giuseppe Monaco; Salvatore Gitto; Anna Pisani Mainini; Angelo Corazza; Santi Rapisarda; Grazia Pozzi; Antonio Barile; Carlo Masciocchi; Luca Maria Sconfienza Journal: Acta Biomed Date: 2018-01-19