Machine learning can accurately predict risk factors for all-cause reoperation after ACLR: creating a clinical tool to improve patient counseling and outcomes.

PURPOSE: Identifying predictive factors for all-cause reoperation after anterior cruciate ligament reconstruction could inform clinical decision making and improve risk mitigation. The primary purposes of this study are to (1) determine the incidence of all-cause reoperation after anterior cruciate ligament reconstruction, (2) identify predictors of reoperation after anterior cruciate ligament reconstruction using machine learning methodology, and (3) compare the predictive capacity of the machine learning methods to that of traditional logistic regression. METHODS: A longitudinal geographical database was utilized to identify patients with a diagnosis of new anterior cruciate ligament injury. Eight machine learning models were appraised on their ability to predict all-cause reoperation after anterior cruciate ligament reconstruction. Model performance was evaluated via area under the receiver operating characteristics curve. To explore modeling interpretability and radiomic feature influence on the predictions, we utilized a game-theory-based method through SHapley Additive exPlanations. RESULTS: A total of 1400 patients underwent anterior cruciate ligament reconstruction with a mean postoperative follow-up of 9 years. Two-hundred and eighteen (16%) patients experienced a reoperation after anterior cruciate ligament reconstruction, of which 6% of these were revision ACL reconstruction. SHapley Additive exPlanations plots identified the following risk factors as predictive for all-cause reoperation: diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. XGBoost was the best-performing model (area under the receiver operating characteristics curve of 0.77) and outperformed logistic regression in this regard. CONCLUSIONS: All-cause reoperation after anterior cruciate ligament reconstruction occurred at a rate of 16%. Machine learning models outperformed traditional statistics and identified diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair as predictive risk factors for reoperation. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. These models will allow surgeons to tabulate individualized risk for future reoperation for patients undergoing anterior cruciate ligament reconstruction. LEVEL OF EVIDENCE: III.

A Deep Learning Tool for Automated Landmark Annotation on Hip and Pelvis Radiographs.

BACKGROUND: Automatic methods for labeling and segmenting pelvis structures can improve the efficiency of clinical and research workflows and reduce the variability introduced with manual labeling. The purpose of this study was to develop a single deep learning model to annotate certain anatomical structures and landmarks on antero-posterior (AP) pelvis radiographs. METHODS: A total of 1,100 AP pelvis radiographs were manually annotated by 3 reviewers. These images included a mix of preoperative and postoperative images as well as a mix of AP pelvis and hip images. A convolutional neural network was trained to segment 22 different structures (7 points, 6 lines, and 9 shapes). Dice score, which measures overlap between model output and ground truth, was calculated for the shapes and lines structures. Euclidean distance error was calculated for point structures. RESULTS: Dice score averaged across all images in the test set was 0.88 and 0.80 for the shape and line structures, respectively. For the 7-point structures, average distance between real and automated annotations ranged from 1.9 mm to 5.6 mm, with all averages falling below 3.1 mm except for the structure labeling the center of the sacrococcygeal junction, where performance was low for both human and machine-produced labels. Blinded qualitative evaluation of human and machine produced segmentations did not reveal any drastic decrease in performance of the automatic method. CONCLUSION: We present a deep learning model for automated annotation of pelvis radiographs that flexibly handles a variety of views, contrasts, and operative statuses for 22 structures and landmarks.

Frank Stinchfield Award: Creation of a Patient-Specific Total Hip Arthroplasty Periprosthetic Fracture Risk Calculator.

BACKGROUND: Many risk factors have been described for periprosthetic femur fracture (PPFFx) following total hip arthroplasty (THA), yet a patient-specific risk assessment tool remains elusive. The purpose of this study was to develop a high-dimensional, patient-specific risk-stratification nomogram that allows dynamic risk modification based on operative decisions. METHODS: We evaluated 16,696 primary nononcologic THAs performed between 1998 and 2018. During a mean 6-year follow-up, 558 patients (3.3%) sustained a PPFFx. Patients were characterized by individual natural language processing-assisted chart review on nonmodifiable factors (demographics, THA indication, and comorbidities), and modifiable operative decisions (femoral fixation [cemented/uncemented], surgical approach [direct anterior, lateral, and posterior], and implant type [collared/collarless]). Multivariable Cox regression models and nomograms were developed with PPFFx as a binary outcome at 90 days, 1 year, and 5 years, postoperatively. RESULTS: Patient-specific PPFFx risk based on comorbid profile was wide-ranging from 0.4-18% at 90 days, 0.4%-20% at 1 year, and 0.5%-25% at 5 years. Among 18 evaluated patient factors, 7 were retained in multivariable analyses. The 4 significant nonmodifiable factors included the following: women (hazard ratio (HR) = 1.6), older age (HR = 1.2 per 10 years), diagnosis of osteoporosis or use of osteoporosis medications (HR = 1.7), and indication for surgery other than osteoarthritis (HR = 2.2 for fracture, HR = 1.8 for inflammatory arthritis, HR = 1.7 for osteonecrosis). The 3 modifiable surgical factors were included as follows: uncemented femoral fixation (HR = 2.5), collarless femoral implants (HR = 1.3), and surgical approach other than direct anterior (lateral HR = 2.9, posterior HR = 1.9). CONCLUSION: This patient-specific PPFFx risk calculator demonstrated a wide-ranging risk based on comorbid profile and enables surgeons to quantify risk mitigation based on operative decisions. LEVEL OF EVIDENCE: Level III, Prognostic.

Shoulder arthroplasty after prior external beam radiation therapy: a matched cohort analysis.

BACKGROUND: External beam radiation therapy (XRT) is a commonly used therapeutic modality for the treatment of various chest wall and axillary malignancies. Despite the known risk of local soft tissue dysfunction, and possibly compromised bone ingrowth for cementless implants, there remains limited data on the impact of prior XRT in a shoulder arthroplasty (SA) cohort. This study evaluated the outcomes of primary SA in patients with prior XRT compared to a matched cohort (MC). METHODS: Over a 27-year time period (1993-2020), 80 primary SAs (7 hemiarthroplasties [HAs], 29 anatomic total shoulder arthroplasties [aTSAs], and 44 reverse shoulder arthroplasties [rTSAs]) with previous XRT to the upper chest or axillary region and a minimum of 2-year follow-up were included. This cohort was matched (1:2) according to age, sex, body mass index (BMI), implant, and year of surgery with patients who had undergone HA or TSA for osteoarthritis or RSA for cuff tear arthropathy. Clinical outcomes including pain, active shoulder range of motion (ROM), strength, complications, and reoperations inclusive of revision surgery were assessed. RESULTS: The XRT cohort consisted of 71 (88.8%) women with a mean age of 70.9 (range, 43-87) years, BMI of 30.9 ± 7.6, and follow-up period of 6.6 years (range, 2.0-28.2). In these patients, SA led to substantial improvements in pain, ROM, and strength across the entire cohort. When compared to the MC, the XRT group demonstrated a lower final postoperative forward elevation (FE) (111° vs. 126°; P = .013) and less improvements in pain (5.3 vs. 6.2; P = .002), FE (34° vs. 54°; P = .002), and external rotation (13° vs. 24°; P < .001). There were 14 (17.5%) complications and 7 reoperations in the XRT group, with rotator cuff failure after HA or TSA (n = 4 of 36; 11.1%) as the most common complication and no instances of loose humeral components. The XRT group had a higher rate of complications (17.5% vs. 8.1%; P = .03) but not reoperations (8.8% vs. 3.1%; P = .059). When evaluated by implant, rTSA demonstrated the lowest rate of reoperations followed by aTSA and HA (2.3% vs. 10.3% vs. 42.9%; P = .002). CONCLUSIONS: Primary SA is an effective treatment modality for the improvement of pain, motion, and strength in patients with a history of prior XRT. However, when compared to patients without prior XRT, less clinical improvement and a higher rate of postoperative complications were observed.

Patient-specific Hip Arthroplasty Dislocation Risk Calculator: An Explainable Multimodal Machine Learning-based Approach.

Purpose: To develop a multimodal machine learning-based pipeline to predict patient-specific risk of dislocation following primary total hip arthroplasty (THA). Materials and Methods: This study retrospectively evaluated 17 073 patients who underwent primary THA between 1998 and 2018. A test set of 1718 patients was held out. A hybrid network of EfficientNet-B4 and Swin-B transformer was developed to classify patients according to 5-year dislocation outcomes from preoperative anteroposterior pelvic radiographs and clinical characteristics (demographics, comorbidities, and surgical characteristics). The most informative imaging features, extracted by the mentioned model, were selected and concatenated with clinical features. A collection of these features was then used to train a multimodal survival XGBoost model to predict the individualized hazard of dislocation within 5 years. C index was used to evaluate the multimodal survival model on the test set and compare it with another clinical-only model trained only on clinical data. Shapley additive explanation values were used for model explanation. Results: The study sample had a median age of 65 years (IQR: 18 years; 52.1% [8889] women) with a 5-year dislocation incidence of 2%. On the holdout test set, the clinical-only model achieved a C index of 0.64 (95% CI: 0.60, 0.68). The addition of imaging features boosted multimodal model performance to a C index of 0.74 (95% CI: 0.69, 0.78; P = .02). Conclusion: Due to its discrimination ability and explainability, this risk calculator can be a potential powerful dislocation risk stratification and THA planning tool.Keywords: Conventional Radiography, Surgery, Skeletal-Appendicular, Hip, Outcomes Analysis, Supervised Learning, Convolutional Neural Network (CNN), Gradient Boosting Machines (GBM) Supplemental material is available for this article. © RSNA, 2022.

Applying Deep Learning to Establish a Total Hip Arthroplasty Radiography Registry: A Stepwise Approach.

BACKGROUND: Establishing imaging registries for large patient cohorts is challenging because manual labeling is tedious and relying solely on DICOM (digital imaging and communications in medicine) metadata can result in errors. We endeavored to establish an automated hip and pelvic radiography registry of total hip arthroplasty (THA) patients by utilizing deep-learning pipelines. The aims of the study were (1) to utilize these automated pipelines to identify all pelvic and hip radiographs with appropriate annotation of laterality and presence or absence of implants, and (2) to automatically measure acetabular component inclination and version for THA images. METHODS: We retrospectively retrieved 846,988 hip and pelvic radiography DICOM files from 20,378 patients who underwent primary or revision THA performed at our institution from 2000 to 2020. Metadata for the files were screened followed by extraction of imaging data. Two deep-learning algorithms (an EfficientNetB3 classifier and a YOLOv5 object detector) were developed to automatically determine the radiographic appearance of all files. Additional deep-learning algorithms were utilized to automatically measure the acetabular angles on anteroposterior pelvic and lateral hip radiographs. Algorithm performance was compared with that of human annotators on a random test sample of 5,000 radiographs. RESULTS: Deep-learning algorithms enabled appropriate exclusion of 209,332 DICOM files (24.7%) as misclassified non-hip/pelvic radiographs or having corrupted pixel data. The final registry was automatically curated and annotated in <8 hours and included 168,551 anteroposterior pelvic, 176,890 anteroposterior hip, 174,637 lateral hip, and 117,578 oblique hip radiographs. The algorithms achieved 99.9% accuracy, 99.6% precision, 99.5% recall, and a 99.6% F1 score in determining the radiograph appearance. CONCLUSIONS: We developed a highly accurate series of deep-learning algorithms to rapidly curate and annotate THA patient radiographs. This efficient pipeline can be utilized by other institutions or registries to construct radiography databases for patient care, longitudinal surveillance, and large-scale research. The stepwise approach for establishing a radiography registry can further be utilized as a workflow guide for other anatomic areas. LEVEL OF EVIDENCE: Diagnostic Level IV . See Instructions for Authors for a complete description of levels of evidence.

Cost comparison and complication profiles of superior capsular reconstruction, lower trapezius transfer, and reverse shoulder arthroplasty for irreparable rotator cuff tears.

BACKGROUND: Irreparable rotator cuff tears (IRCTs) pose treatment challenges both clinically and financially. As cost-effectiveness initiatives are prioritized, value-based health care delivery models are becoming increasingly common. The purpose of this study was to perform a comprehensive analysis of the cost, complications, and readmission rates of 3 common surgical treatment options for IRCTs: superior capsular reconstruction (SCR), arthroscopically assisted lower trapezius tendon transfer (LTTT), and reverse shoulder arthroplasty (RSA). METHODS: Between 2018 and 2020, 155 patients who underwent shoulder surgery at a single institution for IRCT with minimal to no arthritis were identified. Procedures performed included 20 SCRs, 47 LTTTs, and 88 RSAs. A cost analysis was designed to include a period of 60 days preoperatively, the index surgical hospitalization, and 90 days postoperatively, including costs of any readmission or reoperation. RESULTS: Mean standardized costs were as follows: preoperative evaluation SCR $507, LTTT $507, and RSA $730; index surgical hospitalization SCR $19,675, LTTT $15,722, and RSA $16,077; and postoperative care SCR $655, LTTT $686, and RSA $404. Significant differences were observed in the index surgical costs (P < .001), with SCR incurring an additional average cost of $3953 and $3598 compared with LTTT and RSA, respectively. The 90-day complication, reoperation, and readmission rates were 0%, 0%, and 0% in the SCR group; 2.1%, 0%, and 0% in the LTTT group; and 3.4%, 0%, and 1.1% in the RSA group, respectively. With the numbers available, differences among the 3 surgical procedures with respect to complication (P = .223), reoperation (P = .999), and readmission rates (P = .568) did not reach statistical significance. CONCLUSIONS: The mean standardized costs for the treatment of 3 common IRCT procedures inclusive of 60-day workup and 90-day postoperative recovery were $16,915, $17,210, and $20,837 for LTTT, RSA (average added cost $295), and SCR (average added cost $3922), respectively. This information may provide surgeons and institutions with cost-related information that will become increasingly relevant with the expansion of value-based surgical reimbursements.