Application of Machine Learning Algorithms for Prognostic Assessment in Rotator Cuff Pathologies: A Clinical Data-Based Approach.

AIM: The overall aim of this proposal is to ameliorate the care of rotator cuff (RC) tear patients by applying an innovative machine learning approach for outcome prediction after arthroscopic repair. MATERIALS AND METHODS: We applied state-of-the-art machine learning algorithms to evaluate the best predictors of the outcome, and 100 RC patients were evaluated at baseline (T0), after 1 month (T1), 3 months (T2), 6 months (T3), and 1 year (T4) from surgical intervention. The outcome measure was the Costant-Murley Shoulder Score, whereas age, sex, BMI, the 36-Item Short-Form Survey, the Simple Shoulder Test, the Hospital Anxiety and Depression Scale, the American Shoulder and Elbow Surgeons Score, the Oxford Shoulder Score, and the Shoulder Pain and Disability Index were considered as predictive factors. Support vector machine (SVM), k-nearest neighbors (k-NN), naïve Bayes (NB), and random forest (RF) algorithms were employed. RESULTS: Across all sessions, the classifiers demonstrated suboptimal performance when using both the complete and shrunken sets of features. Specifically, the logistic regression (LR) classifier achieved a mean accuracy of 46.5% ± 6%, while the random forest (RF) classifier achieved 51.25% ± 4%. For the shrunken set of features, LR obtained a mean accuracy of 48.5% ± 6%, and RF achieved 45.5% ± 4.5%. No statistical differences were found when comparing the performance metrics of ML algorithms. CONCLUSIONS: This study underlines the importance of extending the application of AI methods to new predictors, such as neuroimaging and kinematic data, in order to better record significant shifts in RC patients' prognosis. LIMITATIONS: The data quality within the cohort could represent a limitation, since certain variables, such as smoking, diabetes, and work injury, are known to have an impact on the outcome.

Minimal Clinically Important Difference (MCID), Substantial Clinical Benefit (SCB), and Patient Acceptable Symptom State (PASS) of the Shoulder Disability Questionnaire (SDQ) in Patients Undergoing Rotator Cuff Repair.

The Shoulder Disability Questionnaire (SDQ) is a Patient-Reported Outcome Measure (PROM) applied to evaluate shoulder surgery outcomes. The purpose of this study is to identify the accurate Minimal Clinically Important Difference (MCID), Substantial Clinical Benefit (SCB) and Patient Acceptable Symptom State (PASS) values for the SDQ score. A total of 35 patients (21 women and 16 men, mean age 76.6 ± 3.2 years) were followed up at 6 months postoperatively. To assess the patient's health satisfaction and symptoms, anchor questions were used. The MCID and SCB values of the SDQ score for patients who underwent arthroscopic rotator cuff repair from inception to final follow-up were 40.8 and 55.6, respectively. A change of 40.8 in the SDQ score at 6 months after surgery shows that patients achieved a minimum clinically important improvement in their state of health, and a 55.6 change in the SDQ score reflects a substantial clinically important improvement. The PASS cut-off of the SDQ score at 6 months postoperatively ranged from 22.5 to 25.8. If an SDQ score of 22.5 or more is attained after surgery, the health condition can be recognized as acceptable by the majority of patients. These cut-offs will help with understanding specific patient results and allow clinicians to personally assess patient improvement after rotator cuff repair.

Instability Severity Index Score Does Not Predict the Risk of Shoulder Dislocation after a First Episode Treated Conservatively.

The first purpose of this study was to verify the association between Instability Severity Index Score (ISIS) and Recurrent Shoulder Dislocation (RSD) after a first episode treated conservatively. The second aim is to identify the risk factors associated with RSD after a primary acute shoulder anterior dislocation treated conservatively. A total of 111 patients with first traumatic anterior shoulder dislocation treated at a single trauma centre between January 2014 and March 2016 were enrolled. The main predictive variables of risk factors and the ISIS score were calculated. Among the 85 patients included, 26 cases of RSD were observed (30.6%). Considering the whole population, no significant association between ISIS and RSD were reported. Regarding other risk factors, high-risk working activities and rotator cuff injury had a significantly higher RSD risk. Sex, dominant limb, familiar history, hyperlaxity, contact or overhead sports, competitive sport, post-reduction physiokinesitherapy, return to sports activity time, Hill-Sachs lesion, bony Bankart lesion and great tuberosity fracture did not seem to influence the risk of RSD. No correlation between ISIS score and RSD in patients treated conservatively after a first episode of shoulder dislocation were reported. The only risk factors with a significant association to RSD were high-risk working activities and rotator cuff injury.

Unicompartmental Knee Arthroplasty: Minimal Important Difference and Patient Acceptable Symptom State for the Forgotten Joint Score.

Background and Objectives: Unicompartmental knee arthroplasty (UKA) is a valid alternative to total knee arthroplasties (TKAs) in selected cases. After surgery, patients' experience and satisfaction were traditionally evaluated by pre- and postsurgical scores and Patient-Reported Outcome Measures (PROMs). Otherwise, a statistically significant change does not necessarily correlate to a clinically meaningful improvement when measured using PROMs. To evaluate the real effect of a specific treatment and understand the difference between groups in a clinical trial, it is necessary to use a meaningful quantum of change on the score assessed. The minimal clinically important difference (MCID) and the Patient Acceptable Symptom State (PASS) can provide this meaningful change. This paper aimed to calculate the MCID and the PASS of the Forgotten Joint Score (FJS-12) after UKA. Materials and Methods: A total of 40 patients with a mean age 72.5 ± 6.4 years undergoing UKA were assessed preoperatively and six months postsurgery using the FJS-12 and the Oxford Knee Score (OKS). The baseline and 6-month postoperative scores were compared using the Wilcoxon signed ranks test. The correlation was calculated with Spearman's rho. Both distribution-based approaches and anchor approaches were used to estimate MCID for the FJS-12. The 75th percentile and the Receiver operating characteristic (ROC) curve methods were used to calculate the PASS of FJS-12. Results: MCID estimates for normalized FJS-12 for UKA ranged from 5.68 to 19.82. The threshold of the FJS-12 with ROC method was 72.92 (AUC = 0.76). The cut-off value computed with the 75th percentile approach was 92.71. Conclusions: The MCID and PASS represent valid tools to assess the real perception of clinical improvement in patients who underwent UKA. The MCID value of FJS-12 was 12.5 for patients who underwent UKA. The value of the PASS for the FJS-12 in patients who underwent UKA was 72.92.

Posterior shoulder instability: a systematic review.

INTRODUCTION: This review aims to provide information on outcomes of surgical procedures for soft tissue or bony glenoid and/or humeral abnormalities in case of posterior shoulder instability. SOURCE OF DATA: A systematic review of the literature according to the PRISMA guidelines was performed. A comprehensive search of PubMed, Medline, CINAHL, Cochrane, Embase, Ovid and Google Scholar databases using various combinations of the keywords 'shoulder', 'posterior instability', 'dislocation', 'reversed bony bankart', 'reversed Hill Sachs', and 'capsulolabral' was performed. AREAS OF AGREEMENT: A total of 847 shoulders in 810 patients were included. A redislocation event occurred in 33 (8.7%) of 411 shoulders with soft tissue abnormalities and in 12 (9.1%) of 132 shoulders with bony abnormalities of the glenoid, humeral head or both. AREAS OF CONTROVERSY: The optimal treatment modalities for posterior shoulder dislocation remain to be defined. GROWING POINTS: Operative stabilization for posterior shoulder instability should be lesion-specific and should correct all components of the posterior instability. AREAS TIMELY FOR DEVELOPING RESEARCH: Future prospective studies should aim to establish the optimal treatment modalities for posterior shoulder instability.