Symmetry of the left and right tibial plafond; a comparison of 75 distal tibia pairs.

PURPOSE: Tibia plafond or pilon fractures present a high level of complexity, making their surgical management challenging. Three-Dimensional Virtual Planning (3DVP) can assist in preoperative planning to achieve optimal fracture reduction. This study aimed to assess the symmetry of the left and right tibial plafond and whether left-right mirroring can reliably be used. METHODS: Bilateral CT scans of the lower limbs of 75 patients without ankle problems or prior fractures of the lower limb were included. The CT images were segmented to create 3D surface models of the tibia. Subsequently, the left tibial models were mirrored and superimposed onto the right tibia models using a Coherent Point Drift surface matching algorithm. The tibias were then cut to create bone models of the distal tibia with a height of 30 mm, and correspondence points were established. The Euclidean distance was calculated between correspondence points and visualized in a boxplot and heatmaps. The articulating surface was selected as a region of interest. RESULTS: The median left-right difference was 0.57 mm (IQR, 0.38 - 0.85 mm) of the entire tibial plafond and 0.53 mm (IQR, 0.37 - 0.76 mm) of the articulating surface. The area with the greatest left-right differences were the medial malleoli and the anterior tubercle of the tibial plafond. CONCLUSION: The tibial plafond exhibits a high degree of bilateral symmetry. Therefore, the mirrored unfractured tibial plafond may be used as a template to optimize preoperative surgical reduction using 3DVP techniques in patients with pilon fractures.

Prevalence of Rotational Malalignment After Infrapatellar Versus Suprapatellar Intramedullary Nailing of Tibial Shaft Fractures.

Background: Up to 30% of patients with a tibial shaft fracture sustain iatrogenic rotational malalignment (RM) after infrapatellar (IP) nailing. Although IP nailing remains the management of choice for most patients, suprapatellar (SP) nailing has been gaining popularity. It is currently unknown whether SP nailing can provide superior outcomes with regard to tibial RM. The aim of this study was to compare the differences in the prevalence of RM following IP versus SP nailing. Methods: This retrospective study included 253 patients with a unilateral, closed tibial shaft fracture treated with either an IP or SP approach between January 2009 and April 2023 in a Level-I trauma center. All patients underwent a postoperative, protocolized, bilateral computed tomography (CT) scan for RM assessment. Results: RM was observed in 30% and 33% of patients treated with IP and SP nailing, respectively. These results indicate no significant difference (p = 0.639) in the prevalence of RM between approaches. Furthermore, there were no significant differences in the distribution (p = 0.553) and direction of RM (p = 0.771) between the 2 approaches. With the IP and SP approaches, nailing of left-sided tibial shaft fractures resulted in predominantly internal RM (85% and 73%, respectively), while nailing of right-sided tibial shaft fractures resulted in predominantly external RM (90% and 80%, respectively). The intraobserver reliability for the CT measurements was 0.95. Conclusions: The prevalence of RM was not influenced by the entry point of tibial nailing (i.e., IP versus SP). Hence, the choice of surgical approach should rely on factors other than the risk of RM. Level of Evidence: Therapeutic Level III. See Instructions for Authors for a complete description of levels of evidence.

Rotational Malalignment After Intramedullary Nailing of Tibial Shaft Fractures Is Predictable.

OBJECTIVES: Intramedullary nailing is the treatment of choice for most tibial shaft fractures (TSF). However, an iatrogenic pitfall may be rotational malalignment. The aim of this retrospective analysis was to determine predictors of rotational malalignment following intramedullary nailing of TSF. DESIGN: Retrospective study. SETTING: Single level 1 trauma center. PATIENT SELECTION CRITERIA: Patients who had a unilateral intramedullary nailing for TSF with a low-dose bilateral postoperative CT to assess rotational malalignment. OUTCOME MEASURES AND COMPARISONS: Bivariable analysis followed by multivariable analysis was then undertaken to assess for any independent predictors, such as fracture type/sight, surgeon experience, and side of fracture, predictive of rotational malalignment. RESULTS: In total, 154 patients (71% male, median age 37 years) were included in this study. Thirty-nine percent of variability in postoperative rotational malalignment could be explained using a model including (increased) tibial torsion of the noninjured side (mean [38.9 degrees ± 9.02 degrees] considered normal tibial torsion), side of tibial fracture, and spiral-type tibial fracture (R2 = 0.39, P ≤ 0.001, F = 31.40). In this model, there was a negative linear association between degrees of torsion on the noninjured side and rotational malalignment (-0.45, P < 0.001)-as baseline torsion increased from mean by 1 degree, malrotation in the opposite direction of 0.54 degrees seen. Positive linear associations between right-sided TSF and rotational malalignment (8.59 P < 0.001) as well as spiral fractures and rotational malalignment (5.03, P < 0.01) were seen. CONCLUSIONS: This study demonstrates that baseline reduced (internal) tibial torsion of the noninjured limb, spiral fractures, and right-sided TSF are predictive of postoperative external rotational malalignment. Conversely, increased baseline (external) tibial torsion of the noninjured limb and left-sided TSF are predictive of postoperative internal rotational malalignment. Surgeons may use this regression model preoperatively to predict what sort of postoperative rotational difference their patient may be prone to. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Machine Learning Did Not Outperform Conventional Competing Risk Modeling to Predict Revision Arthroplasty.

BACKGROUND: Estimating the risk of revision after arthroplasty could inform patient and surgeon decision-making. However, there is a lack of well-performing prediction models assisting in this task, which may be due to current conventional modeling approaches such as traditional survivorship estimators (such as Kaplan-Meier) or competing risk estimators. Recent advances in machine learning survival analysis might improve decision support tools in this setting. Therefore, this study aimed to assess the performance of machine learning compared with that of conventional modeling to predict revision after arthroplasty. QUESTION/PURPOSE: Does machine learning perform better than traditional regression models for estimating the risk of revision for patients undergoing hip or knee arthroplasty? METHODS: Eleven datasets from published studies from the Dutch Arthroplasty Register reporting on factors associated with revision or survival after partial or total knee and hip arthroplasty between 2018 and 2022 were included in our study. The 11 datasets were observational registry studies, with a sample size ranging from 3038 to 218,214 procedures. We developed a set of time-to-event models for each dataset, leading to 11 comparisons. A set of predictors (factors associated with revision surgery) was identified based on the variables that were selected in the included studies. We assessed the predictive performance of two state-of-the-art statistical time-to-event models for 1-, 2-, and 3-year follow-up: a Fine and Gray model (which models the cumulative incidence of revision) and a cause-specific Cox model (which models the hazard of revision). These were compared with a machine-learning approach (a random survival forest model, which is a decision tree-based machine-learning algorithm for time-to-event analysis). Performance was assessed according to discriminative ability (time-dependent area under the receiver operating curve), calibration (slope and intercept), and overall prediction error (scaled Brier score). Discrimination, known as the area under the receiver operating characteristic curve, measures the model's ability to distinguish patients who achieved the outcomes from those who did not and ranges from 0.5 to 1.0, with 1.0 indicating the highest discrimination score and 0.50 the lowest. Calibration plots the predicted versus the observed probabilities; a perfect plot has an intercept of 0 and a slope of 1. The Brier score calculates a composite of discrimination and calibration, with 0 indicating perfect prediction and 1 the poorest. A scaled version of the Brier score, 1 - (model Brier score/null model Brier score), can be interpreted as the amount of overall prediction error. RESULTS: Using machine learning survivorship analysis, we found no differences between the competing risks estimator and traditional regression models for patients undergoing arthroplasty in terms of discriminative ability (patients who received a revision compared with those who did not). We found no consistent differences between the validated performance (time-dependent area under the receiver operating characteristic curve) of different modeling approaches because these values ranged between -0.04 and 0.03 across the 11 datasets (the time-dependent area under the receiver operating characteristic curve of the models across 11 datasets ranged between 0.52 to 0.68). In addition, the calibration metrics and scaled Brier scores produced comparable estimates, showing no advantage of machine learning over traditional regression models. CONCLUSION: Machine learning did not outperform traditional regression models. CLINICAL RELEVANCE: Neither machine learning modeling nor traditional regression methods were sufficiently accurate in order to offer prognostic information when predicting revision arthroplasty. The benefit of these modeling approaches may be limited in this context.

3D surgical planning including patient-specific drilling guides for tibial plateau fractures.

Aims: Proper preoperative planning benefits fracture reduction, fixation, and stability in tibial plateau fracture surgery. We developed and clinically implemented a novel workflow for 3D surgical planning including patient-specific drilling guides in tibial plateau fracture surgery. Methods: A prospective feasibility study was performed in which consecutive tibial plateau fracture patients were treated with 3D surgical planning, including patient-specific drilling guides applied to standard off-the-shelf plates. A postoperative CT scan was obtained to assess whether the screw directions, screw lengths, and plate position were performed according the preoperative planning. Quality of the fracture reduction was assessed by measuring residual intra-articular incongruence (maximum gap and step-off) and compared to a historical matched control group. Results: A total of 15 patients were treated with 3D surgical planning in which 83 screws were placed by using drilling guides. The median deviation of the achieved screw trajectory from the planned trajectory was 3.4° (interquartile range (IQR) 2.5 to 5.4) and the difference in entry points (i.e. plate position) was 3.0 mm (IQR 2.0 to 5.5) compared to the 3D preoperative planning. The length of 72 screws (86.7%) were according to the planning. Compared to the historical cohort, 3D-guided surgery showed an improved surgical reduction in terms of median gap (3.1 vs 4.7 mm; p = 0.126) and step-off (2.9 vs 4.0 mm; p = 0.026). Conclusion: The use of 3D surgical planning including drilling guides was feasible, and facilitated accurate screw directions, screw lengths, and plate positioning. Moreover, the personalized approach improved fracture reduction as compared to a historical cohort.

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.

Development of patient-specific osteosynthesis including 3D-printed drilling guides for medial tibial plateau fracture surgery.

PURPOSE: A substantial proportion of conventional tibial plateau plates have a poor fit, which may result in suboptimal fracture reduction due to applied -uncontrolled- compression on the bone. This study aimed to assess whether patient-specific osteosyntheses could facilitate proper fracture reduction in medial tibial plateau fractures. METHODS: In three Thiel embalmed human cadavers, a total of six tibial plateau fractures (three Schatzker 4, and three Schatzker 6) were created and CT scans were made. A 3D surgical plan was created and a patient-specific implant was designed and fabricated for each fracture. Drilling guides that fitted on top of the customized plates were designed and 3D printed in order to assist the surgeon in positioning the plate and steering the screws in the preplanned direction. After surgery, a postoperative CT scan was obtained and outcome was compared with the preoperative planning in terms of articular reduction, plate positioning, and screw direction. RESULTS: A total of six patient-specific implants including 41 screws were used to operate six tibial plateau fractures. Three fractures were treated with single plating, and three fractures with dual plating. The median intra-articular gap was reduced from 6.0 (IQR 4.5-9.5) to 0.9 mm (IQR 0.2-1.4), whereas the median step-off was reduced from 4.8 (IQR 4.1-5.3) to 1.3 mm (IQR 0.9-1.5). The median Euclidean distance between the centre of gravity of the planned and actual implant was 3.0 mm (IQR: 2.8-3.7). The lengths of the screws were according to the predetermined plan. None of the screws led to screw penetration. The median difference between the planned and actual screw direction was 3.3° (IQR: 2.5-5.1). CONCLUSION: This feasibility study described the development and implementation of a patient-specific workflow for medial tibial plateau fracture surgery that facilitates proper fracture reduction, tibial alignment and accurately placed screws by using custom-made osteosynthesis plates with drilling guides.

The management of elbow trauma from a historical perspective.

The origins of contemporary orthopedics can be traced all the way back to antiquity. Despite the absence of modern imaging techniques, a few bright minds were able to lay the groundwork for understanding these fractures. This historical review will cover the process behind the various treatments for elbow fractures, such as splinting and casting, mobilization, amputation, fracture fixation, arthroplasty, and arthroscopy.

Coronoid fractures and traumatic elbow instability.

The coronoid process is key to concentric elbow alignment. Malalignment can contribute to post-traumatic osteoarthritis. The aim of treatment is to keep the joint aligned while the collateral ligaments and fractures heal. The injury pattern is apparent in the shape and size of the coronoid fracture fragments: (1) coronoid tip fractures associated with terrible triad (TT) injuries; (2) anteromedial facet fractures with posteromedial varus rotational type injuries; and (3) large coronoid base fractures with anterior (trans-) or posterior olecranon fracture dislocations. Each injury pattern is associated with specific ligamentous injuries and fracture characteristics useful in planning treatment. The tip fractures associated with TT injuries are repaired with suture fixation or screw fixation in addition to repair or replacement of the radial head fracture and reattachment of the lateral collateral ligament origin. Anteromedial facet fractures are usually repaired with a medial buttress plate. If the elbow is concentrically located on computed tomography and the patient can avoid varus stress for a month, TT and anteromedial facet injuries can be treated nonoperatively. Base fractures are associated with olecranon fractures and can usually be fixed with screws through the posterior plate or with an additional medial plate. If the surgery makes elbow subluxation or dislocation unlikely, and the fracture fixation is secure, elbow motion and stretching can commence within a week when the patient is comfortable.

Triplane ankle fracture patterns in paediatric patients.

Aims: Triplane ankle fractures are complex injuries typically occurring in children aged between 12 and 15 years. Classic teaching that closure of the physis dictates the overall fracture pattern, based on studies in the 1960s, has not been challenged. The aim of this paper is to analyze whether these injuries correlate with the advancing closure of the physis with age. Methods: A fracture mapping study was performed in 83 paediatric patients with a triplane ankle fracture treated in three trauma centres between January 2010 and June 2020. Patients aged younger than 18 years who had CT scans available were included. An independent Paediatric Orthopaedic Trauma Surgeon assessed all CT scans and classified the injuries as n-part triplane fractures. Qualitative analysis of the fracture pattern was performed using the modified Cole fracture mapping technique. The maps were assessed for both patterns and correlation with the closing of the physis until consensus was reached by a panel of six surgeons. Results: Fracture map grouped by age demonstrates that, regardless of age (even at the extremes of the spectrum), the fracture lines consolidate in a characteristic Y-pattern, and no shift with closure of the physis was observed. A second fracture map with two years added to female age also did not show a shift. The fracture map, grouped by both age and sex, shows a Y-pattern in all different groups. The fracture lines appear to occur between the anterior and posterior inferior tibiofibular ligaments, and the medially fused physis or deltoid ligament. Conclusion: This fracture mapping study reveals that triplane ankle fractures have a characteristic Y-pattern, and acknowledges the weakness created by the physis, however it also challenges classic teaching that the specific fracture pattern at the level of the joint of these injuries relies on advancing closure of the physis with age. Instead, this study observes the importance of ligament attachment in the fracture patterns of these injuries.

Clinical validation of the 'C-arm rotational view (CARV)': study protocol of a prospective randomised controlled trial.

INTRODUCTION: Rotational malalignment occurs in up to 30% of cases after intramedullary nailing of tibial shaft fractures. The aim of this study is to assess the clinical feasibility of a newly introduced standardised intraoperative fluoroscopy protocol coined 'C-arm rotational view (CARV)' in order to reduce the risk of rotational malalignment during intramedullary nailing of tibial shaft fractures. The CARV includes predefined fluoroscopy landmark views of the uninjured side to obtain correct alignment of the injured side with use of the rotation of the C-arm. METHODS AND ANALYSIS: This randomised controlled trial will be conducted in a level 1 trauma centre. Adult patients with an open or closed tibial fracture, eligible for intramedullary nailing, will be enrolled in the study. The interventional group will undergo intramedullary nailing guided by the CARV protocol to obtain accurate alignment. The control group is treated according to current clinical practice, in which alignment control of the tibia is based on clinical estimation of the treating surgeon. The primary endpoint is defined as the degree of rotation measured on low-dose postoperative CT scans. ETHICS AND DISSEMINATION: The study protocol will be performed in line with local ethical guidelines and the Declaration of Helsinki. The results of this trial will be disseminated in a peer-reviewed manuscript. Future patients are likely to benefit from this trial as it aims to provide a clinically feasible and easy-to-use standardised fluoroscopy protocol to reduce the risk for rotational malalignment during intramedullary nailing of tibial shaft fractures. TRIAL REGISTRATION NUMBER: NCT05459038.

Developing a machine learning algorithm to predict the probability of aseptic loosening of the glenoid component after anatomical total shoulder arthroplasty: protocol for a retrospective, multicentre study.

INTRODUCTION: Despite technological advancements in recent years, glenoid component loosening remains a common complication after anatomical total shoulder arthroplasty (ATSA) and is one of the main causes of revision surgery. Increasing emphasis is placed on the prevention of glenoid component failure. Previous studies have successfully predicted range of motion, patient-reported outcomes and short-term complications after ATSA using machine learning methods, but an accurate predictive model for (glenoid component) revision is currently lacking. This study aims to use a large international database to accurately predict aseptic loosening of the glenoid component after ATSA using machine learning algorithms. METHODS AND ANALYSIS: For this multicentre, retrospective study, individual patient data will be compiled from previously published studies reporting revision of ATSA. A systematic literature search will be performed in Medline (PubMed) identifying all studies reporting outcomes of ATSA. Authors will be contacted and invited to participate in the Machine Learning Consortium by sharing their anonymised databases. All databases reporting revisions after ATSA will be included, and individual patients with a follow-up less than 2 years or a fracture as the indication for ATSA will be excluded. First, features (predictive variables) will be identified using a random forest feature selection. The resulting features from the compiled database will be used to train various machine learning algorithms (stochastic gradient boosting, random forest, support vector machine, neural network and elastic-net penalised logistic regression). The developed and validated algorithms will be evaluated across discrimination (c-statistic), calibration, the Brier score and the decision curve analysis. The best-performing algorithm will be used to create an open-access online prediction tool. ETHICS AND DISSEMINATION: Data will be collected adhering to the WHO regulation on data sharing. An Institutional Review Board review is not applicable. The study results will be published in a peer-reviewed journal.

Scaphoid Length Loss Following Nonunion Is Associated with Dorsal Intercalated Segment Instability.

Background Dorsal intercalated segment instability (DISI) in scaphoid nonunions is frequently attributed to fracture location relative to ligamentous attachments onto the scaphoid apex. We hypothesize scaphoid length loss to have a stronger correlation with DISI deformity than fracture location in patients with scaphoid nonunion. Questions/Purposes To investigate the correlation between (1) scaphoid length loss, (2) fracture location relative to the scaphoid apex, and (3) type of nonunion (Herbert classification) and DISI deformity in skeletally mature patients with scaphoid nonunion. Patients and Methods Twenty-seven cases of computed tomography (CT)-confirmed scaphoid nonunion (>6 months) were retrospectively included. Our primary outcome was the degree of DISI as measured by the radiolunate (RL) angle on CT. Scaphoid length loss was expressed as height-to-length (H/L) ratio. Fracture location was classified as proximal or distal to the scaphoid apex. Nonunions were classified as fibrous unions (type D1) or pseudoarthrosis (type D2). The correlation between RL angle, H/L ratio, fracture location, and nonunion type was evaluated. Results H/L ratio was the only factor associated with the degree of DISI as measured by RL angle. As scaphoid length loss increased (increasing H/L ratio), the RL angle increased. There was no significant difference in RL angle between fractures located proximal (30 degrees) or distal (28 degrees) to the scaphoid apex, or type D1 (31 degrees) versus type D2 (28 degrees) nonunions. There was no correlation between patient age, sex, or wrist side affected and RL angle. Conclusions Scaphoid length loss, rather than fracture location, is correlated to the degree of DISI deformity in patients with scaphoid nonunion. This highlights the importance of restoring scaphoid height when planning scaphoid nonunion reconstruction. Level of Evidence Level III, diagnostic study.

Routine MRI Among Patients With a Suspected Scaphoid Fracture Risks Overdiagnosis.

BACKGROUND: In the setting of a suspected scaphoid fracture, MRI may result in overdiagnosis and potential overtreatment. This is in part because of the low prevalence of true fractures among suspected fractures, but also because of potentially misleading variations in signal that may be more common than fracture-related signal changes. To better understand the risk of overdiagnosis, we first need insight into the relative prevalence of useful and potentially distracting signal changes among patients with a suspected scaphoid fracture. QUESTION/PURPOSE: What is the proportion of signal changes representing definite and possible scaphoid fractures relative to other types of signal changes on MRI among patients with a suspected scaphoid fracture? METHODS: In a retrospective study in an orthopaedic trauma clinic associated with a Level I trauma center, we evaluated MR images of patients 16 years and older with a clinically suspected scaphoid fracture. At our institution, patients with symptoms and signs of a possible scaphoid fracture and negative radiographs undergo MRI scanning. Between January 1, 2012, and September 1, 2019, a total of 310 patients 16 years or older had an MRI to evaluate a suspected scaphoid fracture. Exclusion criteria included a scaphoid fracture that was visible on radiographs before MRI as reported by the radiologist (four patients), no available radiographs before MRI (two), MRI more than 3 weeks after injury (28), unknown date of injury (nine), and repeat or bilateral MRI scans (11), leaving 256 MR images for analysis. Sixty percent (153) of patients were women, and the median age was 34 years (IQR 21 to 50 years). The images were taken a median of 8 days (IQR 2 to 12 days) after injury. MR images were screened for the presence of scaphoid signal changes. We identified the following patterns of signal change with a reliability of kappa 0.62: definite scaphoid fracture, possible scaphoid fracture, signal in the waist area other than possible or definite fractures, and other signal changes. A definite scaphoid fracture was defined as a linear, focal, and bicortical signal abnormality, with adjacent edema and a relatively transverse orientation relative to the scaphoid long axis. The transverse linear signal was visible on more than one cut in multiple planes. A possible scaphoid fracture had a transverse linear signal on more than one cut on sagittal or coronal planes, with or without adjacent edema. RESULTS: Six percent (16 of 256) of MR images were categorized as revealing definite (2% [four of 256]) or possible (5% [12 of 256]) scaphoid fractures, whereas 29% (74 of 256) were categorized as revealing nonspecific signal changes at the waist (14% [35 of 256]) and other areas (15% [39 of 256]). Of the 51 patients with scaphoid waist signal changes, 69% (35) were categorized as having distracting and potentially misleading MRI findings. CONCLUSION: The high prevalence of signal changes that are distracting and potentially misleading, the low prevalence of signal changes that clearly represent a scaphoid fracture, and the low pretest odds of a true fracture among patients with a suspected scaphoid fracture illustrate that routine MRI of suspected scaphoid fractures carries a notable risk of overdiagnosis and potential overtreatment. Two alternative strategies are supported by preliminary evidence and merit additional attention: more-selective use of MRI in people deemed at higher risk according to a clinical prediction rule and strategies for involving the patient in decisions regarding how to manage the notably small risk of future symptomatic nonunion. LEVEL OF EVIDENCE: Level IV, diagnostic study.

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.

Can CT-based gap and step-off displacement predict outcome after nonoperative treatment of acetabular fractures?

Aims: The aim of this study was to investigate the association between fracture displacement and survivorship of the native hip joint without conversion to a total hip arthroplasty (THA), and to determine predictors for conversion to THA in patients treated nonoperatively for acetabular fractures. Methods: A multicentre cross-sectional study was performed in 170 patients who were treated nonoperatively for an acetabular fracture in three level 1 trauma centres. Using the post-injury diagnostic CT scan, the maximum gap and step-off values in the weightbearing dome were digitally measured by two trauma surgeons. Native hip survival was reported using Kaplan-Meier curves. Predictors for conversion to THA were determined using Cox regression analysis. Results: Of 170 patients, 22 (13%) subsequently received a THA. Native hip survival in patients with a step-off ≤ 2 mm, > 2 to 4 mm, or > 4 mm differed at five-year follow-up (respectively: 94% vs 70% vs 74%). Native hip survival in patients with a gap ≤ 2 mm, > 2 to 4 mm, or > 4 mm differed at five-year follow-up (respectively: 100% vs 84% vs 78%). Step-off displacement > 2 mm (> 2 to 4 mm hazard ratio (HR) 4.9, > 4 mm HR 5.6) and age > 60 years (HR 2.9) were independent predictors for conversion to THA at follow-up. Conclusion: Patients with minimally displaced acetabular fractures who opt for nonoperative fracture treatment may be informed that fracture displacement (e.g. gap and step-off) up to 2 mm, as measured on CT images, results in limited risk on conversion to THA. Step-off ≥ 2 mm and age > 60 years are predictors for conversion to THA and can be helpful in the shared decision-making process.

Evaluating machine learning algorithms to Predict 30-day Unplanned REadmission (PURE) in Urology patients.

BACKGROUND: Unplanned hospital readmissions are serious medical adverse events, stressful to patients, and expensive for hospitals. This study aims to develop a probability calculator to predict unplanned readmissions (PURE) within 30-days after discharge from the department of Urology, and evaluate the respective diagnostic performance characteristics of the PURE probability calculator developed with machine learning (ML) algorithms comparing regression versus classification algorithms. METHODS: Eight ML models (i.e. logistic regression, LASSO regression, RIDGE regression, decision tree, bagged trees, boosted trees, XGBoost trees, RandomForest) were trained on 5.323 unique patients with 52 different features, and evaluated on diagnostic performance of PURE within 30 days of discharge from the department of Urology. RESULTS: Our main findings were that performances from classification to regression algorithms had good AUC scores (0.62-0.82), and classification algorithms showed a stronger overall performance as compared to models trained with regression algorithms. Tuning the best model, XGBoost, resulted in an accuracy of 0.83, sensitivity of 0.86, specificity of 0.57, AUC of 0.81, PPV of 0.95, and a NPV of 0.31. CONCLUSIONS: Classification models showed stronger performance than regression models with reliable prediction for patients with high probability of readmission, and should be considered as first choice. The tuned XGBoost model shows performance that indicates safe clinical appliance for discharge management in order to prevent an unplanned readmission at the department of Urology.

STUDY NEED AND IMPORTANCE: Unplanned readmissions form a consistent problem for many hospitals. Unplanned readmission rates can go up as high as to 35%, and may differ significantly between respective hospital departments. In addition, in the field of Urology readmission rates can be greatly influenced by type of surgery performed and unplanned readmissions in patients can go up as high as 26%. Although predicting unplanned readmissions for individual patients is often complex, due to multiple factors that need to be taken into account (e.g. functional disability, poor overall condition), there is evidence that these can be prevented when discharge management is evaluated with an objective measuring tool that facilitate such risk stratification between high and low risk patients. However, to the best of our knowledge, the latter risk stratification using ML driven probability calculators in the field of Urology have not been evaluated to date. Using ML, calculated risk scores based on analysing complex data patterns on patient level can support safe discharge and inform concerning the risk of having an unplanned readmission. WHAT WE FOUND: Eight ML models were trained on 5.323 unique patients with 52 different features, and evaluated on diagnostic performance. Classification models showed stronger performance than regression models with reliable prediction for patients with high probability of readmission, and should be considered as first choice. The tuned XGBoost model shows performance that indicates safe clinical appliance for discharge management in order to prevent an unplanned readmission at the department of Urology. Limitations of our study were the quality and presence of patient data on features, and how to implement these findings in clinical setting to transition from predicting to preventing unplanned readmissions. INTERPRETATION FOR CLINICIANS: ML models based on classification should be first choice to predict unplanned readmissions, and the XGBoost model showed the strongest results.

Implications of resampling data to address the class imbalance problem (IRCIP): an evaluation of impact on performance between classification algorithms in medical data.

Objective: When correcting for the "class imbalance" problem in medical data, the effects of resampling applied on classifier algorithms remain unclear. We examined the effect on performance over several combinations of classifiers and resampling ratios. Materials and Methods: Multiple classification algorithms were trained on 7 resampled datasets: no correction, random undersampling, 4 ratios of Synthetic Minority Oversampling Technique (SMOTE), and random oversampling with the Adaptive Synthetic algorithm (ADASYN). Performance was evaluated in Area Under the Curve (AUC), precision, recall, Brier score, and calibration metrics. A case study on prediction modeling for 30-day unplanned readmissions in previously admitted Urology patients was presented. Results: For most algorithms, using resampled data showed a significant increase in AUC and precision, ranging from 0.74 (CI: 0.69-0.79) to 0.93 (CI: 0.92-0.94), and 0.35 (CI: 0.12-0.58) to 0.86 (CI: 0.81-0.92) respectively. All classification algorithms showed significant increases in recall, and significant decreases in Brier score with distorted calibration overestimating positives. Discussion: Imbalance correction resulted in an overall improved performance, yet poorly calibrated models. There can still be clinical utility due to a strong discriminating performance, specifically when predicting only low and high risk cases is clinically more relevant. Conclusion: Resampling data resulted in increased performances in classification algorithms, yet produced an overestimation of positive predictions. Based on the findings from our case study, a thoughtful predefinition of the clinical prediction task may guide the use of resampling techniques in future studies aiming to improve clinical decision support tools.