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.

Travel burden for patients with multimorbidity - Proof of concept study in a Dutch tertiary care center.

Objectives: To explore travel burden in patients with multimorbidity and analyze patients with high travel burden, to stimulate actions towards adequate access and (remote) care coordination for these patients. Design: A retrospective, cross-sectional, explorative proof of concept study. Setting and Participants: Electronic health record data of all patients who visited our academic hospital in 2017 were used. Patients with a valid 4-digit postal code, aged ≥18 years, had >1 chronic or oncological condition and had >1 outpatient visits with >1 specialties were included. Methods: Travel burden (hours/year) was calculated as: travel time in hours × number of outpatient visit days per patient in one year × 2. Baseline variables were analyzed using univariate statistics. Patients were stratified into two groups by the median travel burden. The contribution of travel time (dichotomized) and the number of outpatient clinic visits days (dichotomized) to the travel burden was examined with binary logistic regression by adding these variables consecutively to a crude model with age, sex and number of diagnosis. National maps exploring the geographic variation of multimorbidity and travel burden were built. Furthermore, maps showing the distribution of socioeconomic status (SES) and proportion of older age (≥65 years) of the general population were built. Results: A total of 14 476 patients were included (54.4% female, mean age 57.3 years ([± standard deviation] = ± 16.6 years). Patients travelled an average of 0.42 (± 0.33) hours to the hospital per (one-way) visit with a median travel burden of 3.19 hours/year (interquartile range (IQR) 1.68 - 6.20). Care consumption variables, such as higher number of diagnosis and treating specialties in the outpatient clinic were more frequent in patients with higher travel burden. High travel time showed a higher Odds Ratio (OR = 578 (95% Confidence Interval (CI) = 353 - 947), p < 0.01) than having high number of outpatient clinic visit days (OR = 237, 95% CI = 144 - 338), p < 0.01) to having a high travel burden in the final regression model. Conclusions and implications: The geographic representation of patients with multimorbidity and their travel burden varied but coincided locally with lower SES and older age in the general population. Future studies should aim on identifying patients with high travel burden and low SES, creating opportunity for adequate (remote) care coordination.

Clockwise torque results in higher reoperation rates in left-sided femur fractures.

PURPOSE: Effects of clockwise torque rotation onto proximal femoral fracture fixation have been subject of ongoing debate: fixated right-sided trochanteric fractures seem more rotationally stable than left-sided fractures in the biomechanical setting, but this theoretical advantage has not been demonstrated in the clinical setting to date. The purpose of this study was to identify a difference in early reoperation rate between patients undergoing surgery for left- versus right-sided proximal femur fractures using cephalomedullary nailing (CMN). MATERIALS AND METHODS: The American College of Surgeons National Surgical Quality Improvement Program was queried from 2016-2019 to identify patients aged 50 years and older undergoing CMN for a proximal femoral fracture. The primary outcome was any unplanned reoperation within 30 days following surgery. The difference was calculated using a Chi-square test, and observed power calculated using post-hoc power analysis. RESULTS: In total, of 20,122 patients undergoing CMN for proximal femoral fracture management, 1.8% (n=371) had to undergo an unplanned reoperation within 30 days after surgery. Overall, 208 (2.0%) were left-sided and 163 (1.7%) right-sided fractures (p=0.052, risk ratio [RR] 1.22, 95% confidence interval [CI] 1.00-1.50), odds ratio [OR] 1.23 (95%CI 1.00-1.51), power 49.2% (α=0.05). CONCLUSION: This study shows a higher risk of reoperation for left-sided compared to right-sided proximal femur fractures after CMN in a large sample size. Although results may be underpowered and statistically insignificant, this finding might substantiate the hypothesis that clockwise rotation during implant insertion and (postoperative) weightbearing may lead to higher reoperation rates. LEVEL OF EVIDENCE: Therapeutic level II.

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.

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.

Effectiveness of an individually tailored home-based exercise rogramme for pre-frail older adults, driven by a tablet application and mobility monitoring: a pilot study.

OBJECTIVES: To gain first insight into the effectiveness of a home-based exercise programme for pre-frail older adults with independent use of novel ICT technology. METHODS: A pilot study. Forty pre-frail older adults joined a six-month home-based exercise programme using a tablet PC for exercise administration and feedback, and a necklace-worn motion sensor for daily physical activity registration. Participants received weekly telephone supervision during the first 3 months and exercised independently without supervision from a coach during the last 3 months. Functional performance and daily physical activity were assessed at baseline, after three and 6 months. RESULTS: Twenty-one participants completed the programme. Overall, functional performance showed positive results varying from (very) small to large effects (Cohen's d 0.04-0.81), mainly during the supervised part of the intervention. Regarding daily physical activity, a slight improvement with (very) small effects (Cohen's d 0.07-0.38), was observed for both self-reported and objectively measured physical activity during the supervised period. However, during the unsupervised period this pattern only continued for self-reported physical activity. CONCLUSION: This pilot study showed positive results varying from (very) small to large effects in levels and maintenance of functional performance and daily physical activity, especially during the supervised first 3 months. Remote supervision seems to importantly affect effectiveness of a home-based exercise programme. Effectiveness of the programme and the exact contribution of its components should be further quantified in a randomized controlled trial. PRACTICE IMPLICATIONS: Home-based exercising using novel technology may be promising for functional performance and physical activity improvement in (pre-frail) older adults. TRIAL REGISTRATION: Netherlands Trial Register (NTR); trial number NL4049 . The study was prospectively registered (registration date 14/11/2013).

Augmented and virtual reality in spine surgery, current applications and future potentials.

BACKGROUND CONTEXT: The field of artificial intelligence (AI) is rapidly advancing, especially with recent improvements in deep learning (DL) techniques. Augmented (AR) and virtual reality (VR) are finding their place in healthcare, and spine surgery is no exception. The unique capabilities and advantages of AR and VR devices include their low cost, flexible integration with other technologies, user-friendly features and their application in navigation systems, which makes them beneficial across different aspects of spine surgery. Despite the use of AR for pedicle screw placement, targeted cervical foraminotomy, bone biopsy, osteotomy planning, and percutaneous intervention, the current applications of AR and VR in spine surgery remain limited. PURPOSE: The primary goal of this study was to provide the spine surgeons and clinical researchers with the general information about the current applications, future potentials, and accessibility of AR and VR systems in spine surgery. STUDY DESIGN/SETTING: We reviewed titles of more than 250 journal papers from google scholar and PubMed with search words: augmented reality, virtual reality, spine surgery, and orthopaedic, out of which 89 related papers were selected for abstract review. Finally, full text of 67 papers were analyzed and reviewed. METHODS: The papers were divided into four groups: technological papers, applications in surgery, applications in spine education and training, and general application in orthopaedic. A team of two reviewers performed paper reviews and a thorough web search to ensure the most updated state of the art in each of four group is captured in the review. RESULTS: In this review we discuss the current state of the art in AR and VR hardware, their preoperative applications and surgical applications in spine surgery. Finally, we discuss the future potentials of AR and VR and their integration with AI, robotic surgery, gaming, and wearables. CONCLUSIONS: AR and VR are promising technologies that will soon become part of standard of care in spine surgery.