Systematic review of machine-learning models in orthopaedic trauma.

Aims: Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool. Methods: A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results: A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion: The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice.

Changes in Scapular Function, Shoulder Strength, and Range of Motion Occur After Latarjet Procedure.

Purpose: To evaluate the current literature on the effects of anatomic changes caused by the Latarjet procedure and to identify areas for future research. Methods: English-language studies that addressed the consequences of anatomic alterations after the open Latarjet procedure were included. Articles written in languages other than English, reviews, and case reports were excluded. Titles and abstracts were screened by 2 authors. Studies that met the inclusion criteria were screened by the same authors. The following data were extracted from the included studies: authors, year of publication, journal, country of origin, aims or purpose, study population and sample size, methods, procedure, intervention type, and key findings that relate to the scoping review questions. Results: Twenty-two studies were included for analysis, yielding the following findings: First, the Latarjet procedure may change the position of the scapula owing to pectoralis minor tenotomy and/or transfer of the conjoint tendon. Second, dissection of the coracoacromial ligament may result in increased superior translation of the humeral head. The impact of this increased translation on patients' function remains unclear. Third, the subscapularis split shows, overall, better internal rotation strength compared with subscapularis tenotomy. Fourth, passive external rotation may be limited after capsular repair. Fifth, despite the movement of the conjoint tendon, elbow function seems unchanged. Finally, the musculocutaneous nerve is lengthened with a changed penetration angle into the coracobrachialis muscle, but the clinical impact seems limited. Conclusions: The Latarjet procedure leads to anatomic and biomechanical changes in the shoulder. Areas of future research may include better documentation of scapular movement (bilateral, as well as preoperative and postoperative) and elbow function, the effect of (degenerative) rotator cuff ruptures after the Latarjet procedure on shoulder function, and the impact of capsular closure and its contribution to the development of glenohumeral osteoarthritis. Clinical Relevance: This comprehensive overview of anatomic changes after the Latarjet procedure, with its effects on shoulder and elbow function, showed gaps in the current literature. Orthopaedic shoulder surgeons and physical therapists could use our findings when providing patient information and performing future clinical research.

Development of machine-learning algorithms for 90-day and one-year mortality prediction in the elderly with femoral neck fractures based on the HEALTH and FAITH trials.

To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration). The developed algorithms distinguished between patients at high and low risk for 90-day and one-year mortality. The penalized logistic regression algorithm had the best performance metrics for both 90-day (c-statistic 0.80, calibration slope 0.95, calibration intercept -0.06, and Brier score 0.039) and one-year (c-statistic 0.76, calibration slope 0.86, calibration intercept -0.20, and Brier score 0.074) mortality prediction in the hold-out set. Using high-quality data, the ML-based prediction models accurately predicted 90-day and one-year mortality in patients aged 50 years or older with a FNF. The final models must be externally validated to assess generalizability to other populations, and prospectively evaluated in the process of shared decision-making.

Atherosclerosis and Intrarenal Resistance Index in Kidney Transplant Recipients.

Atherosclerosis of the aortoiliac vessels can adversely affect kidney perfusion after kidney transplantation. Atherosclerosis severity can be determined using the calcium score (CaScore). Potential problems with posttransplantation kidney perfusion can be determined using the intrarenal resistance index (RI). This study investigated the association between aortoiliac CaScore and RI in kidney transplant recipients. Methods: Kidney transplant recipients (2004-2019), for whom the CaScore and RI were determined, were included in this dual-center cohort study. CaScore was measured in 3 aortoiliac segments using noncontrast CT imaging. RI was determined using Doppler ultrasound. Multivariable linear regression analyses were performed between the CaScore and RI, adjusted for confounding variables. Results: The mean age of the 389 included patients was 59 (±13) y. The mean RI (unitless) was 0.71 (±0.09)' and the median CaScore (unitless) was 3340 (399-7833). In univariable linear regression analyses with RI as the dependent variable, CaScore (ß = 0.011; P < 0.001) was positively associated with RI. Moreover, recipient age (ß = 0.014; P < 0.001), history of diabetes (ß = 0.029; P = 0.003), recipient history of vascular interventions (ß = 0.032; P = 0.002), prior dialysis (ß = 0.029; P = 0.003), deceased donor transplantation (ß = 0.042; P < 0.001), donation after cardiac death (ß = 0.036; P = 0.001), an increase in cold ischemia time (ß = 0.011; P < 0.001), and the Comprehensive Complication Index (ß = 0.006; P = 0.002) were also positively associated with RI, whereas preoperative recipient diastolic blood pressure (ß = -0.007; P = 0.030) was inversely associated. In multivariable analyses, CaScore and RI remained significantly (P = 0.010) associated, independent of adjustment for potential confounders. Furthermore, in univariable linear regression analyses, multiple graft function characteristics were associated with RI. Conclusions: A significant association was found between CaScore and RI, independent of adjustment for multiple potential confounding factors, leading to a better insight into the development and interpretation of RI. Aortoiliac atherosclerosis should be considered when interpreting the RI and determining the possible cause of malperfusion and graft failure after kidney transplantation.

Patients With Femoral Neck Fractures Are at Risk for Conversion to Arthroplasty After Internal Fixation: A Machine-learning Algorithm.

BACKGROUND: Femoral neck fractures are common and are frequently treated with internal fixation. A major disadvantage of internal fixation is the substantially high number of conversions to arthroplasty because of nonunion, malunion, avascular necrosis, or implant failure. A clinical prediction model identifying patients at high risk of conversion to arthroplasty may help clinicians in selecting patients who could have benefited from arthroplasty initially. QUESTION/PURPOSE: What is the predictive performance of a machine-learning (ML) algorithm to predict conversion to arthroplasty within 24 months after internal fixation in patients with femoral neck fractures? METHODS: We included 875 patients from the Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trial. The FAITH trial consisted of patients with low-energy femoral neck fractures who were randomly assigned to receive a sliding hip screw or cancellous screws for internal fixation. Of these patients, 18% (155 of 875) underwent conversion to THA or hemiarthroplasty within the first 24 months. All patients were randomly divided into a training set (80%) and test set (20%). First, we identified 27 potential patient and fracture characteristics that may have been associated with our primary outcome, based on biomechanical rationale and previous studies. Then, random forest algorithms (an ML learning, decision tree-based algorithm that selects variables) identified 10 predictors of conversion: BMI, cardiac disease, Garden classification, use of cardiac medication, use of pulmonary medication, age, lung disease, osteoarthritis, sex, and the level of the fracture line. Based on these variables, five different ML algorithms were trained to identify patterns related to conversion. The predictive performance of these trained ML algorithms was assessed on the training and test sets based on the following performance measures: (1) discrimination (the model's ability to distinguish patients who had conversion from those who did not; expressed with the area under the receiver operating characteristic curve [AUC]), (2) calibration (the plotted estimated versus the observed probabilities; expressed with the calibration curve intercept and slope), and (3) the overall model performance (Brier score: a composite of discrimination and calibration). RESULTS: None of the five ML algorithms performed well in predicting conversion to arthroplasty in the training set and the test set; AUCs of the algorithms in the training set ranged from 0.57 to 0.64, slopes of calibration plots ranged from 0.53 to 0.82, calibration intercepts ranged from -0.04 to 0.05, and Brier scores ranged from 0.14 to 0.15. The algorithms were further evaluated in the test set; AUCs ranged from 0.49 to 0.73, calibration slopes ranged from 0.17 to 1.29, calibration intercepts ranged from -1.28 to 0.34, and Brier scores ranged from 0.13 to 0.15. CONCLUSION: The predictive performance of the trained algorithms was poor, despite the use of one of the best datasets available worldwide on this subject. If the current dataset consisted of different variables or more patients, the performance may have been better. Also, various reasons for conversion to arthroplasty were pooled in this study, but the separate prediction of underlying pathology (such as, avascular necrosis or nonunion) may be more precise. Finally, it may be possible that it is inherently difficult to predict conversion to arthroplasty based on preoperative variables alone. Therefore, future studies should aim to include more variables and to differentiate between the various reasons for arthroplasty. LEVEL OF EVIDENCE: Level III, prognostic study.

Postoperative Ultrasound in Kidney Transplant Recipients: Association Between Intrarenal Resistance Index and Cardiovascular Events.

Doppler ultrasound, including intrarenal resistance index (RI) measurement, is a widely used modality to assess kidney transplantation (KTx) vascularization. The aim of this study is to gain insight in the associations between early postoperative RI measurements and cardiovascular events (CVEs), all-cause mortality, and death-censored graft survival. METHODS: From 2015 to 2017, a prospective cohort study was conducted in patients in which RI measurement was performed immediately after KTx. The RI was calculated as (peak systolic velocity-end-diastolic velocity)/peak systolic velocity. End points were CVEs, all-cause mortality, and graft failure. Kaplan-Meier analyses (logrank test) were used for differences in end points. Univariate and multivariate associations were investigated by means of Cox regression analyses. RESULTS: RI cutoff of 0.70 was used. We included 339 recipients, of which 271 (80%) had an RI ≤ 0.70 and 68 (20%) had an RI > 0.70. CVEs were observed in 27 (8%) patients, 27 (8%) patients died, and 17 (5%) patients had graft failure during a median follow-up of 37 months (interquartile range, 33-43). Kaplan-Meier analyses and univariate Cox regression indicated a significant association with overall CVE-free survival (hazard ratios [HR], 2.79; P = 0.011; logrank test, P = 0.008) and all-cause mortality (HR, 2.59; P = 0.017; logrank test, P = 0.013) for patients with an RI above and below 0.70. An independent association was shown between an RI > 0.70 and CVE-free survival (HR, 2.48; P = 0.042) when deceased donation was not included in the model. CONCLUSIONS: In the early postoperative period, a high RI showed to be associated with CVEs after adjustment for cardiovascular risk factors, whereas no independent association was found with overall survival and graft failure. For the interpretation of RI measurements after KTx surgery, patients' cardiovascular state should be taken into consideration.