Ceramic bearing fractures are rare events, but mandate revision and implantation of new bearings. Revisions using metal heads have been reported to lead to gross volumetric head wear (due to abrasive retained ceramic micro-debris), cobalt toxicity, multi-organ failure and death. Such complications are widely published (50+ reports), yet we know that patients continue to be put at risk. Using data from the NJR and AOANJRR, this study seeks to compare the risk of re-revision and death by revision bearing combination following a ceramic bearing fracture. Data were extracted from the NJR and AOANJRR, identifying revisions for ceramic bearing fracture. Subsequent outcomes of survival, re-revision and death were compared between revision bearing combinations (ceramic-on-ceramic, ceramic-on-polyethylene, and metal-on-polyethylene). 366 cases were available for analysis from the NJR dataset (MoP=34, CoP=112, CoC=221) and 174 from the AOANJRR dataset (MoP=17, CoP=44, CoC=113). The overall incidence rate of adverse outcome (revision or death) was 0.65 for metal heads and 0.23 for ceramic head articulations (p=0.0012) across the whole time period (NJR). Kaplan-Meir survival estimates demonstrate an increased risk of both re-revision and death where a metal head has been used vs a ceramic head following revision for ceramic fracture. There are few decisions in arthroplasty surgery that can lead to serious harm or death for our patients, but revision using a metal head following ceramic bearing fracture is one of them. This study enhances the signal of what is already known but previously only reported as inherently low-level evidence (case reports and small series) due to event rarity. Use of a metal head in revision for ceramic fracture represents an avoidable patient safety issue, which revision guidelines should seek to address

Anterior approach total hip arthroplasty (AA-THA) has a steep learning curve, with higher complication rates in initial cases. Proper surgical case selection during the learning curve can reduce early risk. This study aims to identify patient and radiographic factors associated with AA-THA difficulty using Machine Learning (ML).

Consecutive primary AA-THA patients from two centres, operated by two expert surgeons, were enrolled (excluding patients with prior hip surgery and first 100 cases per surgeon). K- means prototype clustering – an unsupervised ML algorithm – was used with two variables - operative duration and surgical complications within 6 weeks - to cluster operations into difficult or standard groups.

Radiographic measurements (neck shaft angle, offset, LCEA, inter-teardrop distance, Tonnis grade) were measured by two independent observers. These factors, alongside patient factors (BMI, age, sex, laterality) were employed in a multivariate logistic regression analysis and used for k-means clustering. Significant continuous variables were investigated for predictive accuracy using Receiver Operator Characteristics (ROC).

Out of 328 THAs analyzed, 130 (40%) were classified as difficult and 198 (60%) as standard. Difficult group had a mean operative time of 106mins (range 99–116) with 2 complications, while standard group had a mean operative time of 77mins (range 69–86) with 0 complications. Decreasing inter-teardrop distance (odds ratio [OR] 0.97, 95% confidence interval [CI] 0.95–0.99, p = 0.03) and right-sided operations (OR 1.73, 95% CI 1.10–2.72, p = 0.02) were associated with operative difficulty. However, ROC analysis showed poor predictive accuracy for these factors alone, with area under the curve of 0.56. Inter-observer reliability was reported as excellent (ICC >0.7).

Right-sided hips (for right-hand dominant surgeons) and decreasing inter-teardrop distance were associated with case difficulty in AA-THA. These data could guide case selection during the learning phase. A larger dataset with more complications may reveal further factors.

We summarise and highlight the safety concerns within the field of trauma and orthopaedic surgery with particular emphasis placed on current controversies and reforms within the United Kingdom National Health Service.

Introduction

Computer navigation is a highly sophisticated tool in orthopedic surgery for component placement in total hip arthroplasty (THA). A number of recommendations have been published. Although Lewinnek's safe-zone is the best-known among these its significance is questioned in recent years since it addresses the acetabular socket only ignoring the femoral stem. Modern target definitions consider both socket and stem and provide well-defined recommendations for complementary component positioning. We present a new small-sized hand-held imageless navigation system that implies these targets and supports the surgeon in realizing the concept of combined anteversion and combined Target-Zone (cTarget- Zone) in THA and to control leg length and offset without altering the standard surgical work-flow and we report initial results.

Purpose: To ascertain whether the methods of prone positioning we use have any influence on the incidence of perioperative critical incidents and development of postoperative liver dysfunction in our scoliosis patients.

Methods: A retrospective review of 72 patients undergoing posterior correction and fusion for scoliosis from August 2006 to November 2007. Details were recorded from anaesthetic charts, operation notes, blood results and cell salvage data.

Results: Patients ranged in age from 2 to 24 years. The methods of prone positioning were Transverse Bolsters (23), Allen Frame 4-point support (25), Lateral Bolsters (11) and the Knight Table (13). Perioperative haemodynamic instability was noted in 8% of patients on the Allen Frame, 43% on transverse bolsters, 15% on the Knight Table and 55% on lateral bolsters. Two cardiac arrests, one fatal and one with good recovery, both occurred on transverse bolsters. Of 22 other complications attributable to mechanical effects of prone positioning, 16 occurred on transverse bolsters, 4 on the Allen Frame, 1 on lateral bolsters and 1 on the Knight Table. 34% of patients had liver dysfunction postoperatively. None had been positioned on the Knight Table or lateral bolsters. There was no significant difference between the incidence of liver dysfunction associated with the Allen Frame or transverse bolsters.

Conclusion: Transverse bolsters are associated with a high number of critical incidents and should be avoided if possible.

Ethics approval – not required

Interest Statement - none

Implementation of the World Health Organisation checklists have reduced errors, however, the impact of pre-operative briefings on adverse events has not been assessed. A prospective case control study assessing the association between pre-operative briefings and minor, potentially major and major adverse events was performed in two phases. Phase one involved prospective data collection for trauma and orthopaedic lists over 2 weeks. Changes were implemented and following this, the study was repeated (phase two). 41 lists were audited during phase one and 47 lists in phase two. Adequate pre-operative briefings were performed in 10/41 lists (24%) in phase one. There was a significant association between the occurrences of intra-operative adverse events (n=37) when a briefing was not performed (p=<0.01), and when a briefing was performed incompletely (p=0.01). In phase two, after staff re-education and policy change, briefings were found to be adequate in 38/47 lists (81%) with the occurrence of only three minor adverse events. Team familiarity also improved significantly (p=0.02). Inadequate pre-operative briefings are associated with increased minor adverse events and are detrimental to team familiarity. On the basis of our findings we recommend that all surgical units perform pre-operative briefings.

The World Health Organization (WHO) launched the first Global Patient Safety Challenge in 2005 and introduced the ‘5 moments of hand hygiene’ in 2009 in an attempt to reduce the burden of health care associated infections. Many NHS trusts in England adopted this model of hand hygiene, which prompts health care workers to clean their hands at five distinct stages of caring for the patient. Our review analyses the scientific foundation for the five moments of hand hygiene and explores the evidence, as referenced by WHO, to support these recommendations. We found no strong scientific support for this regime of hand hygiene as a means of reducing health care associated infections. Consensus-based guidelines based on weak scientific foundations should be assessed carefully to prevent shifting the clinical focus from more important issues and to direct limited resources more effectively. We recommend caution in the universal adoption of the WHO ‘5 moments of hand hygiene’ by orthopaedic surgeons and other health care workers and emphasise the need for evidence-based principles when adopting hospital guidelines aimed at promoting excellence in clinical practice

Aims

Joint registries classify all further arthroplasty procedures to a knee with an existing partial arthroplasty as revision surgery, regardless of the actual procedure performed. Relatively minor procedures, including bearing exchanges, are classified in the same way as major operations requiring augments and stems. A new classification system is proposed to acknowledge and describe the detail of these procedures, which has implications for risk, recovery, and health economics.

The February 2024 Hip & Pelvis Roundup. 360. looks at: Trial of vancomycin and cefazolin as surgical prophylaxis in arthroplasty; Is preoperative posterior femoral neck tilt a risk factor for fixation failure? Cemented versus uncemented hemiarthroplasty for displaced intracapsular fractures of the hip; Periprosthetic fractures in larger hydroxyapatite-coated stems: are collared stems a better alternative for total hip arthroplasty?; Postoperative periprosthetic fracture following hip arthroplasty with a polished taper slip versus composite beam stem; Is oral tranexamic acid as good as intravenous?; Stem design and the risk of early periprosthetic femur fractures following THA in elderly patients; Does powered femoral broaching compromise patient safety in total hip arthroplasty?

Aims. Computer-assisted 3D preoperative planning software has the potential to improve postoperative stability in total hip arthroplasty (THA). Commonly, preoperative protocols simulate two functional positions (standing and relaxed sitting) but do not consider other common positions that may increase postoperative impingement and possible dislocation. This study investigates the feasibility of simulating commonly encountered positions, and positions with an increased risk of impingement, to lower postoperative impingement risk in a CT-based 3D model. Methods. A robotic arm-assisted arthroplasty planning platform was used to investigate 11 patient positions. Data from 43 primary THAs were used for simulation. Sacral slope was retrieved from patient preoperative imaging, while angles of hip flexion/extension, hip external/internal rotation, and hip abduction/adduction for tested positions were derived from literature or estimated with a biomechanical model. The hip was placed in the described positions, and if impingement was detected by the software, inspection of the impingement type was performed. Results. In flexion, an overall impingement rate of 2.3% was detected for flexed-seated, squatting, forward-bending, and criss-cross-sitting positions, and 4.7% for the ankle-over-knee position. In extension, most hips (60.5%) were found to impinge at or prior to 50° of external rotation (pivoting). Many of these impingement events were due to a prominent ischium. The mean maximum external rotation prior to impingement was 45.9° (15° to 80°) and 57.9° (20° to 90°) prior to prosthetic impingement. No impingement was found in standing, sitting, crossing ankles, seiza, and downward dog. Conclusion. This study demonstrated that positions of daily living tested in a CT-based 3D model show high rates of impingement. Simulating additional positions through 3D modelling is a low-cost method of potentially improving outcomes without compromising patient safety. By incorporating CT-based 3D modelling of positions of daily living into routine preoperative protocols for THA, there is the potential to lower the risk of postoperative impingement events. Cite this article: Bone Jt Open 2023;4(6):416–423

Aims. Restarting planned surgery during the COVID-19 pandemic is a clinical and societal priority, but it is unknown whether it can be done safely and include high-risk or complex cases. We developed a Surgical Prioritization and Allocation Guide (SPAG). Here, we validate its effectiveness and safety in COVID-free sites. Methods. A multidisciplinary surgical prioritization committee developed the SPAG, incorporating procedural urgency, shared decision-making, patient safety, and biopsychosocial factors; and applied it to 1,142 adult patients awaiting orthopaedic surgery. Patients were stratified into four priority groups and underwent surgery at three COVID-free sites, including one with access to a high dependency unit (HDU) or intensive care unit (ICU) and specialist resources. Safety was assessed by the number of patients requiring inpatient postoperative HDU/ICU admission, contracting COVID-19 within 14 days postoperatively, and mortality within 30 days postoperatively. Results. A total of 1,142 patients were included, 47 declined surgery, and 110 were deemed high-risk or requiring specialist resources. In the ten-week study period, 28 high-risk patients underwent surgery, during which 68% (13/19) of Priority 2 (P. 2. , surgery within one month) patients underwent surgery, and 15% (3/20) of P. 3. (< three months) and 16% (11/71) of P. 4. (> three months) groups. Of the 1,032 low-risk patients, 322 patients underwent surgery. Overall, 21 P. 3. and P. 4. patients were expedited to ‘Urgent’ based on biopsychosocial factors identified by the SPAG. During the study period, 91% (19/21) of the Urgent group, 52% (49/95) of P. 2. , 36% (70/196) of P. 3. , and 26% (184/720) of P. 4. underwent surgery. No patients died or were admitted to HDU/ICU, or contracted COVID-19. Conclusion. Our widely generalizable model enabled the restart of planned surgery during the COVID-19 pandemic, without compromising patient safety or excluding high-risk or complex cases. Patients classified as Urgent or P. 2. were most likely to undergo surgery, including those deemed high-risk. This model, which includes assessment of biopsychosocial factors alongside disease severity, can assist in equitably prioritizing the substantial list of patients now awaiting planned orthopaedic surgery worldwide. Cite this article: Bone Jt Open 2021;2(2):134–140

The Nottingham Hip Fracture Score (NHFS) was developed in 2007 as a predictor of 30-day mortality after hip fracture surgery following a neck of femur fracture. The National Hip Fracture Database is the standard used which calculated their own score using national data. The NHF score for 30-day mortality was calculated for 50 patients presenting with a fractured neck femur injury between January 2020 to March 2020. A score <5 was classified as low risk and >/=5 as high risk. Aim was to assess the accuracy in calculating the Nottingham Hip Fracture Score against the National Hip Fracture Database. To explore whether it should it be routinely included during initial assessment to aid clinical management?. There was an increase in the number of mortalities observed in patients who belonged to the high-risk group (>=5) compared to the low risk group. COVID-19 positive patients had worse outcomes with average 30-day mortality of 6.78 compared to the average of 6.06. GEH NHF score per month showed significant accuracy against the NHFD scores. The identification of high-risk groups from their NHF score can allow for targeted optimisations and elucidation of risk factors easily gathered at the point of hospitalisation. The NHFS is a valuable tool and useful predictor to stratify the risk of 30-day mortality and 1-year mortality after hip fracture surgery. Inclusion of the score should be considered as mandatory Trust policy for neck of femur fracture patients to aid clinical management and improve patient safety overall

As Total Hip Replacement (THR) rates increase healthcare providers have sought to reduce costs, while at the same time improving patient safety and satisfaction. Up to 50% of patients may be appropriate for Day Case THR, and in appropriately selected patients’ studies show no increase in complication rate while affording a significant cost saving and maintaining a high rate of patient satisfaction. Despite the potential benefits, levels of adoption of Day Case THR vary. A common cause for this is the perception that doing so would require the adoption of new surgical techniques, implants, or theatre equipment. We report on a Day-Case THR pathway in centres with an established and well-functioning Enhanced Recovery pathway, utilising the posterior approach and standard implants and positioning. We prospectively collected the data on consecutive THRs performed by a single surgeon between June 2018 and July 2021. A standardised anaesthetic regimen using short acting spinal was used. Surgical data included approach, implants, operative time, and estimated blood loss. Outcome data included time of discharge from hospital, post operative complications, readmissions, and unscheduled health service attendance. Data was gathered on 120 consecutive DCTHRs in 114 patients. 93% of patients were successfully discharged on the day of surgery. Four patients required re-admission: one infection treated with DAIR, one dislocation, one wound ooze admitted for a day of monitoring, one gastric ulcer. One patient had a short ED attendance for hypertension. Our incidence of infection, dislocation and wound problems were similar to those seen in inpatient THR. Out data show that the widely used posterior approach using standard positioning and implants can be used effectively in a Day Case THR pathway, with no increase in failure of same-day discharge or re-admission to hospital

Background. Cauda Equina Syndrome (CES) needs to be diagnosed and managed promptly to ensure the best outcome for patients. Our current spinal service has been centralised, with referrals currently delivered via an online system. This means that patients aren't seen by spinal specialists until confirmed radiological diagnosis. To ensure patient safety, we must make sure that our CES pathway is as robust as possible. Methods & Results. A Google Forms questionnaire was emailed to various health professionals involved in the CES patient journey throughout the Lancashire & South Cumbria region. Participants were asked to identify problems with our current pathway and to provide possible solutions for improvement. 64 responses were received from 5 different departments throughout 6 NHS employers: 21 (33%) consultants, 6 (9%) middle grade doctors, 31 physiotherapists (48%), 3 (5%) GPs and 3 (5%) others. Many common themes were identified: the need to improve CES education to both referrers and patients (22% responses), addressing the issue of scan availability (39% responses), the need for a clearer pathway for GPs (26% responses) among others. Participants were asked to rate their confidence in the management of both suspected (mean=7.6 +/−2.3) and diagnosed CES (mean=8.0 +/− 2.0). Discussion. These results have made it evident that there is a need for improvement to our current CES pathway at all levels. Our current system is overloaded with poor referrals that backlog the MRI scanner, leading to delays. Providing training for referrers in the first instance may improve things, however a more thorough overhaul of the pathway is required. Conflicts of interest: No conflicts of interest. Sources of funding: No funding obtained

Simulation use in training is rapidly becoming a mainstay educational tool seen to offer perceived benefits of a safe environment for repeated practice and learning from errors without jeopardising patient safety. However, there is currently little evidence addressing the trainees’ perspectives and attitudes of simulation training, particularly in comparison with trainers and the educational community. This study investigates orthopaedic trainees’ and trainers’ conceptions of learning from simulation-based training, exploring whether the orthopaedic community are ‘on the same page’, with respect to each other and the educational community. Qualitative research in the form of semi-structured interviews is used to identify commonalities and differences between trainee and trainer conceptions, based on respective experiences and expectations, and suggests ways of enhancing collaboration between stakeholders to achieve better alignment of conceptions. The research revealed that orthopaedic trainees and trainers conceive key themes in a similar manner: supporting the role of simulation in developing the ‘pre-trained novice’ as opposed to skill refinement or maintenance; attributing greater importance to non-technical rather than technical skills development using simulation; questioning the transferability to practice of learnt skills; and emphasising similar barriers to increased curriculum integration, including financing and scheduling. These conceptions are largely in contrast to those of the educational community, possibly due to differing conceptions of learning between the two communities, along with a lack of a common language in the discourse of simulation. There was some evidence of changing attitudes and positively emerging conceptions among the orthopaedic community, and capitalising on this by engaging trainers and trainees may help reconcile the differing conceptions and facilitate increasing simulation utilisation and curriculum integration. Developing a common language to make the educational more tangible to surgeons, bringing the educational closer to the surgical, may help maximise the educational benefit and shape the future of simulation use in surgical training

Neurological complications in oncological and degenerative spine surgery represent one of the most feared risks of these procedures. Multimodal intraoperative neurophysiological monitoring (IONM) mainly uses methods to detect changes in the patient's neurological status in a timely manner, thus allowing actions that can reverse neurological deficits before they become irreversible. The utopian goal of spinal surgery is the absence of neurological complications while the realistic goal is to optimize the responses to changes in neuromonitoring such that permanent deficits occur less frequently as possible. In 2014, an algorithm was proposed in response to changes in neuromonitoring for deformity corrections in spinal surgery. There are several studies that confirm the positive impact that a checklist has on care. The proposed checklist has been specifically designed for interventions on stable columns which is significantly different from oncological and degenerative surgery. The goal of this project is to provide a checklist for oncological and degenerative spine surgery to improve the quality of care and minimize the risk of neurological deficit through the optimization of clinical decision-making during periods of intraoperative stress or uncertainty. After a literature review on risk factors and recommendations for responding to IONM changes, 3 surveys were administered to 8 surgeons with experience in oncological and degenerative spine surgery from 5 hospitals in Italy. In addition, anesthesiologists, intraoperative neuro-monitoring teams, operating room nurses participated. The members participated in the optimization and final drafting of the checklist. The authors reassessed and modified the checklist during 3 meetings over 9 months, including a clinical validation period using a modified Delphi process. A checklist containing 28 items to be considered in responding to the changes of the IONM was created. The checklist was submitted for inclusion in the new recommendations of the Italian Society of Clinical Neurophysiology (SINC) for intraoperative neurophysiological monitoring. The final checklist represents the consensus of a group of experienced spine surgeons. The checklist includes the most important and high-performance items to consider when responding to IONM changes in patients with an unstable spine. The implementation of this checklist has the potential to improve surgical outcomes and patient safety in the field of spinal surgery

Superior team performance in surgery leads to fewer technical errors, reduced mortality, and improved patient outcomes. Scrub nurses are a pivotal part of this team, however they have very little structured training, leading to high levels of stress, low confidence, inefficiency, and potential for harm. Immersive virtual reality (iVR) simulation has demonstrated excellent efficacy in training surgeons. We tested the efficacy of an iVR curriculum for training scrub nurses in performing their role in an anterior approach total hip arthroplasty (AA-THA). Sixty nursing students were included in this study and randomised in a 1:1 ratio to learning the scrub nurse role for an AA-THA using either conventional training or iVR. The training was derived through expert consensus with senior surgeons, scrub nurses and industry reps. Conventional training consisted of a 1-hour seminar and 2 hours of e-learning where participants were taught the equipment and sequence of steps. The iVR training involved 3 separate hour-long sessions where participants performed the scrub nurse role with an avatar surgeon in a virtual operation. The primary outcome was their performance in a physical world practical objective assessment with real equipment. Data were confirmed parametric using the Shapiro-Wilk test and means compared using the independent samples student's t-test. 53 participants successfully completed the study (26 iVR, 27 conventional) with a mean age of 31±9 years. There were no significant differences in baseline characteristics or baseline knowledge test scores between the two groups (p>0.05). The iVR group significantly outperformed the conventionally trained group in the real-world assessment, scoring 66.9±17.9% vs 41.3±16.7%, p<0.0001. iVR is an easily accessible, low cost training modality which could be integrated into scrub nursing curricula to address the current shortfall in training. Prolonged operating times are strongly associated with an increased risk of developing serious complications. By upskilling scrub nurses, operations may proceed more efficiently which in turn may improve patient safety

Introduction. Frame HI is the #Days for device removal/cm. IM Nail HI is less relevant (31–45 D/cm). Albizzia HI was 33 D/cm (1991–2003). Patients felt fine approximately 1M after end of lengthening (EoL), resuming normal life and sports. This sometimes resulted in implants fractures (e.g. skying before bone fusion). Ideally, the full fusion should occur at the EoL. We decided to shorten the HI to reach this target, optimising all parameters. Materials & Methods. The evolution of care has been monitored over a 32-year clinical experience with a fully weight-bearing nails (Albizzia then G-nail). Monitoring was with X-rays, DEXA, blood bone activity, and in London with special 5G CBCT Scans. We implemented several changes in the Care of patients and measured them according to the ‘Five Principles’ (stability, function, ‘Roads-vascular supply’, ‘Materials-calories’ and ‘Workers-BFC’, with actions on food intake, activity levels and on muscle and bone vascular growths. Results. Preop: training (vascularity, muscle force). Op & Postop: spine morphine, IM sawing preserving BFC, controlled hypo-pressure, low hydration, 50 cm leg elevation, walking, resistance bike, full motion (drainage, muscle reactivation), discharge 3–4h postop (including bilateral). Postop daily intense gym training. POD07-21: Distraction increased to fight non-linear hyper-ossification (44–50 mm gain at POD30) +/- aided by NSAIDs. HI decreased to 12–20D/cm, sometimes 8D/cm with some ‘soft fusion’ during lengthening, hardening within 1W after EoL. Conclusions. The surgeon is not a passive X-rays observer, but has an active role in changing the healing speed and decreasing HI for patient safety. Electro/Magnetic nails (torque 1 Nm) may be clocked by bone fusion, which does not occur with the G-Nail (19 Nm). An holistic vision for patients and treatments at several levels is essential to accelerate bone healing, and to return fast to full normal life, after a short ‘lengthening parenthesis’

INTRODUCTION. Simulation plays an important role in surgical education and the ability to perfect surgical performance. Simulation can be enhanced by adding various layers of realism to the experience. Haptic feedback enhances the simulation experience by providing tactile responses and virtual reality imagery provides an immersive experience and allows for greater appreciation of three-dimensional structures. In this study, we present a proof-of-concept haptic simulator to replicate key steps of a cervical laminoplasty procedure. The technology uses affordable components and is easily modifiable so that it can be used from novice through to expert level. Custom models can be easily added ensuring the simulator can be used in a wide range of orthopaedic applications from baseline education through to day of surgery pre-operative simulation. METHOD. We used the Unity Game Engine, the 3D Systems “Touch” Haptic Feedback Device (HFD), and a Meta Quest VR headset. Our system uses a number of complex algorithms to track the shape and provide haptic feedback of a virtual bone model. This allows for simulation of various tools including a high-speed burr, Kerrison rongeur and intraoperative X-rays. RESULTS. Our simulator replicates the tactile sensations of bone-burring tasks. Although we focused on the cervical laminoplasty procedure, the system can load data from CT scans, enabling the simulation of multiple other procedures. The parts cost of our system, $10,000 NZD, is a fraction of the cost of traditional surgical simulators. DISCUSSION. Our simulator reduces financial barriers to accessing orthopaedic simulators. Trainees can perform hands-on practice without compromising patient safety. The immersive nature of VR, combined with realistic haptic feedback, enables trainees to develop the dexterity and three-dimensional understanding of detailed bony work. Further refinements are needed before we can perform validation studies on our system. CONCLUSIONS. We present an affordable surgical simulator capable of simulating bony surgical procedures in a VR environment using haptic feedback technology and consumer-grade components. ACKNOWLEDGEMENTS. This research was made possible by the generosity of the Wishbone Trust

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