Excessive resident duty hours (RDH) are a recognized issue with implications for physician well-being and patient safety. A major component of the RDH concern is on-call duty. While considerable work has been done to reduce resident call workload, there is a paucity of research in optimizing resident call scheduling. Call coverage is scheduled manually rather than demand-based, which generally leads to over-scheduling to prevent a service gap. Machine learning (ML) has been widely applied in other industries to prevent such issues of a supply-demand mismatch. However, the healthcare field has been slow to adopt these innovations. As such, the aim of this study was to use ML models to 1) predict demand on orthopaedic surgery residents at a level I trauma centre and 2) identify variables key to demand prediction.

Daily surgical handover emails over an eight year (2012-2019) period at a level I trauma centre were collected. The following data was used to calculate demand: spine call coverage, date, and number of operating rooms (ORs), traumas, admissions and consults completed. Various ML models (linear, tree-based and neural networks) were trained to predict the workload, with their results compared to the current scheduling approach. Quality of models was determined by using the area under the receiver operator curve (AUC) and accuracy of the predictions. The top ten most important variables were extracted from the most successful model.

During training, the model with the highest AUC and accuracy was the multivariate adaptive regression splines (MARS) model, with an AUC of 0.78±0.03 and accuracy of 71.7%±3.1%. During testing, the model with the highest AUC and accuracy was the neural network model, with an AUC of 0.81 and accuracy of 73.7%. All models were better than the current approach, which had an AUC of 0.50 and accuracy of 50.1%. Key variables used by the neural network model were (descending order): spine call duty, year, weekday/weekend, month, and day of the week.

This was the first study attempting to use ML to predict the service demand on orthopaedic surgery residents at a major level I trauma centre. Multiple ML models were shown to be more appropriate and accurate at predicting the demand on surgical residents as compared to the current scheduling approach. Future work should look to incorporate predictive models with optimization strategies to match scheduling with demand in order to improve resident well being and patient care.

The management of periprosthetic distal femur fractures is an issue of increasing importance for orthopaedic surgeons. Because of the expanding indications for total knee arthroplasty (TKA) and an aging population with increasingly active lifestyles there has been a corresponding increase in the prevalence of these injuries. The management of these fractures is often complex because of issues with obtaining fixation around implants and dealing with osteopenic bone or compromised bone stock. In addition, these injuries frequently occur in frail, elderly patients, and the early restoration of function and ambulation is critical in these patients. There remains substantial controversy with respect to the optimal treatment of periprosthetic distal femur fractures, with some advocating for Locked Plating (LP), others Retrograde Intramedullary Nailing (RIMN) and finally those who advocate for Distal Femoral Replacement (DFR). The literature comparing these treatments, has been infrequent, and commonly restricted to single-center studies. The purpose of this study was to retrospectively evaluate a large series of operatively treated periprosthetic distal femur fractures from multiple centers and compare treatment strategies.

Patients who were treated operatively for a periprosthetic distal femur fracture at 8 centers across North America between 2003 and 2018 were retrospectively identified. Baseline characteristics, surgical details and post-operative clinical outcomes were collected from patients meeting inclusion criteria. Inclusion criteria were patients aged 18 and older, any displaced operatively treated periprosthetic femur fracture and documented 1 year follow-up. Patients with other major lower extremity trauma or ipsilateral total hip replacement were excluded. Patients were divided into 3 groups depending on the type of fixation received: Locked Plating, Retrograde Intramedullary Nailing and Distal Femoral Replacement. Documented clinical follow-up was reviewed at 2 weeks, 3 months, 6 months and 1 year following surgery. Outcome and covariate measures were assessed using basic descriptive statistics. Categorical variables, including the rate of re-operation, were compared across the three treatment groups using Fisher Exact Test.

In total, 121 patients (male: 21% / female: 79%) from 8 centers were included in our analysis. Sixty-seven patients were treated with Locked Plating, 15 with Retrograde Intramedullary Nailing, and 39 were treated with Distal Femoral Replacement. At 1 year, 64% of LP patients showed radiographic union compared to 77% in the RIMN group (p=0.747). Between the 3 groups, we did not find any significant differences in ambulation, return to work and complication rates at 6 months and 1 year (Table 1). Reoperation rates at 1 year were 27% in the LP group (17 reoperations), 16% in the DFR group (6 reoperations) and 0% in the RIMN group. These differences were not statistically significant (p=0.058).

We evaluated a large multicenter series of operatively treated periprosthetic distal femur fractures in this study. We did not find any statistically significant differences at 1 year between treatment groups in this study. There was a trend towards a lower rate of reoperation in the Retrograde Intramedullary Nailing group that should be evaluated further with prospective studies.

For any figures or tables, please contact the authors directly.

The 2020-2021 Canadian Residency Matching Service (CaRMS) match year was altered on an unprecedented scale. Visiting electives were cancelled at a national level, and the CaRMS interview tour was moved to a virtual model. These changes posed a significant challenge to both prospective students and program directors (PDs), requiring each party to employ alternative strategies to distinguish themselves throughout the match process. For a variety of reasons, including a decline in applicant interest secondary to reduced job prospects, the field of orthopaedic surgery was identified as vulnerable to many of these changes, creating a window of opportunity to evaluate their impacts on students and recruiting residency programs.

This longitudinal survey study was disseminated to match-year medical students (3rd and 4th year) with an interest in orthopaedic surgery, as well as orthopaedic surgery program directors. Responses to the survey were collected using an electronic form designed in Qualtrics (Qualtrics, 2021, Provo, Utah, USA). Students were contacted through social media posts, as well as by snowball sampling methods through appropriate medical student leadership intermediates. The survey was disseminated to all 17 orthopedic surgery program directors in Canada.

A pre-match and post-match iteration of this survey were designed to identify whether expectations differed from reality regarding the effect of the COVID-19 pandemic on the CaRMS match 2020-2021 process. A similar package was disseminated to Canadian orthopaedic surgery program directors pre-match, with an option to opt-in for a post-match survey follow-up. This survey had a focus on program directors’ opinions of various novel communication, recruitment, and assessment strategies, in the wake of the COVID-19 pandemic.

Students’ responses to the loss of visiting electives were negative. Despite a reduction in financial stress associated with reduced need to travel (p=0.001), this was identified as a core component of the clerkship experience. In the case of virtual interviews, students’ initial trepidation pre-CaRMS turned into a positive outlook post-CaRMS (significant improvement, p=0.009) indicating an overall satisfaction with the virtual interview format, despite some concerns about a reduction in their capacity to network. Program directors and selection committee faculty also felt positively about the virtual interview format. Both students and program directors were overwhelmingly positive about virtual events put on by both school programs and student-led initiatives to complement the CaRMS tour.

CaRMS was initially developed to facilitate the matching process for both students and programs alike. We hope to continue this tradition of student-led and student-informed change by providing three evidence-based recommendations. First, visiting electives should not be discontinued in future iterations of CaRMS if at all possible. Second, virtual interviews should be considered as an alternative approach to the CaRMS interview tour moving forward. And third, ongoing virtual events should be associated with a centralized platform from which programs can easily communicate virtual sessions to their target audience.