ABSTRACT
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.
ABSTRACT
PURPOSE: Unicompartmental Knee Arthroplasty (UKA) recorded an increased incidence of around 30% per year in the United States. Patient's experience and satisfaction after surgery were traditionally assessed by pre, and post-surgical scores and Patient-Reported Outcome Measures (PROMs) scales. Traditional scales as Western Ontario and McMaster University Osteoarthritis Index (WOMAC) and Oxford Knee Score (OKS) reported high ceiling effect. Patients treated by UKA usually perform well; therefore, it is necessary to have a PROMs' scale with a low ceiling effect as the Forgotten Joint Score-12 (FJS-12). PROMs have to be validated in the local language to be used. This study aims to perform a psychometric validation of the Italian version of FJS-12 for UKA for the first time. METHODS: Between January 2019 and October 2019, 44 patients were included. Each patient completed both the FJS-12 Italian version and the WOMAC Italian version in preoperative follow-up, after 2-week and 1-month, 3-month, and 6-month postoperative follow-up. Cronbach's α, intraclass correlation coefficient (ICC), standard error of measurement (SEM), and minimal detectable change (MDC) were calculated to evaluate the reliability. The Pearson coefficient was used to assess validity. The Effect Size (ES) was used to test the responsiveness. RESULTS: A range of Cronbach's α between 0.90 and 0.95 indicated good internal consistency for the FJS-12. The test-retest reliability was acceptable (i.e., the ICC was higher than 0.7) at each follow-up. The Pearson correlation coefficient between the FJS-12 and WOMAC was - 0.11 (n.s.) at preoperative follow-up, r = 0.47 (P = 0.001) at 1 month, r = 0.57 (P < 0.001) at 3 months, and r = 0.57 (P < 0.001) at 6 months. Therefore, except for the preoperative period, the validity of the FJS-12 score was assessed. CONCLUSION: The FJS-12 represents a valid and reliable tool with a low ceiling effect to assess the outcomes improvement in UKA patients. Therefore, validating and translating this score in different languages could help perform more accurate studies on outcomes after UKA. LEVEL OF EVIDENCE: Level III, diagnostic study.
Subject(s)
Arthroplasty, Replacement, Knee , Knee Prosthesis , Osteoarthritis, Knee , Humans , Knee Joint/surgery , Language , Osteoarthritis, Knee/diagnosis , Osteoarthritis, Knee/surgery , Prostheses and Implants , Reproducibility of Results , Surveys and Questionnaires , Treatment OutcomeABSTRACT
The Forgotten Joint Score-12 (FJS-12) is a valid patient-reported outcome measures (PROMs) used to assess prosthesis awareness during daily activities after total hip arthroplasty (THA). The minimum clinically important difference (MCID) can be defined as the smallest change or difference that is evaluated as beneficial and could change the patient's clinical management. The patient acceptable symptom state (PASS) is considered the minimum PROMs cut-off value that corresponds to a patient's satisfactory state of health. Despite the validity and reliability of the FJS-12 having been already demonstrated, the MCID and the PASS of this score have not previously been defined. Patients undergoing THA from January 2019 to October 2019 were assessed pre-operatively and six months post-surgery using the FJS-12, the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) and the Oxford Hip Score (OHS). Pre-operative and follow-up questionnaires were completed by 50 patients. Both distribution-based approaches and anchor approaches were used to estimate MCID. The aim of this paper was to assess the MCID and PASS values of FJS-12 after total hip replacement. The FJS-12 MCID from baseline to 6 months post-operative follow-up was 17.5. The PASS calculated ranged from 69.8 to 91.7.
Subject(s)
Arthroplasty, Replacement, Hip , Humans , Minimal Clinically Important Difference , Patient Reported Outcome Measures , Reproducibility of Results , Surveys and Questionnaires , Treatment OutcomeABSTRACT
Purpose: Nowadays, surgical treatment of acute avulsions of the Achilles tendon represents a hard challenge. There is often the possibility that the calcaneus remains completely uncovered from the tendon, making the reinsertion of its distal stub complex. At the same time, the standard open surgical technique could cause difficult wound healing because of the weak blood supply, the increasing possibility of rupture, and the bacterial contamination. To overcome these risks, less invasive procedures should be considered. Methods: We developed an innovative minimally invasive procedure for fixation of acute avulsions of the Achilles tendon employing an integration of four longitudinal stab incisions and one distal semicircular Cincinnati incision. In this way, the distal Achilles tendon stub and the calcaneal insertion are exhibited. Results: We basted the tendon through percutaneous sutures performed across the four stab incisions with a Mayo needle threaded with Ultrabraid. The procedure is repeated with another loop of Ultrabraid. After having bruised the calcaneus bone insertion of the tendon, two sites for two suture anchors were prepared using a specific hole preparation device for the anchors' footprint. Finally, we placed two suture anchors to reinsert the tendon to the calcaneal insertion. Conclusion: Our new less invasive technique is a promising alternative optional procedure for the Achilles tendon (AT) avulsion repair allowing clear exposure of the Achilles tendon insertion, maintaining the longitudinal wholeness of the dermis, and minimizing possible associated complications.
Subject(s)
Achilles Tendon , Calcaneus , Tendon Injuries , Achilles Tendon/surgery , Humans , Rupture/surgery , Suture Techniques , Tendon Injuries/surgeryABSTRACT
Background and objectives: Our research aimed to evaluate the quality of reporting of randomized controlled trials (RCTs) linked to rotator cuff (RC) tears. The present study analyzed factors connected to the quality of the RCTs and trends in the quality of reporting through time. Materials and Methods: The online databases used to search all RCTs on the topic of RC surgery completed until March 2020 were PubMed and Ovid (MEDLINE). The quality of reporting was evaluated using the modified Coleman methodology score (MCMS) and the consolidated standards of reporting trials (CONSORT). Results: The online search found 957 articles. Finally, 183 studies were included in the quantitative synthesis. A total of 97 (53%) of 183 studies had a level of evidence I and 86 (47%) of 183 studies had a level of evidence II, according to the Oxford Center of Evidence Based Medicine (EBM). A statistically significant difference in MCMS between articles written before 2010 and articles written after 2010 was found. Articles written after 2010 had, on average, the highest Coleman score. The average number of CONSORT checklist items for each article across all analyzed RCTs was 21.67. The 37 studies completed up to 2010 averaged a number of checklist items of 19.97 and the studies completed between 2011 and 2019 averaged a number of checklist items of 22.10. A statistically significant difference in the number of checklist items between articles written before 2010 and articles written after 2010 was found. Articles written after 2010 had on average more checklist items. However, low correlation (0.26) between the number of checklist items for each article and the respective Coleman score was found. On the other hand, articles with the CONSORT diagram had a significantly high Coleman score. Conclusions: An improvement in the quantity and quality of RCTs relating to RC surgery over the analyzed period was found.