Using Machine Learning to Predict Nonachievement of Clinically Significant Outcomes After Rotator Cuff Repair.

Background: Although some evidence suggests that machine learning algorithms may outperform classical statistical methods in prognosis prediction for several orthopaedic surgeries, to our knowledge, no study has yet used machine learning to predict patient-reported outcome measures after rotator cuff repair. Purpose: To determine whether machine learning algorithms using preoperative data can predict the nonachievement of the minimal clinically important difference (MCID) of disability at 2 years after rotator cuff surgical repair with a similar performance to that of other machine learning studies in the orthopaedic surgery literature. Study Design: Case-control study; Level of evidence, 3. Methods: We evaluated 474 patients (n = 500 shoulders) with rotator cuff tears who underwent arthroscopic rotator cuff repair between January 2013 and April 2019. The study outcome was the difference between the preoperative and 24-month postoperative American Shoulder and Elbow Surgeons (ASES) score. A cutoff score was calculated based on the established MCID of 15.2 points to separate success (higher than the cutoff) from failure (lower than the cutoff). Routinely collected imaging, clinical, and demographic data were used to train 8 machine learning algorithms (random forest classifier; light gradient boosting machine [LightGBM]; decision tree classifier; extra trees classifier; logistic regression; extreme gradient boosting [XGBoost]; k-nearest neighbors [KNN] classifier; and CatBoost classifier). We used a random sample of 70% of patients to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC). Results: The AUCs for all algorithms ranged from 0.58 to 0.68. The random forest classifier and LightGBM presented the highest AUC values (0.68 [95% CI, 0.48-0.79] and 0.67 [95% CI, 0.43-0.75], respectively) of the 8 machine learning algorithms. Most of the machine learning algorithms outperformed logistic regression (AUC, 0.59 [95% CI, 0.48-0.81]); nonetheless, their performance was lower than that of other machine learning studies in the orthopaedic surgery literature. Conclusion: Machine learning algorithms demonstrated some ability to predict the nonachievement of the MCID on the ASES 2 years after rotator cuff repair surgery.

Rotator cuff repair in patients 50 years of age or younger: A comparative study of functional outcomes in relation to older patients.

BACKGROUND: Few studies have evaluated the clinical results of surgical treatment of rotator cuff tears in young patients and most of the publications are only case series and with a small number of evaluated individuals. The aim of this study is to compare the clinical outcomes of patients undergoing arthroscopic rotator cuff repair according to age at the time of the procedure. HYPOTHESIS: Patients with 50 years of age or younger undergoing surgical treatment of rotator cuff tear have similar clinical outcomes to older patients. MATERIALS AND METHODS: Retrospective cohort study comparing results obtained after surgical treatment of rotator cuff tears between patients aged 50 years or younger and the older patients by the ASES and UCLA functional scales. Patients undergoing arthroscopy full-thickness rotator cuff repair were included. RESULTS: We evaluated 390 shoulders (377 patients), 94 aged 50 years or younger (median=46.5 years) and 296 aged over 50 years (median=60 years). Both groups significantly improved with the procedure after 24 months of follow-up, according to the ASES and UCLA scales (p<0.001). The groups did not differ in the scores obtained in the preoperative assessments and at 24 months of follow-up. The score obtained on the ASES scale at 24 months of follow-up had a median of 87.2 (IQR=38) among patients aged 50 years or younger and 90 points (IQR=26.4) among older patients (p=0.253). The scores obtained by the UCLA scale were 31 points (IQR=9) and 33 points (IQR =7) respectively (p=0.156). DISCUSSION: Our results showed that, after 24 months, the functional results of arthroscopic full-thickness rotator cuff repair did not differ between patients younger than 50 years and older patients. These results are similar to those found by other authors. Both groups of patients achieved significant improvement after the surgical procedure, achieving approximately 90 points on the ASES scale and 32 points on the UCLA scale. LEVEL OF EVIDENCE: III Retrospective cohort study.

Intramedullary Steinmann pin nailing of the ulna: an option for the damage control orthopedics treatment of forearm fractures in open injuries in polytraumatized patients - A description of the technique and presentation of a case series.

INTRODUCTION: Forearm shaft fracture is common in young adult patients and associated with soft tissue and organ injuries. In open fractures in polytrauma patients, damage control orthopaedics (DCO) is well indicated. The aim of this study is to describe intramedullary Steinmann pin fixation of the ulna as a DCO procedure for the forearm and present a case series. DESCRIPTION OF THE TECHNIQUE: A 3.0 mm Steinmann pin is inserted retrograde in the ulna proximal fragment through the fracture site using the open wound as the approach. With direct visualization of the reduction, the pin is advanced into the distal fragment. The reduction of the longitudinal axis and shortening is thus achieved. PATIENTS AND METHODS: This method was used for all open fractures of forearm both-bone fractures in polytrauma patients undergoing DCO from 2014 to 2019. The alignment and length of the ulna were evaluated radiographically after pin fixation and before and after definitive fixation. Differences in the need for secondary procedures and infection rate between DCO and definitive fixation were also evaluated. RESULTS: There were 30 males (85.7%) with an average age of 32.9 ± 12.0 years and a mean ISS (Injury Severity Score) of 29.4 (range, 18.0-41.0). The most common associated injuries were thoracic trauma (62.8%) and head trauma (45.7%). In the radius and ulna, 51.4% and 60.0% of fractures, respectively, were multifragmentary (types B and C). Gustilo type IIIA represented 77.1% of the injuries. Pin fixation achieved good alignment and length in all cases. The mean time between DCO and definitive fixation was 12.0 days, and no secondary procedure was needed, nor any case developed either superficial or deep infection. The conversion from DCO to definitive fixation was considered easy in all cases. CONCLUSION: Intramedullary Steinmann pin fixation of the ulna is a viable option for DCO for forearm both-bone fractures in open fractures in polytrauma patients.

Bioactive glass S53P4 to fill-up large cavitary bone defect after acute and chronic osteomyelitis treated with antibiotic-loaded cement beads: A prospective case series with a minimum 2-year follow-up.

INTRODUCTION: Bioactive glass S53P4 (BAG-S53P4) has been used in the treatment of osteomyelitis with excellent results. The aim of this study was to evaluate the clinical and radiographic results of patients treated with use of antibiotic-loaded cement beads, followed by bone defects filling using bioglass. METHODS: We treated a prospective series of patients presenting with acute or chronic osteomyelitis of a long bone of the upper or lower limb. The first-stage procedure involved debridement and filling of cavitary defects with antibiotic-loaded polymethylmethacrylate (PMMA) beads. When signs of infection subsided, the defects were filled with BAG-S53P4. The main outcomes assessed were the reinfection rate, need for reoperation, radiographic and functional evaluations (DASH and Lysholm scores). RESULTS: Ten patients were included, aged between 4 and 66 years (mean 25.4 years). The source of infection was hematogenic in five cases and post-traumatic in the other five. Hematogenic infections required two debridements before filling with bioglass, whereas post-traumatic cases required only one. The time between the first debridement and the application of bioglass varied from 1 to 63 weeks (average of 17 weeks). All patients showed a favorable evolution after bioglass procedure, with no need for reoperation or relevant wound problems. The radiographic evaluation showed partial incorporation of the material and adequate bone formation, and functional scores were satisfactory in all cases. CONCLUSION: The treatment of osteomyelitis with surgical debridement and PMMA beads, followed by filling of bone defect with BAG-S53P4, was effective in all patients evaluated, with adequate infectious control and bone regeneration. No cases required reoperation after bioglass implantation. Patients with hematogenous osteomyelitis required a greater number of debridements before filling with bioglass.