Lateral elbow tendinopathy and artificial intelligence: Binary and multilabel findings detection using machine learning algorithms.

Background: Ultrasound (US) is a valuable technique to detect degenerative findings and intrasubstance tears in lateral elbow tendinopathy (LET). Machine learning methods allow supporting this radiological diagnosis. Aim: To assess multilabel classification models using machine learning models to detect degenerative findings and intrasubstance tears in US images with LET diagnosis. Materials and methods: A retrospective study was performed. US images and medical records from patients with LET diagnosis from January 1st, 2017, to December 30th, 2018, were selected. Datasets were built for training and testing models. For image analysis, features extraction, texture characteristics, intensity distribution, pixel-pixel co-occurrence patterns, and scales granularity were implemented. Six different supervised learning models were implemented for binary and multilabel classification. All models were trained to classify four tendon findings (hypoechogenicity, neovascularity, enthesopathy, and intrasubstance tear). Accuracy indicators and their confidence intervals (CI) were obtained for all models following a K-fold-repeated-cross-validation method. To measure multilabel prediction, multilabel accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) with 95% CI were used. Results: A total of 30,007 US images (4,324 exams, 2,917 patients) were included in the analysis. The RF model presented the highest mean values in the area under the curve (AUC), sensitivity, and also specificity by each degenerative finding in the binary classification. The AUC and sensitivity showed the best performance in intrasubstance tear with 0.991 [95% CI, 099, 0.99], and 0.775 [95% CI, 0.77, 0.77], respectively. Instead, specificity showed upper values in hypoechogenicity with 0.821 [95% CI, 0.82, -0.82]. In the multilabel classifier, RF also presented the highest performance. The accuracy was 0.772 [95% CI, 0.771, 0.773], a great macro of 0.948 [95% CI, 0.94, 0.94], and a micro of 0.962 [95% CI, 0.96, 0.96] AUC scores were detected. Diagnostic accuracy, sensitivity, and specificity with 95% CI were calculated. Conclusion: Machine learning algorithms based on US images with LET presented high diagnosis accuracy. Mainly the random forest model shows the best performance in binary and multilabel classifiers, particularly for intrasubstance tears.

A New Test for the Advanced Diagnosis of Lateral Elbow Tendinopathy with Concomitant Intrasubstance Tear: Failure to Resist Extension Effort (the Free Test).

Background: Lateral elbow tendinopathy (LET) is one of the most common causes of musculoskeletal pain. The diagnosis is based on the clinical history and different physical maneuvers. Ultrasound (US) is a complementary diagnostic method to detect degenerative tendon changes and intrasubstance tears (IST). To date, there is no available physical maneuver to identify an IST in patients with LET. Aim: To evaluate the diagnostic accuracy of an index test to detect an IST confirmed by ultrasound in patients with LET. Methods: A diagnostic retrospective study was performed. Patients who presented medical records with LET were recruited. Two orthopaedic surgeons developed the physical maneuver. The index test was considered positive when the position failed to resist the wrist extension maximum effort. Clinical findings were associated with confirmation of IST by US. Data were calculated using diagnostic accuracy, sensitivity, and specificity with 95% confidence intervals. Results: Thirty-nine patients (39 elbows) were analyzed, 25 (64%) women and 14 (36%) men, with an average age of 47.7 years. The index test's sensitivity was 0.86 (95% CI, 0.67-0.96). Accuracy was 0.79 (95% CI, 0.64-0.91), and the specificity was 0.64 (95% CI, 0.31-0.89). Conclusion: The index test presented very good sensitivity and good accuracy in patients with LET with US diagnostic confirmation of IST. Level of Evidence: Diagnostic study, Level III.

Ultrasound-Guided Hydraulic Release Associated With Corticosteroids in Radial Tunnel Syndrome: Description of Technique and Preliminary Clinical Results.

The aim of this study was to describe a perineural ultrasound-guided infiltration technique for management of radial tunnel syndrome and to report its preliminary results in 54 patients. A mixture of a saline solution, a local anesthetic, and a corticosteroid solution was infiltrated in the perineural region at the arcade of Frohse. Pain was reported in 100% of patients before the procedure versus 1.9% after the procedure. Scratch collapse and Cozen test results were positive in 98.1% and 66.7% of patients before infiltration, respectively, versus 5.6% and 9.2% after infiltration. All variables had statistically significant differences between preprocedure and postprocedure evaluations (P < .01).