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.

Conferences centered around surgery suffers from gender disparity with male faculty having a more dominant presence in meetings compared to female faculty. Orthopedic Surgery possibly suffers the most from this problem of all surgical specialties, and is reflective of a gender disparity in the field. The objective of this study was to investigate the prevalence of “manels”, or male-only sessions, in eight major Orthopedic Surgery meetings hosted in 2021 and to quantify the differences in location of practice, academic position, years of practice, and research qualifications between male and female faculty.

Eight Orthopedic conferences organized by major Orthopedic associations (AAOS, COA, OTA, EFORT, AAHKS, ORS, NASS, and AOSSM) from February 2021 to November 2021 were analyzed. Meeting information was retrieved from the conference agendas, and details of chairs and speakers were obtained from Linkedin, Doximity, CPSO, personal websites, and Web of Science. Primary outcomes included: one) percentage of male faculty in all included sessions and two) overall percentage of manels. Secondary outcomes included one) percentage of male speakers and chairs in all included sessions, two) overall percentage of male-chair and male-speaker only sessions. Comparisons for outcomes were made between conferences and session topics (adult reconstruction hip, adult reconstruction knee, practice management/rehabilitation, trauma, sports, general, pediatrics, upper extremity, musculoskeletal oncology, foot and ankle, spine, and miscellaneous). Mean number of sessions for male and female were compared after being stratified into quartiles based on publications, sum of times cited, and H-indexes. Data was analyzed with non-parametric analysis, chi-square tests, or independent samples t-tests using SPSS version 28.0.0.0 with a p-value of < 0 .05 being considered statistically significant.

Of 193 included sessions, 121 (62.3%) were manels and the mean percentage of included faculty that was male was 88.9% Apart from the topics of practice management/rehabilitation and musculoskeletal oncology, male representation was very high. Additionally, most included conferences had an extremely high percentage of male representation apart from meetings hosted by the COA and ORS. Non-manel sessions had a greater mean number of chairs (p=0.006), speakers (p < 0 .001), and faculty (p < 0 .001) than manel sessions. Of 1080 total included faculty members, 960 (88.9%) were male. Male faculty were more likely to be Orthopedic surgeons than female faculty (p < 0 .001) while also more likely to hold academic rank as a professor. Mean number of sessions between male and female faculty within their respective quartiles of H-indexes, sum of times cited, and number of publications did not reach statistical significance. Mean years of practice between male and female faculty was also not significantly different.

There is a high prevalence of manels and an overall lack of female representation in Orthopedic meetings. Orthopedic associations should aim to make efforts to increase gender equity in future meetings.

While surgeon-industry relationships in orthopaedics have a critical role in advancing techniques and patient outcomes, they also present the potential for conflict of interest (COI) and increased risk of bias in surgical education. Consequently, robust processes of disclosure and mitigation of potential COI have been adopted across educational institutions, professional societies, and specialty journals. The past years have seen marked growth in the use of online video-based surgical education platforms that are commonly used by both trainees and practicing surgeons. However, it is unclear to what extent the same COI disclosure and mitigation principles are adhered to on these platforms. Thus, the purpose of the present study was to evaluate the frequency and adequacy of potential COI disclosure on orthopaedic online video-based educational platforms.

We retrospectively reviewed videos from a single, publicly-accessible online peer-to-peer orthopaedic educational video platform (VuMedi) that is used as an educational resource by a large number of orthopaedic trainees across North America. The 25 highest-viewed videos were identified for each of 6 subspecialty areas (hip reconstruction, knee reconstruction, shoulder/elbow, foot and ankle, spine and sports). A standardized case report form was developed based on the COI disclosure guidelines of the American Academy of Orthopaedic Surgery (AAOS) and the Journal of Bone and Joint Surgery. Two reviewers watched and assessed each video for presentation of any identifiable commercial products or brand names, disclosure of funding source for video, and presenter's potential conflict of interest. Additionally, presenter disclosures were cross-referenced against commercial relationships reported in the AAOS disclosure database to determine adequacy of disclosure. Any discrepancies between reviewers were resolved by consensus wherever possible, or with adjudication by a third reviewer when necessary.

Out of 150 reviewed videos, only 37 (25%) included a disclosure statement of any kind. Sixty-nine (46%) videos involved the presentation of a readily identifiable commercial orthopaedic device, implant or brand. Despite this, only 13 of these (19%) included a disclosure of any kind, and only 8 were considered adequate when compared to the presenter's disclosures in the AAOS database. In contrast, 83% of the presenters of the videos included in this study reported one or more commercial relationships in the AAOS disclosure database.

Videos of presentations given at conferences and/or academic meetings had significantly greater rates of disclosure as compared to those that were not (41% vs 14%; p=0.004). Similarly, disclosures associated with conference/meeting presentations had significantly greater rates of adequacy (21% vs 7%; p=0.018). Even so, less than half of the educational videos originating from a conference or meeting included a disclosure of any kind, and only about half of these were deemed adequate. No differences were seen in the rate of disclosures between orthopaedic subspecialties (p=0.791).

Online orthopaedic educational videos commonly involve presentation of specific, identifiable commercial products and brands, and the large majority of presenters have existing financial relationships with potential for conflict of interest. Despite this, the overall rate of disclosure of potential conflict of interest in these educational videos is low, and many of these disclosures are incomplete or inadequate. Further work is needed to better understand the impact of this low rate of disclosure on orthopaedic education both in-training and in practice.