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.

It has been established that a dedicated orthopaedic trauma room (DOTR) provides significant clinical and organizational benefits to the management of trauma patients. After-hours care is associated with surgeon fatigue, a high risk of patient complications, and increased costs related to staffing. However, hesitation due to concerns of the associated opportunity cost at the hospital leadership level is a major barrier to wide-spread adoption. The primary aim of this study is to determine the impact of dedicated orthopaedic trauma room (DOTR) implementation on operating room efficiency. Secondly, we sought to evaluate the associated financial impact of the DOTR, with respect to both after-hours care costs as well as the opportunity cost of displaced elective cases.

This was a retrospective cost-analysis study performed at a single academic-affiliated community hospital in Toronto, Canada. All patients that underwent the most frequently performed orthopedic trauma procedures (hip hemiarthroplasty, open reduction internal fixation of the ankle, femur, elbow and distal radius), over a four-year period from 2016-2019 were included. Patient data acquired for two-years prior and two-years after the implementation of a DOTR were compared, adjusting for the number of cases performed. Surgical duration and number of day-time and after-hours cases was recorded pre- and post-implementation. Cost savings of performing trauma cases during daytime and the opportunity cost of displacing elective cases by performing cases during the day was calculated. A sensitivity analysis accounting for varying overtime costs and hospital elective case profit was also performed.

1960 orthopaedic cases were examined pre- and post-DOTR. All procedures had reduced total operative time post-DOTR. After accounting for the total number of each procedure performed, the mean weighted reduction was 31.4% and the mean time saved was 29.6 minutes per surgery. The number of daytime surgical hours increased 21%, while nighttime hours decreased by 37.8%. Overtime staffing costs were reduced by $24,976 alongside increase in opportunity costs of $22,500. This resulted in a net profit of $2,476.

Our results support the premise that DOTRs improve operating room efficiency and can be cost efficient. Through the regular scheduling of a DOTR at a single hospital in Canada, the number of surgeries occurring during daytime hours increased while the number of after-hours cases decreased. The same surgeries were also completed nearly one-third faster (30 minutes per case) on average. Our study also specifically addresses the hesitation regarding potential loss of profit from elective surgeries. Notably, the savings partially stem from decreased OR time as well as decreased nurse overtime. Widespread implementation can improve patient care while still remaining financially favourable.

Single level discectomy (SLD) is one of the most commonly performed spinal surgery procedures. Two key drivers of their cost-of-care are duration of surgery (DOS) and postoperative length of stay (LOS). Therefore, the ability to preoperatively predict SLD DOS and LOS has substantial implications for both hospital and healthcare system finances, scheduling and resource allocation. As such, the goal of this study was to predict DOS and LOS for SLD using machine learning models (MLMs) constructed on preoperative factors using a large North American database.

The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for SLD procedures from 2014-2019. The dataset was split in a 60/20/20 ratio of training/validation/testing based on year. Various MLMs (traditional regression models, tree-based models, and multilayer perceptron neural networks) were used and evaluated according to 1) mean squared error (MSE), 2) buffer accuracy (the number of times the predicted target was within a predesignated buffer), and 3) classification accuracy (the number of times the correct class was predicted by the models). To ensure real world applicability, the results of the models were compared to a mean regressor model.

A total of 11,525 patients were included in this study. During validation, the neural network model (NNM) had the best MSEs for DOS (0.99) and LOS (0.67). During testing, the NNM had the best MSEs for DOS (0.89) and LOS (0.65). The NNM yielded the best 30-minute buffer accuracy for DOS (70.9%) and ≤120 min, >120 min classification accuracy (86.8%). The NNM had the best 1-day buffer accuracy for LOS (84.5%) and ≤2 days, >2 days classification accuracy (94.6%). All models were more accurate than the mean regressors for both DOS and LOS predictions.

We successfully demonstrated that MLMs can be used to accurately predict the DOS and LOS of SLD based on preoperative factors. This big-data application has significant practical implications with respect to surgical scheduling and inpatient bedflow, as well as major implications for both private and publicly funded healthcare systems. Incorporating this artificial intelligence technique in real-time hospital operations would be enhanced by including institution-specific operational factors such as surgical team and operating room workflow.

Knee arthroscopy with meniscectomy is the third most common Orthopaedic surgery performed after TKA and THA, comprising up to 16.6% of all procedures. The efficiency of Orthopaedic care delivery with respect to waiting times and systemic costs is extremely concerning. Canadian Orthopaedic patients experience the longest wait times of any G7 country, yet perioperative surgical care constitutes a significant portion of a hospital's budget.

In-Office Needle Arthroscopy (IONA) is an emerging technology that has been primarily studied as a diagnostic tool. Recent evidence shows that it is a cost-effective alternative to hospital- and community-based MRI with comparable accuracy. Recent procedure guides detailing IONA medial meniscectomy suggest a potential node for OR diversion. Given the high case volume of knee arthroscopy as well as the potential amenability to be diverted away from the OR to the office setting, IONA has the potential to generate considerable improvements in healthcare system efficiency with respect to throughput and cost savings. As such, the purpose of this study is to investigate the cost savings and impact on waiting times on a mid-sized Canadian community hospital if IONA is offered as an alternative to traditional operating room (OR) arthroscopy for medial meniscal tears.

In order to develop a comprehensive understanding and accurate representation of the quantifiable operations involved in the current state for medial meniscus tear care, process mapping was performed that describes the journey of a patient from when they present with knee pain to their general practitioner until case resolution. This technique was then repeated to create a second process map describing the hypothetical proposed state whereby OR diversion may be conducted utilizing IONA. Once the respective process maps for each state were determined, each process map was translated into a Dupont decision tree. In order to accurately determine the total number of patients which would be eligible for this care pathway at our institution, the OR booking scheduling for arthroscopy and meniscectomy/repair over a four year time period (2016-2020) were reviewed. A sensitivity analysis was performed to examine the effect of the number of patients who select IONA over meniscectomy and the number of revision meniscectomies after IONA on 1) the profit and profit margin determined by the MCS-Dupont financial model and 2) the throughput (percentage and number) determined by the MCS-throughput model.

Based on historic data at our institution, an average of 198 patients (SD 31) underwent either a meniscectomy or repair from years 2016-2020. Revenue for both states was similar (p = .22), with the current state revenue being $ 248,555.99 (standard deviation $ 39,005.43) and proposed state of $ 249,223.86 (SD $ 39,188.73). However, the reduction in expenses was significant (p < .0001) at 5.15%, with expenses in the current state being $ 281,415.23 (SD $ 44,157.80) and proposed state of $ 266,912.68 (SD $ 42,093.19), representing $14,502.95 in savings. Accordingly, profit improvement was also significant (p < .0001) at 46.2%, with current state profit being $ (32,859.24) (SD $ 5,153.49) and proposed state being $ (17,678.82) (SD $ 2,921.28). The addition of IONA into the care pathway of the proposed state produced an average improvement in throughput of 42 patients (SD 7), representing a 21.2% reduction in the number of patients that require an OR procedure. Financial sensitivity analysis revealed that the proposed state profit was higher than the current state profit if as few as 10% of patients select IONA, with the maximum revision rate needing to remain below 40% to achieve improved profits.

The most important finding from this study is that IONA is a cost-effective alternative to traditional surgical arthroscopy for medial meniscus meniscectomy. Importantly, IONA can also be used as a diagnostic procedure. It is shown to be a cost-effective alternative to MRI with similar diagnostic accuracy. The role of IONA as a joint diagnostic-therapeutic tool could positively impact MRI waiting times and MRI/MRA costs, and further reduce indirect costs to society. Given the well-established benefit of early meniscus treatment, accelerating both diagnosis and therapy is bound to result in positive effects.

Most cost containment efforts in public health systems have focused on regulating the use of hospital resources, especially operative time. As such, attempting to maximize the efficiency of limited operative time is important. Typically, hospital operating room (OR) scheduling of time is performed in two tiers: 1) master surgical scheduling (annual allocation of time between surgical services and surgeons) and 2) daily scheduling (a surgeon's selection of cases per operative day). Master surgical scheduling is based on a hospital's annual case mix and depends on the annual throughput rate per case type. This throughput rate depends on the efficiency of surgeons’ daily scheduling. However, daily scheduling is predominantly performed manually, which requires that the human planner simultaneously reasons about unknowns such as case-specific length-of-surgery and variability while attempting to maximize throughput. This often leads to OR overtime and likely sub-optimal throughput rate. In contrast, scheduling using mathematical and optimization methods can produce maximum systems efficiency, and is extensively used in the business world. As such, the purpose of our study was to compare the efficiency of 1) manual and 2) optimized OR scheduling at an academic-affiliated community hospital representative of most North American centres.

Historic OR data was collected over a four year period for seven surgeons. The actual scheduling, surgical duration, overtime and number of OR days were extracted. This data was first configured to represent the historic manual scheduling process. Following this, the data was then used as the input to an integer linear programming model with the goal of determining the minimum number of OR days to complete the same number of cases while not exceeding the historic overtime values. Parameters included the use of a different quantile for each case type's surgical duration in order to ensure a schedule within five percent of the historic overtime value per OR day.

All surgeons saw a median 10% (range: 9.2% to 18.3%) reduction in the number of OR days needed to complete their annual case-load compared to their historical scheduling practices. Meanwhile, the OR overtime varied by a maximum of 5%. The daily OR configurations differed from historic configurations in 87% of cases. In addition, the number of configurations per surgeon was reduced from an average of six to four.

Our study demonstrates a significant increase in OR throughput rate (10%) with no change in operative time required. This has considerable implications in terms of cost reduction, surgical wait lists and surgeon satisfaction. A limitation of this study was that the potential gains are based on the efficiency of the pre-existing manual scheduling at our hospital. However, given the range of scenarios tested, number of surgeons included and the similarity of our hospital size and configuration to the majority of North American hospitals with an orthopedic service, these results are generalizable. Further optimization may be achieved by taking into account factors that could predict case duration such as surgeon experience, patients characteristics, and institutional attributes via machine learning.

Total knee and hip arthroplasty (TKA and THA) are two of the highest volume and resource intensive surgical procedures. Key drivers of the cost of surgical care are duration of surgery (DOS) and postoperative inpatient length of stay (LOS). The ability to predict TKA and THA DOS and LOS has substantial implications for hospital finances, scheduling and resource allocation. The goal of this study was to predict DOS and LOS for elective unilateral TKAs and THAs using machine learning models (MLMs) constructed on preoperative patient factors using a large North American database.

The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for elective unilateral TKA and THA procedures from 2014-2019. The dataset was split into training, validation and testing based on year. Multiple conventional and deep MLMs such as linear, tree-based and multilayer perceptrons (MLPs) were constructed. The models with best performance on the validation set were evaluated on the testing set. Models were evaluated according to 1) mean squared error (MSE), 2) buffer accuracy (the number of times the predicted target was within a predesignated buffer of the actual target), and 3) classification accuracy (the number of times the correct class was predicted by the models). To ensure useful predictions, the results of the models were compared to a mean regressor.

A total of 499,432 patients (TKA 302,490; THA 196,942) were included. The MLP models had the best MSEs and accuracy across both TKA and THA patients. During testing, the TKA MSEs for DOS and LOS were 0.893 and 0.688 while the THA MSEs for DOS and LOS were 0.895 and 0.691. The TKA DOS 30-minute buffer accuracy and ≤120 min, >120 min classification accuracy were 78.8% and 88.3%, while the TKA LOS 1-day buffer accuracy and ≤2 days, >2 days classification accuracy were 75.2% and 76.1%. The THA DOS 30-minute buffer accuracy and ≤120 min, >120 min classification accuracy were 81.6% and 91.4%, while the THA LOS 1-day buffer accuracy and ≤2 days, >2 days classification accuracy were 78.3% and 80.4%. All models across both TKA and THA patients were more accurate than the mean regressors for both DOS and LOS predictions across both buffer and classification accuracies.

Conventional and deep MLMs have been effectively implemented to predict the DOS and LOS of elective unilateral TKA and THA patients based on preoperative patient factors using a large North American database with a high level of accuracy. Future work should include using operational factors to further refine these models and improve predictive accuracy. Results of this work will allow institutions to optimize their resource allocation, reduce costs and improve surgical scheduling.

In the current healthcare environment, cost containment has become more important than ever. Perioperative services are often scrutinized as they consume more than 30% of North American hospitals’ budgets. The procurement, processing, and use of sterile surgical inventory is a major component of the perioperative care budget and has been recognized as an area of operational inefficiency. Although a recent systematic review supported the optimization of surgical inventory reprocessing as a means to increase efficiency and eliminate waste, there is a paucity of data on how to actually implement this change. A well-studied and established approach to implementing organizational change is Kotter's Change Model (KCM). The KCM process posits that organizational change can be facilitated by a dynamic 8-step approach and has been increasingly applied to the healthcare setting to facilitate the implementation of quality improvement (QI) interventions. We performed an inventory optimization (IO) to improve inventory and instrument reprocessing efficiency for the purpose of cost containment using the KCM framework. The purpose of this quality improvement (QI) project was to implement the IO using KCM, overcome organizational barriers to change, and measure key outcome metrics related to surgical inventory and corresponding clinician satisfaction. We hypothesized that the KCM would be an effective method of implementing the IO.

This study was conducted at a tertiary academic hospital across the four highest-volume surgical services - Orthopedics, Otolaryngology, General Surgery, and Gynecology. The IO was implemented using the steps outlined by KCM (Figure 1): 1) create coalition, 2) create vision for change, 3) establish urgency, 4) communicate the vision, 5) empower broad based action, 6) generate general short term wins, 7) consolidate gains, and 8) anchor change. This process was evaluated using inventory metrics - total inventory reduction and depreciation cost savings; operational efficiency metrics - reprocessing labor efficiency and case cancellation rate; and clinician satisfaction.

The implementation of KCM is described in Table 1. Total inventory was reduced by 37.7% with an average tray size reduction of 18.0%. This led to a total reprocessing time savings of 1333 hours per annum and labour cost savings of $39 995 per annum. Depreciation cost savings was $64 320 per annum. Case cancellation rate due to instrument-related errors decreased from 3.9% to 0.2%. The proportion of staff completely satisfied with the inventory was 1.7% pre-IO and 80% post-IO.

This was the first study to show the success of applying KCM to facilitate change in the perioperative setting with respect to surgical inventory. We have outlined the important organizational obstacles faced when making changes to surgical inventory. The same KCM protocol can be followed for optimization processes for disposable versus reusable surgical device purchasing or perioperative scheduling. Although increasing efforts are being dedicated to quality improvement and efficiency, institutions will need an organized and systematic approach such as the KCM to successfully enact changes.

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

A common step to revision surgery for infected total knee replacement (TKR) is a thorough debridement. Whilst surgical and mechanical debridement are established as the gold standard, we investigate a novel adjuvant chemical debridement using an Acetic Acid (AA) soak that seeks to create a hostile environment for organisms, further degradation of biofilm and death of the bacteria.

We report the first orthopaedic in vivo series using AA soak as an intra-operative chemical debridement agent for treating infected TKR's. We also investigate the in vitro efficacy of AA against bacteria isolated from infected TKR's.

A prospective single surgeon consecutive series of patients with infected TKR were treated according to a standard debridement protocol. Patients in the series received sequential debridement of surgical, mechanical and finally chemical debridement with a 10 minute 3% AA soak.

In parallel, we isolated, cultured and identified bacteria from infected TKR's and assessed the in vitro efficacy of AA. Susceptibility testing was performed with AA solutions of different concentrations as well as with a control of a gentamicin sulphate disc. The effect of AA on the pH of tryptone soya was also monitored in an attempt to understand its potential mechanism of action.

Physiological responses during the AA soak were unremarkable. Intraoperatively, there were no tachycardic or arrythmic responses, any increase in respiratory rate or changes in blood pressure. This was also the case when the tourniquet was released. In addition, during the post-operative period no increase in analgesic requirements or wound complications was noted. Wound and soft tissue healing was excellent and there have not been any early recurrent infections at mean of 18 months follow up.

In vitro, zones of inhibition were formed on less than 40% of the organisms, demonstrating that AA was not directly bactericidal against the majority of the clinical isolates. However, when cultured in a bacterial suspension, AA completely inhibited the growth of the isolates at concentrations as low as 0.19%v/v.

This study has shown that the use of 3% AA soak, as part of a debridement protocol, is safe. Whilst the exact mechanism of action of acetic acid is yet to be determined, we have demonstrated that concentrations as low as 0.19%v/v in solution in vitro is sufficient to completely inhibit bacterial growth from infected TKR's.