Improving Operating Room Efficiency: Machine Learning Approach to Predict Case-Time Duration

Quantifying the impact of surgical teams on each stage of the operating room process

Introduction

Operating room (OR) efficiency is a key factor in determining surgical healthcare costs. To enable targeted changes for improving OR efficiency, a comprehensive quantification of the underlying sources of variability contributing to OR efficiency is needed. Previous literature has focused on select stages of the OR process or on aggregate process times influencing efficiency. This study proposes to analyze the OR process in more fine-grained stages to better localize and quantify the impact of important factors.

Methods

Data spanning from 2019-2023 were obtained from a surgery center at a large academic hospital. Linear mixed models were developed to quantify the sources of variability in the OR process. The primary factors analyzed in this study included the primary surgeon, responsible anesthesia provider, primary circulating nurse, and procedure type. The OR process was segmented into eight stages that quantify eight process times, e.g., procedure duration and procedure start time delay. Model selection was performed to identify the key factors in each stage and to quantify variability.

Results

Procedure type accounted for the most variability in three process times and for 44.2% and 45.5% of variability, respectively, in procedure duration and OR time (defined as the total time the patient spent in the OR). Primary surgeon, however, accounted for the most variability in five of the eight process times and accounted for as much as 21.1% of variability. The primary circulating nurse was also found to be significant for all eight process times.

Discussion

The key findings of this study include the following. (1) It is crucial to segment the OR process into smaller, more homogeneous stages to more accurately assess the underlying sources of variability. (2) Variability in the aggregate quantity of OR time appears to mostly reflect the variability in procedure duration, which is a subinterval of OR time. (3) Primary surgeon has a larger effect on OR efficiency than previously reported in the literature and is an important factor throughout the entire OR process. (4) Primary circulating nurse is significant for all stages of the OR process, albeit their effect is small.

A novel approach to forecast surgery durations using machine learning techniques

This study presents a methodology for predicting the duration of surgical procedures using Machine Learning (ML). The methodology incorporates a new set of predictors emphasizing the significance of surgical team dynamics and composition, including experience, familiarity, social behavior, and gender diversity. By applying ML techniques to a comprehensive dataset of over 77,000 surgeries, we achieved a 24% improvement in the mean absolute error (MAE) over a model that mimics the current approach of the decision maker. Our results also underscore the critical role of surgeon experience and team composition dynamics in enhancing prediction accuracy. These advancements can lead to more efficient operational planning and resource allocation in hospitals, potentially reducing downtime in operating rooms and improving healthcare delivery.

CASEMIX study: Assessment of patient factors influencing the subprocedure duration of trauma/orthopaedic surgeries

INTRODUCTION

The social and financial burdens of the operative environment remains to be a major problem in modern society. We analyse the impact of the introduction and application of a perioperative cloud system that cross-analyzes the pre-/intraoperative risks to minimize surgical time and maximize operation theater efficiency through improved planning.

METHODS

TCC-CASEMIX© was introduced to our Department of Trauma Surgery of the University of Szeged to objectively measure intraoperative time durations according to each essential subprocedure. The study is largely divided into pre-operative assessments and intraoperative measurements. Patient data (age, sex, and ethnicity etc.) was registered preoperatively, and the expected time per each essential intraoperative step (skin incision, reduction, fixation etc.) was entered. The steps were then timed intraoperatively by surveyors, and postoperative cross analysis was performed. Our study was divided into two phases; phase 1, the surveying of general trauma / orthopedic cases, and phase two; the examination of high volume surgeries.

RESULTS

Acute cases of Open Reductions and Internal Fixation (ORIF) procedures depended heavily on the presentation of the fracture, and no clear correlations in the risk factors were found. Arthroscopies were a short, high-volume procedure, but there was a large difference between the surgeon's estimates and the operation duration. In high volume surgeries, although individual factors only slightly influenced surgical duration, patient cohort stratification led to a better understanding of factors that impact surgeries, namely the combination of BMI and surgeon years of experience. While the average (Intraoperative Duration) seemed to increase with BMI, younger surgeons were more influenced by the patients BMI.

CONCLUSION

A data filtering algorithm-assisted cloud system can be a reliable way to facilitate the planning of operating theater schedules. Patient stratification according to BMI and surgeon years of experience seems to affect intraoperative duration significantly, and the understanding of the risks and intraoperative steps has the potential to forecast surgeries with high precision.

Preovulatory progesterone levels are the top indicator for ovulation prediction based on machine learning model evaluation: a retrospective study

BACKGROUND

Accurately predicting ovulation timing is critical for women undergoing natural cycle-frozen embryo transfer. However, the precise predicting of the ovulation timing remains challenging due to the lack of consensus among different clinics regarding the definition of this significant event.

OBJECTIVE

To compare the effectiveness of preovulatory serum progesterone levels (P4) versus luteinizing hormone levels (LH) in predicting ovulation time using two machine learning models.

METHODS

771 patients who underwent autologous natural cycle-frozen embryo transfer between January 2015 and February 2022 were recruited. Utilizing variables including follicle diameters, preovulatory serum levels of LH, E2, and P4, two machine learning models were constructed to predict the ovulation time, the importance of the variables in predicting ovulation timing was further ranked.

RESULTS

Two machine learning models have the capability to accurately predict the timing of ovulation, specifically within 72, 48, or 24 h. The overall accuracy rates of the validation dataset, as determined by the classification trees and random forest models, were found to be 78.83% and 85.28% respectively. Notably, when predicting ovulation within 24 h, the accuracy rate of P4 ≥ 0.65ng/ml exceeded 92%. Furthermore, it was important to consider LH or E2 levels in conjunction with P4 when assessing ovulation timing in cases where P4<0.65ng/ml.

CONCLUSIONS

Preovulatory serum P4 levels are better predictors of ovulation timing than LH levels and could be used as an alternative in clinical settings, and the model we developed can be used to pinpoint the day of ovulation. Ongoing research and advancements in technology are anticipated to enhance and refine the ovulation method.

Variability and relative contribution of surgeon- and anesthesia-specific time components to total procedural time in cardiac surgery

BACKGROUND

Decreasing variability in time-intensive tasks during cardiac surgery may reduce total procedural time, lower costs, reduce clinician burnout, and improve patient access. The relative contribution and variability of surgeon control time (SCT) and anesthesia control time (ACT) to total procedural time is unknown.

METHODS

A total of 669 patients undergoing coronary artery bypass graft (CABG) surgery were enrolled. Using linear regression, we estimated adjusted SCTs and ACTs, controlling for patient and procedural covariates. The primary endpoint compared overall SCTs and ACTs. The secondary endpoint compared the variability in adjusted SCTs and ACTs. Sensitivity analyses quantified the relative importance of the specific surgeon and anesthesiologist in the adjusted linear models.

RESULTS

The median SCT was 4.1 hours (interquartile range [IQR], 3.4-4.9 hours) compared to a median ACT of 1.0 hours (IQR, 0.8-1.2 hours; P < .001). Using linear regression, the variability in adjusted SCT among surgeons (range, 1.8 hours) was 3.5-fold greater than the variability in adjusted ACT among anesthesiologists (range, 0.5 hour; P < .001). The specific surgeon and anesthesiologist accounted for 50% of the explanatory power of the predictive model (P < .001).

CONCLUSIONS

SCT variability is significantly greater than ACT variability and is strongly associated with the surgeon performing the procedure. Although these results suggest that SCT variability is an attractive operational target, further studies are needed to determine practitioner specific and modifiable attributes to reduce variability and improve efficiency.

Artificial Intelligence in Perioperative Care: Opportunities and Challenges

Artificial intelligence (AI) applications have great potential to enhance perioperative care. This paper explores promising areas for AI in anesthesiology; expertise, stakeholders, and infrastructure for development; and barriers and challenges to implementation.

Bibliometric Research on Surgical Scheduling Management from the Perspective of Web of Science

Objective

Reasonable surgical scheduling management is crucial to optimize the utilization rate of operating room. This study aims to understand the context, frontier and hot spots of surgical scheduling management research, in order to provide reference for surgical scheduling optimization.

Methods

Literature on operation scheduling management collected in Web of Science core collection database was searched from the database establishment to June 21, 2023. HisCite Pro 2.1 software was used to analyze the publication time, countries, research institutions, journals, authors, keywords and highly cited papers.

Results

A total of 1383 literatures were included, and research institutions in the United States, Canada and other countries played a leading role in this field. Among them, the combination of machine algorithm and system model optimization to improve the accuracy of surgical duration prediction is the future research focus in this field.

Conclusion

Improving operation efficiency is one of the key issues in operating room management. Managers should find the best operation scheduling plan from a more detailed and comprehensive perspective to improve operation efficiency.

First Reported Series of Cerebral Angiography Performed at an Outpatient Center: Safety and Satisfaction Results

BACKGROUND AND OBJECTIVE

Ambulatory surgery centers (ASCs) are increasingly common venues for same-day neurosurgical procedures, allowing for cost-effective, high-quality patient care. We present the first and largest series of patients undergoing diagnostic cerebral angiography at an ASC to demonstrate the effectiveness, safety, and efficiency of outpatient endovascular care.

METHODS

We retrospectively reviewed data for consecutive patients who underwent diagnostic cerebral angiography at our ASC between January 1, 2024, and May 29, 2024. Data collected included vascular access approach, procedural duration, turnover time, and periprocedural complications. Using a standardized 2-week postprocedural survey, patients were asked to provide comments and rate their subjective satisfaction from a 1 to 5 scale, with "5" being completely satisfied. All cases were performed with a physician team comprising 1 attending neuroendovascular neurosurgery and 1 neuroendovascular fellow present. Fentanyl and midazolam were administered for conscious sedation in all cases.

RESULTS

Among the 67 patients included in this series, the mean procedural duration was 29.4 ± 8.6 minutes. The mean turnover time was 13.7 ± 3.6 minutes. Between transradial (46 of 67 [68.7%]) and transfemoral (21 of 67 [31.3%]) access site approaches, there were no statistically significant differences in mean procedural duration (29.4 ± 8.0 vs 29.2 ± 9.9 minutes, respectively; P = .72) or turnover time (14.0 ± 3.9 vs 12.9 ± 2.8 minutes, respectively; P = .4). No complications occurred periprocedurally or within the 2-week follow-up period. A total of 48 (71.6%) of 67 patients responded to the postprocedural survey, all of whom unanimously reported a score of "5."

CONCLUSION

We found that diagnostic cerebral angiography performed at our ASC was safe and effective for patient care. In addition, all survey respondents (71.6% of those provided the survey) reported highest levels of satisfaction. The integration of neuroendovascular procedures into ASCs potentially offers a cost-effective and highly efficient option in an evolving economic landscape.

The Use of Artificial Intelligence for Orthopedic Surgical Backlogs Such as the One Following the COVID-19 Pandemic: A Narrative Review

➤ The COVID-19 pandemic created a persistent surgical backlog in elective orthopedic surgeries. ➤ Artificial intelligence (AI) uses computer algorithms to solve problems and has potential as a powerful tool in health care. ➤ AI can help improve current and future orthopedic backlogs through enhancing surgical schedules, optimizing preoperative planning, and predicting postsurgical outcomes. ➤ AI may help manage existing waitlists and increase efficiency in orthopedic workflows.

Specific Factors Affecting Operating Room Efficiency: An Analysis of Case Time Estimates

PURPOSE

Operating room (OR) efficiency has an impact on surgeon productivity and patient experience. Accuracy of case duration estimation is important to optimize OR efficiency. The purpose of this study was to identify factors associated with inaccurate case time estimates in outpatient hand surgery. A better understanding of these findings may help to improve OR efficiency and scheduling.

METHODS

All outpatient hand surgical cases from 2018 to 2019 were reviewed. Poorly-estimated cases (i.e., poor scheduling accuracy) were defined as those cases where the actual operative time differed from the predicted time by >50% (either quicker by >50% or slower by >50% than the predicted time). The percentages of poorly-estimated cases were analyzed, categorized, and compared by surgeon, procedure type, and scheduled case length.

RESULTS

A total of 6,620 cases were identified. Of 1,107 (16.7%) cases with poorly estimated case durations, 75.2% were underestimated. There was no difference in the likelihood of poor estimation related to start time. Well-estimated cases tended to have longer scheduled case duration, but shorter realized case duration and surgical time. Our systems analysis identified specific surgeons and procedures as predictable outliers. Cases scheduled for 15-30 minutes frequently were inaccurate, whereas cases scheduled for 30-45 and 106-120 minutes had accurate estimates.

CONCLUSIONS

The accuracy of case time estimations in a standard outpatient hand surgery practice is highly variable. Nearly one-fifth of outpatient hand surgery case durations are poorly estimated, and inaccurate case time estimation can be predicted based on surgeon, procedure type, and case time.

CLINICAL RELEVANCE

Maximizing OR efficiency should be a priority for surgeons and hospital systems. With multiple surgeries done per day, the efficiency of the OR has an impact on surgeon productivity and patient experience.

Determining pre-procedure fasting alert time using procedural and scheduling data

Before a medical procedure requiring anesthesia, patients are required to not eat or drink non-clear fluids for 6 h and not drink clear fluids for 2 h. Fasting durations in standard practice far exceed these minimum thresholds due to uncertainties in procedure start time. The aim of this retrospective, observational study was to compare fasting durations arising from standard practice with different approaches for calculating the timepoint at which patients are instructed to stop eating and drinking. Scheduling data for procedures performed in the cardiac catheterization laboratory of an academic hospital in Canada (January 2020 to April 2022) were used. Four approaches utilizing machine learning (ML) and simulation were used to predict procedure start times and calculate when patients should be instructed to start fasting. Median fasting duration for standard practice was 10.08 h (IQR 3.5) for both food and clear fluids intake. The best performing alternative approach, using tree-based ML models to predict procedure start time, reduced median fasting from food/non-clear fluids to 7.7 h (IQR 2) and clear liquids fasting to 3.7 h (IQR 2.4). 97.3% met the minimum fasting duration requirements (95% CI 96.9% to 97.6%). Further studies are required to determine the effectiveness of operationalizing this approach as an automated fasting alert system.

Operative Time Accuracy in the Era of Electronic Health Records: Addressing the Elephant in the Room

GOAL

Accurate prediction of operating room (OR) time is critical for effective utilization of resources, optimal staffing, and reduced costs. Currently, electronic health record (EHR) systems aid OR scheduling by predicting OR time for a specific surgeon and operation. On many occasions, the predicted OR time is subject to manipulation by surgeons during scheduling. We aimed to address the use of the EHR for OR scheduling and the impact of manipulations on OR time accuracy.

METHODS

Between April and August 2022, a pilot study was performed in our tertiary center where surgeons in multiple surgical specialties were encouraged toward nonmanipulation for predicted OR time during scheduling. The OR time accuracy within 5 months before trial (Group 1) and within the trial period (Group 2) were compared. Accurate cases were defined as cases with total length (wheels-in to wheels-out) within ±30 min or ±20% of the scheduled duration if the scheduled time is ≥ or <150 min, respectively. The study included single and multiple Current Procedural Terminology code procedures, while procedures involving multiple surgical specialties (combo cases) were excluded.

PRINCIPAL FINDINGS

The study included a total of 8,821 operations, 4,243 (Group 1) and 4,578 (Group 2), (p < .001). The percentage of manipulation dropped from 19.8% (Group 1) to 7.6% (Group 2), (p < .001), while scheduling accuracy rose from 41.7% (Group 1) to 47.9% (Group 2), (p = .0001) with a significant reduction of underscheduling percentage (38.7% vs. 31.7%, p = .0001) and without a significant difference in the percentage of overscheduled cases (15% vs. 17%, p = .22). Inaccurate OR hours were reduced by 18% during the trial period (2,383 hr vs. 1,954 hr).

PRACTICAL APPLICATIONS

The utilization of EHR systems for predicting OR time and reducing manipulation by surgeons helps improve OR scheduling accuracy and utilization of OR resources.

The impact of minimally-invasive esophagectomy operative duration on post-operative outcomes

Background

Esophagectomy, an esophageal cancer treatment mainstay, is a highly morbid procedure. Prolonged operative time, only partially predetermined by case complexity, may be uniquely harmful to minimally-invasive esophagectomy (MIE) patients for numerous reasons, including anastomotic leak, tenuous conduit perfusion and protracted single-lung ventilation, but the impact is unknown. This multi-center retrospective cohort study sought to characterize the relationship between MIE operative time and post-operative outcomes.

Methods

We abstracted multi-center data on esophageal cancer patients who underwent MIE from 2010 to 2021. Predictor variables included age, sex, comorbidities, body mass index, prior cardiothoracic surgery, stage, and neoadjuvant therapy. Outcomes included complications, readmissions, and mortality. Association analysis evaluated the relationship between predictor variables and operative time. Multivariate logistic regression characterized the influence of potential predictor variables and operative time on post-operative outcomes. Subgroup analysis evaluated the association between MIE >4 h vs. ≤4 h and complications, readmissions and survival.

Results

For the 297 esophageal cancer patients who underwent MIE between 2010 and 2021, the median operative duration was 4.8 h [IQR: 3.7-6.3]. For patients with anastomotic leak (5.1%) and 1-year mortality, operative duration was elevated above the median at 6.3 h [IQR: 4.8-8.6], p = 0.008) and 5.3 h [IQR: 4.4-6.8], p = 0.04), respectively. In multivariate logistic regression, each additional hour of operative time increased the odds of anastomotic leak and 1-year mortality by 39% and 19%, respectively.

Conclusions

Esophageal cancer is a poor prognosis disease, even with optimal treatment. Operative efficiency, a modifiable surgical variable, may be an important target to improve MIE patient outcomes.

Artificial Intelligence in Operating Room Management

This systematic review examines the recent use of artificial intelligence, particularly machine learning, in the management of operating rooms. A total of 22 selected studies from February 2019 to September 2023 are analyzed. The review emphasizes the significant impact of AI on predicting surgical case durations, optimizing post-anesthesia care unit resource allocation, and detecting surgical case cancellations. Machine learning algorithms such as XGBoost, random forest, and neural networks have demonstrated their effectiveness in improving prediction accuracy and resource utilization. However, challenges such as data access and privacy concerns are acknowledged. The review highlights the evolving nature of artificial intelligence in perioperative medicine research and the need for continued innovation to harness artificial intelligence's transformative potential for healthcare administrators, practitioners, and patients. Ultimately, artificial intelligence integration in operative room management promises to enhance healthcare efficiency and patient outcomes.

First deployment of artificial intelligence recommendations in orthopedic surgery

Scant research has delved into the non-clinical facets of artificial intelligence (AI), concentrating on leveraging data to enhance the efficiency of healthcare systems and operating rooms. Notably, there is a gap in the literature regarding the implementation and outcomes of AI solutions. The absence of published results demonstrating the practical application and effectiveness of AI in domains beyond clinical settings, particularly in the field of surgery, served as the impetus for our undertaking in this area. Within the realm of non-clinical strategies aimed at enhancing operating room efficiency, we characterize OR efficiency as the capacity to successfully perform four uncomplicated arthroplasty surgeries within an 8-h timeframe. This Community Case Study addresses this gap by presenting the results of incorporating AI recommendations at our clinical institute on 228 patient arthroplasty surgeries. The implementation of a prescriptive analytics system (PAS), utilizing supervised machine learning techniques, led to a significant improvement in the overall efficiency of the operating room, increasing it from 39 to 93%. This noteworthy achievement highlights the impact of AI in optimizing surgery workflows.

Improving preoperative prediction of surgery duration

BACKGROUND

Operating rooms (ORs) are one of the costliest units in a hospital, therefore the cumulative consequences of any kind of inefficiency in OR management lead to a significant loss of revenue for the hospital, staff dissatisfaction, and patient care disruption. One of the possible solutions to improving OR efficiency is knowing a reliable estimate of the duration of operations. The literature suggests that the current methods used in hospitals, e.g., a surgeon's estimate for the given surgery or taking the average of only five previous records of the same procedure, have room for improvement.

METHODS

We used over 4 years of elective surgery records (n = 52,171) from one of the major metropolitan hospitals in Australia. We developed robust Machine Learning (ML) approaches to provide a more accurate prediction of operation duration, especially in the absence of surgeon's estimation. Individual patient characteristics and historic surgery information attributed to medical records were used to train predictive models. A wide range of algorithms such as Extreme Gradient Boosting (XGBoost) and Random Forest (RF) were tested for predicting operation duration.

RESULTS

The results show that the XGBoost model provided statistically significantly less error than other compared ML models. The XGBoost model also reduced the total absolute error by 6854 min (i.e., about 114 h) compared to the current hospital methods.

CONCLUSION

The results indicate the potential of using ML methods for reaching a more accurate estimation of operation duration compared to current methods used in the hospital. In addition, using a set of realistic features in the ML models that are available at the point of OR scheduling enabled the potential deployment of the proposed approach.

Development, Deployment, and Implementation of a Machine Learning Surgical Case Length Prediction Model and Prospective Evaluation

OBJECTIVE

To implement a machine learning model using only the restricted data available at case creation time to predict surgical case length for multiple services at different locations.

BACKGROUND

The operating room is one of the most expensive resources in a health system, estimated to cost $22 to $133 per minute and generate about 40% of hospital revenue. Accurate prediction of surgical case length is necessary for efficient scheduling and cost-effective utilization of the operating room and other resources.

METHODS

We introduced a similarity cascade to capture the complexity of cases and surgeon influence on the case length and incorporated that into a gradient-boosting machine learning model. The model loss function was customized to improve the balance between over- and under-prediction of the case length. A production pipeline was created to seamlessly deploy and implement the model across our institution.

RESULTS

The prospective analysis showed that the model output was gradually adopted by the schedulers and outperformed the scheduler-predicted case length from August to December 2022. In 33,815 surgical cases across outpatient and inpatient platforms, the operational implementation predicted 11.2% fewer underpredicted cases and 5.9% more cases within 20% of the actual case length compared with the schedulers and only overpredicted 5.3% more. The model assisted schedulers to predict 3.4% more cases within 20% of the actual case length and 4.3% fewer underpredicted cases.

CONCLUSIONS

We created a unique framework that is being leveraged every day to predict surgical case length more accurately at case posting time and could be potentially utilized to deploy future machine learning models.

Predictive analytics for cardio-thoracic surgery duration as a stepstone towards data-driven capacity management

Effective capacity management of operation rooms is key to avoid surgery cancellations and prevent long waiting lists that negatively affect clinical and financial outcomes as well as patient and staff satisfaction. This requires optimal surgery scheduling, leveraging essential parameters like surgery duration, post-operative bed type and hospital length-of-stay. Common clinical practice is to use the surgeon's average procedure time of the last N patients as a planned surgery duration for the next patient. A discrepancy between the actual and planned surgery duration may lead to suboptimal surgery schedule. We used deidentified data from 2294 cardio-thoracic surgeries to first calculate the discrepancy of the current model and second to develop new predictive models based on linear regression, random forest, and extreme gradient boosting. The new ensamble models reduced the RMSE for elective and acute surgeries by 19% (0.99 vs 0.80, p = 0.002) and 52% (1.87 vs 0.89, p < 0.001), respectively. Also, the elective and acute surgeries "behind schedule" were reduced by 28% (60% vs. 32%, p < 0.001) and 9% (37% vs. 28%, p = 0.003), respectively. These improvements were fueled by the patient and surgery features added to the models. Surgery planners can benefit from these predictive models as a patient flow AI decision support tool to optimize OR utilization.

Impact of body mass index on surgical case durations in an academic medical center

STUDY OBJECTIVE

To investigate the association between patient body mass index (BMI) and operating room duration.

DESIGN

Retrospective cohort analysis.

SETTING

Demographic data and anesthesia/surgical times for adult surgical patients at University of Virginia Health between August 2017 and February 2019 were collected and analyzed.

PATIENTS

A total of 31,548 cases were included in the final analysis. 55% of patients were female, and 51% were classified as ASA Physical Status 2. The mean operating room (OR) duration was 144.2 min ± 112.7 (median = 118, IQR = 121). Orthopedic surgery (32%) was the most common surgery.

MEASUREMENTS

Linear mixed effects models were used to examine whether procedure intervals differed across three BMI categories (BMI < 30, 30 ≤ BMI < 40, BMI ≥ 40), considering within-surgeon correlations. Surgical times were log-transformed to correct for positive skewness.

MAIN RESULTS

The average time in the operating room was longer for patients with higher BMI (mean ± SD [median, IQR] = 139.5 ± 111.2 [113.0, IQR = 114], 150.2 ± 115.4 [125, IQR = 127], and 153.1 ± 111.1 [130, IQR = 134] for BMI < 30, 30 ≤ BMI < 40, and BMI ≥ 40), respectively. We found a 2% [95% CI = 1-3%] and 3% [95% CI = 1-5%] increase in OR time for 30 ≤ BMI < 40 and BMI ≥ 40, respectively, compared to BMI < 30, after controlling for within-surgeon correlations and covariates. The excess time was primarily determined by anesthesia times.

CONCLUSION

In an academic hospital, patients with BMI ≥ 30 required more time in the operating room than patients with BMI < 30, when controlling for confounders. This information can be incorporated into modern-day OR scheduling software, potentially resulting in more accurate case duration estimates that reduce waiting and improve OR efficiency.

Machine learning models to predict surgical case duration compared to current industry standards: scoping review

BACKGROUND

Surgical waiting lists have risen dramatically across the UK as a result of the COVID-19 pandemic. The effective use of operating theatres by optimal scheduling could help mitigate this, but this requires accurate case duration predictions. Current standards for predicting the duration of surgery are inaccurate. Artificial intelligence (AI) offers the potential for greater accuracy in predicting surgical case duration. This study aimed to investigate whether there is evidence to support that AI is more accurate than current industry standards at predicting surgical case duration, with a secondary aim of analysing whether the implementation of the models used produced efficiency savings.

METHOD

PubMed, Embase, and MEDLINE libraries were searched through to July 2023 to identify appropriate articles. PRISMA extension for scoping reviews and the Arksey and O'Malley framework were followed. Study quality was assessed using a modified version of the reporting guidelines for surgical AI papers by Farrow et al. Algorithm performance was reported using evaluation metrics.

RESULTS

The search identified 2593 articles: 14 were suitable for inclusion and 13 reported on the accuracy of AI algorithms against industry standards, with seven demonstrating a statistically significant improvement in prediction accuracy (P < 0.05). The larger studies demonstrated the superiority of neural networks over other machine learning techniques. Efficiency savings were identified in a RCT. Significant methodological limitations were identified across most studies.

CONCLUSION

The studies suggest that machine learning and deep learning models are more accurate at predicting the duration of surgery; however, further research is required to determine the best way to implement this technology.

Leveraging machine learning and prescriptive analytics to improve operating room throughput

Successful days are defined as days when four cases were completed before 3:45pm, and overtime hours are defined as time spent after 3:45pm. Based on these definitions and the 460 unsuccessful days isolated from the dataset, 465 hours, 22 minutes, and 30 seconds total overtime hours were calculated. To reduce the increasing wait lists for hip and knee surgeries, we aim to verify whether it is possible to add a 5th surgery, to the typical 4 arthroplasty surgery per day schedule, without adding extra overtime hours and cost at our clinical institution. To predict 5th cases, 301 successful days were isolated and used to fit linear regression models for each individual day. After using the models' predictions, it was determined that increasing performance to a 77% success rate can lead to approximately 35 extra cases per year, while performing optimally at a 100% success rate can translate to 56 extra cases per year at no extra cost. Overall, this shows the extent of resources wasted by overtime costs, and the potential for their use in reducing long wait times. Future work can explore optimal staffing procedures to account for these extra cases.

Machine Learning for the Prediction of Procedural Case Durations Developed Using a Large Multicenter Database: Algorithm Development and Validation Study

BACKGROUND

Accurate projections of procedural case durations are complex but critical to the planning of perioperative staffing, operating room resources, and patient communication. Nonlinear prediction models using machine learning methods may provide opportunities for hospitals to improve upon current estimates of procedure duration.

OBJECTIVE

The aim of this study was to determine whether a machine learning algorithm scalable across multiple centers could make estimations of case duration within a tolerance limit because there are substantial resources required for operating room functioning that relate to case duration.

METHODS

Deep learning, gradient boosting, and ensemble machine learning models were generated using perioperative data available at 3 distinct time points: the time of scheduling, the time of patient arrival to the operating or procedure room (primary model), and the time of surgical incision or procedure start. The primary outcome was procedure duration, defined by the time between the arrival and the departure of the patient from the procedure room. Model performance was assessed by mean absolute error (MAE), the proportion of predictions falling within 20% of the actual duration, and other standard metrics. Performance was compared with a baseline method of historical means within a linear regression model. Model features driving predictions were assessed using Shapley additive explanations values and permutation feature importance.

RESULTS

A total of 1,177,893 procedures from 13 academic and private hospitals between 2016 and 2019 were used. Across all procedures, the median procedure duration was 94 (IQR 50-167) minutes. In estimating the procedure duration, the gradient boosting machine was the best-performing model, demonstrating an MAE of 34 (SD 47) minutes, with 46% of the predictions falling within 20% of the actual duration in the test data set. This represented a statistically and clinically significant improvement in predictions compared with a baseline linear regression model (MAE 43 min; P<.001; 39% of the predictions falling within 20% of the actual duration). The most important features in model training were historical procedure duration by surgeon, the word "free" within the procedure text, and the time of day.

CONCLUSIONS

Nonlinear models using machine learning techniques may be used to generate high-performing, automatable, explainable, and scalable prediction models for procedure duration.

Improving Operating Room Efficiency Through Reducing First Start Delays in an Academic Center

BACKGROUND

Delays in operating room (OR) first-case start times can cause additional costs for hospitals, healthcare team frustration and delay in patient care. Here, a novel process improvement strategy to improving first-case start times is presented.

METHODS

First case in room start times were recorded for ORs at an academic medical center. Three interventions-automatic preoperative orders, dot phrases to permit re-creation of unavailable consent forms, and improved H&P linking to the surgical encounter-were implemented to target documentation-related delays. Monthly percentages of first-case on-time starts (FCOTS) and time saved were compared with the "preintervention" time period, and total cost savings were estimated.

RESULTS

During the first 3-months after implementation of the interventions, the percentage of FCOTS improved from an average of 36.7%-52.7%. Total time savings across all ORs over the same time period was found to be 55.63 hours, which is estimated to have saved a total of $121,834.52 over the 3-month interventional period.

CONCLUSIONS

By implementing multiple quality improvement interventions, delays to first start in room OR cases can be meaningfully reduced. Quality improvement protocols targeted toward root causes of OR delays can be a significant driver to reduce healthcare costs.

Accurate Operative Time Prediction in Thyroid Surgery: A Rural Tertiary Care Facility Experience

OBJECTIVE

To determine whether surgeons can estimate thyroid operative time more accurately than a system-generated average time estimate.

METHODS

Four otolaryngologists at a single institution with extensive endocrine surgery experience were asked to predict their operative times for all eligible thyroid surgeries. These estimates were compared to system-generated operative time predications based on averaging the surgeon's previous 10 cases with the same Current Procedural Terminology code. The surgeon-generated estimations and system-generated estimations were then compared to each other and the actual operative time.

RESULTS

A final sample of 73 cases was used for all analyses. Average age was 51 years old and the majority of patients were female. Surgeon-generated operative time estimates were significantly more accurate than system-generated estimates based on time averaging (P < .001). These findings were consistent across each surgeon individually and within each procedure type (hemithyroidectomy and total thyroidectomy). These findings had a power of over 99% based on mean differences.

CONCLUSION

As the financial center of modern hospitals, an efficient operating room is integral to economic success. Improving the precision of operative time estimation reduces costly unplanned staff overtime, canceled cases, and underutilization. Our research at a rural tertiary care center shows that experienced thyroid surgeons can substantially reduce the error of estimating thyroid operative times by considering individual patient characteristics. Although no objective variables have so far been identified to correlate with thyroid operative time, surgeon-generated operative time estimation is significantly more accurate than a generic system approach of averaging previous operative times.

A Comparison of Surgeon Estimated Times and Actual Operative Times in Pediatric Dental Rehabilitation under General Anesthesia. A Retrospective Study

This retrospective study aimed to compare the accuracy of the pediatric dental surgeon's estimated operative times for dental rehabilitation under general anesthesia (DRGA) in pediatric patients. This study population included 674 pediatric patients who underwent DRGA at the study facility between January 2022 and December 2022, using convenience sampling to select patients who met our inclusion criteria. Data were collected from electronic medical and anesthesia records based on several factors, including patient-related factors such as age and gender, surgeon-related factors such as rank and experience, and anesthesia-related factors such as induction and recovery time (in minutes). This study highlights a significant difference between the surgeon's estimated time (SET) and actual operative time (AOT) for pediatric DRGA procedures, with a mean difference of 19.28 min (SD = 43.17, p < 0.0001), indicating a tendency for surgeons to overestimate surgery time. Surgical procedure time was the strongest predictor of this discrepancy, with an R square value of 0.427 and a significant p-value of 0.000. Experience with surgeons, anesthesia induction, and recovery time were also significant predictors. Meanwhile, age, gender, and rank of surgeons did not significantly predict the difference between SET and AOT. Therefore, the study suggests that surgeons should adjust their estimates for pediatric DRGA procedures, specifically emphasizing a more accurate estimation of surgery time, to ensure adequate resource allocation and patient outcomes.

Assessing the Precision of Surgery Duration Estimation: A Retrospective Study

Background and Objectives

The operating room (OR) is considered the highest source of cost and earnings. Therefore, measuring OR efficiency, which means how time and resources are allocated precisely for their intended purposes in the operating room is crucial. Both overestimation and underestimation negatively impact OR efficiency Therefore, hospitals defined metrics to Measuring OR Effeciency. Many studies have discussed OR efficiency and how surgery scheduling accuracy plays a vital role in increasing OR efficiency. This study aims to evaluate OR efficiency using surgery duration accuracy.

Methods

This retrospective, quantitative study was conducted at King Abdulaziz Medical City. We extracted data on 97,397 surgeries from 2017 to 2021 from the OR database. The accuracy of surgery duration was identified by calculating the duration of each surgery in minutes by subtracting the time of leaving the OR from the time of entering the OR. Based on the scheduled duration, the calculated durations were categorized as either underestimation or overestimation. Descriptive and bivariate analyses (Chi-square test) were performed using the Statistical Package for the Social Sciences (SPSS) software.

Results

Sixty percent out of the 97,397 surgeries performed were overestimated compared to the time scheduled by the surgeons. Patient characteristics, surgical division, and anesthesia type showed statistically significant differences (p <0.05) in their OR estimation.

Conclusion

Significant proportion of procedures have overestimated. This finding provides insight into the need for improvement.

Recommendations

It is recommended to enhance the surgical scheduling method using machine learning (ML) models to include patient characteristics, department, anesthesia type, and even the performing surgeon increases the accuracy of duration estimation. Then, evaluate the performance of an ML model in future studies.

Surgical procedure prediction using medical ontological information

BACKGROUND AND OBJECTIVE

Predicting the duration of surgical procedures is an important step in scheduling operating rooms. Many factors have been shown to influence the duration of a procedure, in this research we aim to use medical ontological information to improve the predictions.

METHODS

This paper presents two methods for incorporating the medical information about a surgical procedure into the prediction of the duration of the procedure. The first method uses the Systematised Nomenclature of Medicine Clinical Terms to relate different procedures to each other. The second uses simple text fragments. The relationships between types of procedures are included in a regression model for the procedure duration. These methods are applied to data from New Zealand healthcare facilities and the accuracy of the estimations of the durations is compared. In addition a simulation of scheduling the procedures in an operating room is performed.

RESULTS

It is shown that both of the methods provide an improvement in the prediction of procedure durations. When compared to a traditional categorical encoding, the ontological information provides an improvement in the continuous ranked probability scores of the prediction of procedure durations from 18.4 min to 17.1 min, and from 25.3 to 21.3 min for types of procedures that are not performed very often.

CONCLUSIONS

Different methods for encoding medical ontological information in surgery procedure duration predictions are presented, and show an improvement over traditional models. The improvement in duration prediction is shown to improve the efficiency of scheduling in a simple simulation.

Clinical Informatics and the Electronic Medical Record

The electronic medical record has fundamentally altered the way surgeons participate and practice medicine. There is now a wealth of data, once hidden behind paper records, that is, now available to surgeons to provide superior care to their patients. This article reviews the history of the electronic medical record, discusses use cases of additional data resources, and highlights the pitfalls of this relatively new technology.

Machine Learning and Artificial Intelligence in Surgical Research

Machine learning, a subtype of artificial intelligence, is an emerging field of surgical research dedicated to predictive modeling. From its inception, machine learning has been of interest in medical and surgical research. Built on traditional research metrics for optimal success, avenues of research include diagnostics, prognosis, operative timing, and surgical education, in a variety of surgical subspecialties. Machine learning represents an exciting and developing future in the world of surgical research that will not only allow for more personalized and comprehensive medical care.

Genetic Algorithm for Solving the No-Wait Three-Stage Surgery Scheduling Problem

In this research, we consider a deterministic three-stage operating room surgery scheduling problem. The three successive stages are pre-surgery, surgery, and post-surgery. The no-wait constraint is considered among the three stages. Surgeries are known in advance (elective). Multiple resources are considered throughout the surgical process: PHU (preoperative holding unit) beds in the first stage, ORs (operating rooms) in the second stage, and PACU (post-anesthesia care unit) beds in the third stage. The objective is to minimize the makespan. The makespan is defined as the maximum end time of the last activity in stage 3. Minimizing the makespan not only maximizes the utilization of ORs but also improves patient satisfaction by allowing treatments to be delivered to patients in a timely manner. We proposed a genetic algorithm (GA) for solving the operating room scheduling problem. Randomly generated problem instances were tested to evaluate the performance of the proposed GA. The computational results show that overall, the GA deviated from the lower bound (LB) by 3.25% on average, and the average computation time of the GA was 10.71 s. We conclude that the GA can efficiently find near-optimal solutions to the daily three-stage operating room surgery scheduling problem.

Alignment of RVU Targets With Operating Room Block Time

Background

Surgeon productivity is measured in relative value units (RVUs). The feasibility of attaining RVU productivity targets requires surgeons to have enough allocated block time to generate RVUs. However, it is unknown how much block time is required for surgeons to attain specific RVU targets. We aimed to estimate the effect of surgeon and practice environment characteristics (SPECs) on block time needed to attain fixed RVU targets.

Methods

We computationally simulated individual surgeons' annual caseloads under a variety of SPECs in the following way. First, empirical case data were sampled from ACS NSQIP in accordance with surgeon specialty, case-mix complexity, and RVU target. Surgeons' operating schedules were then constructed according to the block length, turnover time, and scheduling flexibility of the practice environment. These 6 SPECs were concurrently varied over their ranges for a 6-way sensitivity analysis.

Results

Annual operating schedules for 60,000,000 surgeons were simulated. The number of blocks required to attain RVU targets varied significantly with surgeon specialty and increased with increased case-mix complexity, increased turnover time, and decreased scheduling flexibility. Intraspecialty variation in block requirement with variation in environmental characteristics exceeded interspecialty variation with fixed environmental characteristics. Multivariate linear models predicted block utilization across surgical specialties with consideration for the stated factors. An online tool is shared with which to apply these results to one's particular practice.

Conclusions

Block time required to attain RVU targets varies widely with SPECs; intraspecialty variation exceeds interspecialty variation. The feasibility of attaining RVU targets requires alignment between targets and allocated operating time with consideration for surgical specialty and other practice conditions.

Evolution of the digital operating room: the place of video technology in surgery

PURPOSE

The aim of this review was to collate current evidence wherein digitalisation, through the incorporation of video technology and artificial intelligence (AI), is being applied to the practice of surgery. Applications are vast, and the literature investigating the utility of surgical video and its synergy with AI has steadily increased over the last 2 decades. This type of technology is widespread in other industries, such as autonomy in transportation and manufacturing.

METHODS

Articles were identified primarily using the PubMed and MEDLINE databases. The MeSH terms used were "surgical education", "surgical video", "video labelling", "surgery", "surgical workflow", "telementoring", "telemedicine", "machine learning", "deep learning" and "operating room". Given the breadth of the subject and the scarcity of high-level data in certain areas, a narrative synthesis was selected over a meta-analysis or systematic review to allow for a focussed discussion of the topic.

RESULTS

Three main themes were identified and analysed throughout this review, (1) the multifaceted utility of surgical video recording, (2) teleconferencing/telemedicine and (3) artificial intelligence in the operating room.

CONCLUSIONS

Evidence suggests the routine collection of intraoperative data will be beneficial in the advancement of surgery, by driving standardised, evidence-based surgical care and personalised training of future surgeons. However, many barriers stand in the way of widespread implementation, necessitating close collaboration between surgeons, data scientists, medicolegal personnel and hospital policy makers.

Artificial intelligence-enhanced care pathway planning and scheduling system: content validity assessment of required functionalities

BACKGROUND

Artificial intelligence (AI) and machine learning are transforming the optimization of clinical and patient workflows in healthcare. There is a need for research to specify clinical requirements for AI-enhanced care pathway planning and scheduling systems to improve human-AI interaction in machine learning applications. The aim of this study was to assess content validity and prioritize the most relevant functionalities of an AI-enhanced care pathway planning and scheduling system.

METHODS

A prospective content validity assessment was conducted in five university hospitals in three different countries using an electronic survey. The content of the survey was formed from clinical requirements, which were formulated into generic statements of required AI functionalities. The relevancy of each statement was evaluated using a content validity index. In addition, weighted ranking points were calculated to prioritize the most relevant functionalities of an AI-enhanced care pathway planning and scheduling system.

RESULTS

A total of 50 responses were received from clinical professionals from three European countries. An item-level content validity index ranged from 0.42 to 0.96. 45% of the generic statements were considered good. The highest ranked functionalities for an AI-enhanced care pathway planning and scheduling system were related to risk assessment, patient profiling, and resources. The highest ranked functionalities for the user interface were related to the explainability of machine learning models.

CONCLUSION

This study provided a comprehensive list of functionalities that can be used to design future AI-enhanced solutions and evaluate the designed solutions against requirements. The relevance of statements concerning the AI functionalities were considered somewhat relevant, which might be due to the low level or organizational readiness for AI in healthcare.

Surgery duration: Optimized prediction and causality analysis

Accurate estimation of duration of surgery (DOS) can lead to cost-effective utilization of surgical staff and operating rooms and decrease patients’ waiting time. In this study, we present a supervised DOS nonlinear regression prediction model whose accuracy outperforms earlier results. In addition, unlike previous studies, we identify the features that influence DOS prediction. Further, in difference from others, we study the causal relationship between the feature set and DOS. The feature sets used in prior studies included a subset of the features presented in this study. This study aimed to derive influential effectors of duration of surgery via optimized prediction and causality analysis. We implemented an array of machine learning algorithms and trained them on datasets comprising surgery-related data, to derive DOS prediction models. The datasets we acquired contain patient, surgical staff, and surgery features. The datasets comprised 23,293 surgery records of eight surgery types performed over a 10-year period in a public hospital. We have introduced new, unstudied features and combined them with features adopted from previous studies to generate a comprehensive feature set. We utilized feature importance methods to identify the influential features, and causal inference methods to identify the causal features. Our model demonstrates superior performance in comparison to DOS prediction models in the art. The performance of our DOS model in terms of the mean absolute error (MAE) was 14.9 minutes. The algorithm that derived the model with the best performance was the gradient boosted trees (GBT). We identified the 10 most influential features and the 10 most causal features. In addition, we showed that 40% of the influential features have a significant (p-value = 0.05) causal relationship with DOS. We developed a DOS prediction model whose accuracy is higher than that of prior models. This improvement is achieved via the introduction of a novel feature set on which the model was trained. Utilizing our prediction model, hospitals can improve the efficiency of surgery schedules, and by exploiting the identified causal relationship, can influence the DOS. Further, the feature importance methods we used can help explain the model’s predictions.

Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models

BACKGROUND

Prolonged surgical operative time is associated with postoperative adverse outcomes following total knee arthroplasty (TKA). Increasing operating room efficiency necessitates the accurate prediction of surgical operative time for each patient. One potential way to increase the accuracy of predictions is to use advanced predictive analytics, such as machine learning. The aim of this study is to use machine learning to develop an accurate predictive model for surgical operative time for patients undergoing primary total knee arthroplasty.

METHODS

A retrospective chart review of electronic medical records was conducted to identify patients who underwent primary total knee arthroplasty at a tertiary referral center. Three machine learning algorithms were developed to predict surgical operative time and were assessed by discrimination, calibration and decision curve analysis. Specifically, we used: (1) Artificial Neural Networks (ANNs), (2) Random Forest (RF), and (3) K-Nearest Neighbor (KNN).

RESULTS

We analyzed the surgical operative time for 10,021 consecutive patients who underwent primary total knee arthroplasty. The neural network model achieved the best performance across discrimination (AUC = 0.82), calibration and decision curve analysis for predicting surgical operative time. Based on this algorithm, younger age (< 45 years), tranexamic acid non-usage, and a high BMI (> 40 kg/m²) were the strongest predictors associated with surgical operative time.

CONCLUSIONS

This study shows excellent performance of machine learning models for predicting surgical operative time in primary total knee arthroplasty. The accurate estimation of surgical duration is important in enhancing OR efficiency and identifying patients at risk for prolonged surgical operative time.

LEVEL OF EVIDENCE

Level III, case control retrospective analysis.

Quantile regression forests for individualized surgery scheduling

Determining the optimal surgical case start times is a challenging stochastic optimization problem that shares a key feature with many other healthcare operations problems. Namely, successful problem solutions require using a vast array of available historical data to create distributions that accurately capture a case duration's uncertainty for integration into an optimization model. Distribution fitting is the conventional approach to generate these distributions, but it can only employ a limited, aggregate portion of the detailed patient features available in Electronic Medical Records systems today. If all the available information can be taken advantage of, then distributions individualized to every case can be constructed whose precision would support higher quality solutions in the presence of uncertainty. Our individualized stochastic optimization framework shows how the quantile regression forest (QRF) method predicts individualized distributions that are integrable into sample-average approximation, robust optimization, and distributionally robust optimization models for problems like surgery scheduling. In this paper, we present some related theoretical performance guarantees for each formulation. Numerically, we also study our approach's benefits relative to three other traditional models using data from Memorial Sloan Kettering Cancer Center in New York, NY, USA.

Operating Room Usage Time Estimation with Machine Learning Models

Effectively handling the limited number of surgery operating rooms equipped with expensive equipment is a challenging task for hospital management such as reducing the case-time duration and reducing idle time. Improving the efficiency of operating room usage via reducing the idle time with better scheduling would rely on accurate estimation of surgery duration. Our model can achieve a good prediction result on surgery duration with a dozen of features. We have found the result of our best performing department-specific XGBoost model with the values 31.6 min, 18.71 min, 0.71, 28% and 27% for the metrics of root-mean-square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), mean absolute percentage error (MAPE) and proportion of estimated result within 10% variation, respectively. We have presented each department-specific result with our estimated results between 5 and 10 min deviation would be more informative to the users in the real application. Our study shows comparable performance with previous studies, and the machine learning methods use fewer features that are better suited for universal usability.

A Case Study of Multiple Maintenance Efficacy in Gynaecological Surgery Assessed by Deep Learning

Deep learning is a new learning concept and a highly effective way of learning, which is still being explored in the field of nursing education. This paper analyses the effectiveness of interventions in perioperative gynaecological care using humanised care in the operating theatre and the impact of this model of care on patients’ psychological well-being and sleep quality. A deep learning-based vision robot was designed to provide higher quality of care for our human care and simplify our approach to gynaecological surgery. The anxiety and depression scores of the two groups were significantly improved after and before care, and the scores of the observation group were lower than those of the control group, with a statistically significant difference ( $P<0.05$ ). The humanised care for gynaecological surgery patients in the perioperative period is more conducive to the improvement of their negative emotions and at the same time can improve the sleep quality of patients, so it can be further promoted.

Timely completion of spinal fusion: A multidisciplinary quality improvement initiative to improve operating room efficiency

BACKGROUND

Failure to complete surgery within the scheduled timeframe impairs operating room efficiency leading to patient dissatisfaction and unplanned labor costs. We sought to improve timely completion (within 30 min of scheduled time) of first-case spine fusion surgery (for idiopathic scoliosis) from a baseline of 25%-80% over 12 months. We also targeted timely completion of perioperative stages within predetermined target completion times.

METHODS

The project was conducted in three overlapping phases over 16 months. A simplified process map outlining five sequential perioperative stages, preintervention baselines (N = 24) and time targets were defined. A multidisciplinary team conducted a series of tests of change addressing the aims. The key drivers included effective scheduling, team communications, family engagement, data collection veracity, standardized pathways, and situational awareness. Data collected by an independent data collector and from electronic medical records were analyzed using control charts and statistical process control methods.

RESULTS

Post-intervention, timely case completion increased from 25% to 68% (N = 49) (95% CI 15.1-62.7), (p = 0.003) and was sustained (N = 14). Implementation of prediction model for case-scheduling decreased difference between scheduled and actual case end-time (33 vs. 53 min [baseline]) and variance [lower/upper control limits ([-26, 51] vs. [-109, 216] min [baseline]). Average start time delay decreased from 6 to 2 min and on-time surgical starts improved from 50% to 70% (95% CI 3.2-41.6%). Timely completion increased for anesthesia induction (60% to 85%), surgical procedure (26% to 48%) and emergence from anesthesia (44% to 80%) but not for intraoperative patient preparation (30% to 25%) perioperative stages. Families reported satisfaction with preoperative processes (N = 14), and no untoward intraoperative safety events occurred.

CONCLUSIONS

Application of QI methodology reduced time variation of several tasks and improved timely completion of spine surgery. Beyond the study period, sustained team behavior, adaptive changes, and vigilant monitoring are imperative for continued success.

Optimizing Operation Room Utilization—A Prediction Model

Background: Operating rooms are the core of hospitals. They are a primary source of revenue and are often seen as one of the bottlenecks in the medical system. Many efforts are made to increase throughput, reduce costs, and maximize incomes, as well as optimize clinical outcomes and patient satisfaction. We trained a predictive model on the length of surgeries to improve the productivity and utility of operative rooms in general hospitals. Methods: We collected clinical and administrative data for the last 10 years from two large general public hospitals in Israel. We trained a machine learning model to give the expected length of surgery using pre-operative data. These data included diagnoses, laboratory tests, risk factors, demographics, procedures, anesthesia type, and the main surgeon’s level of experience. We compared our model to a naïve model that represented current practice. Findings: Our prediction model achieved better performance than the naïve model and explained almost 70% of the variance in surgery durations. Interpretation: A machine learning-based model can be a useful approach for increasing operating room utilization. Among the most important factors were the type of procedures and the main surgeon’s level of experience. The model enables the harmonizing of hospital productivity through wise scheduling and matching suitable teams for a variety of clinical procedures for the benefit of the individual patient and the system as a whole.

Machine Learning-Based Models Predicting Outpatient Surgery End Time and Recovery Room Discharge at an Ambulatory Surgery Center

Days before surgery, add-ons may be scheduled to fill unused surgical block time at an outpatient surgery center. At times, outpatient surgery centers have time limitations for end of block time and discharge from the postanesthesia care unit (PACU). The objective of our study was to develop machine learning models that predicted the following composite outcome: (1) surgery finished by end of operating room block time and (2) patient was discharged by end of recovery room nursing shift. We compared various machine learning models to logistic regression. By evaluating various performance metrics, including F1 scores, we hypothesized that models using ensemble learning will be superior to logistic regression.

Analysis of Holmium Laser Enucleation of Prostate Fixed Operating Room Times

OBJECTIVE

To evaluate factors influencing fixed operating room time during holmium laser enucleation of the prostate.

MATERIALS AND METHODS

A prospective observational study was performed for all holmium laser enucleation of the prostate (HoLEP) cases performed by a single surgeon over a 24-month period. Operating room (OR) time was divided into fixed and variable time. The variable time was defined as cut-to-close time. Fixed time included in room time to anesthesia release time (IRAT), anesthesia release time to cut time (ARCT), and close time to wheels out (CTWO). The effects of time of day and anesthesia personnel (AP) changes on fixed operating room time were evaluated.

RESULTS

A total of 406 HoLEPs were analyzed. There was no statistically significant difference in nonprocedural OR times between morning and afternoon surgeries (IRAT, P=0.38, ARCT P=0.10, CTWO P=0.77). Median nonprocedural OR times accounted for 27% (IQR: 22%-31%) of the total procedure time in the AM group and 29% (IQR: 24%-33%) in the PM group (P=0.005). Of the HoLEPs,78.1% (178/228) experienced one or more AP changes during the procedure. The median fixed OR time was not significantly different between procedures with 1 AP and procedures with ≥2 APs (IRAT, P=0.53; ARCT, P=0.71; CTWO, P=0.98).

CONCLUSIONS

Fixed operating room time makes up a significant portion of HoLEP procedures and should be considered when evaluating OR efficiency. The time of day and number of anesthesia personnel involved did not affect the fixed OR times.

Estimation of Surgery Durations Using Machine Learning Methods-A Cross-Country Multi-Site Collaborative Study

The scheduling of operating room (OR) slots requires the accurate prediction of surgery duration. We evaluated the performance of existing Moving Average (MA) based estimates with novel machine learning (ML)-based models of surgery durations across two sites in the US and Singapore. We used the Duke Protected Analytics Computing Environment (PACE) to facilitate data-sharing and big data analytics across the US and Singapore. Data from all colorectal surgery patients between 1 January 2012 and 31 December 2017 in Singapore and, 1 January 2015 to 31 December 2019 in the US were used, and 7585 cases and 3597 single and multiple procedure cases from Singapore and US were included. The ML models were based on categorical gradient boosting (CatBoost) models trained on common data fields shared by both institutions. The procedure codes were based on the Table of Surgical Procedure (TOSP) (Singapore) and the Current Procedural Terminology (CPT) codes (US). The two types of codes were mapped by surgical experts. The CPT codes were then transformed into the relative value unit (RVU). The ML models outperformed the baseline MA models. The MA, scheduled durations and procedure codes were found to have higher loadings as compared to surgeon factors. We further demonstrated the use of the Duke PACE in facilitating data-sharing and big data analytics.

Continuous real-time prediction of surgical case duration using a modular artificial neural network

BACKGROUND

Real-time prediction of surgical duration can inform perioperative decisions and reduce surgical costs. We developed a machine learning approach that continuously incorporates preoperative and intraoperative information for forecasting surgical duration.

METHODS

Preoperative (e.g. procedure name) and intraoperative (e.g. medications and vital signs) variables were retrieved from anaesthetic records of surgeries performed between March 1, 2019 and October 31, 2019. A modular artificial neural network was developed and compared with a Bayesian approach and the scheduled surgical duration. Continuous ranked probability score (CRPS) was used as a measure of time error to assess model accuracy. For evaluating clinical performance, accuracy for each approach was assessed in identifying cases that ran beyond 15:00 (commonly scheduled end of shift), thus identifying opportunities to avoid overtime labour costs.

RESULTS

The analysis included 70 826 cases performed at eight hospitals. The modular artificial neural network had the lowest time error (CRPS: mean=13.8; standard deviation=35.4 min), which was significantly better (mean difference=6.4 min [95% confidence interval: 6.3-6.5]; P<0.001) than the Bayesian approach. The modular artificial neural network also had the highest accuracy in identifying operating theatres that would overrun 15:00 (accuracy at 1 h prior=89%) compared with the Bayesian approach (80%) and a naïve approach using the scheduled duration (78%).

CONCLUSIONS

A real-time neural network model using preoperative and intraoperative data had significantly better performance than a Bayesian approach or scheduled duration, offering opportunities to avoid overtime labour costs and reduce the cost of surgery by providing superior real-time information for perioperative decision support.

Automatic Surgery and Anesthesia Emergence Duration Prediction Using Artificial Neural Networks

Cost control is becoming increasingly important in hospital management. Hospital operating rooms have high resource consumption because they are a major part of a hospital. Thus, the optimal use of operating rooms can lead to high resource savings. However, because of the uncertainty of the operation procedures, it is difficult to arrange for the use of operating rooms in advance. In general, the durations of both surgery and anesthesia emergence determine the time requirements of operating rooms, and these durations are difficult to predict. In this study, we used an artificial neural network to construct a surgery and anesthesia emergence duration-prediction system. We propose an intelligent data preprocessing algorithm to balance and enhance the training dataset automatically. The experimental results indicate that the prediction accuracies of the proposed serial prediction systems are acceptable in comparison to separate systems.

Efficiency Metrics at an Academic Freestanding Ambulatory Surgery Center: Analysis of the Impact on Scheduled End-Times

BACKGROUND

Understanding the impact of key metrics on operating room (OR) efficiency is important to optimize utilization and reduce costs, particularly in freestanding ambulatory surgery centers. The aim of this study was to assess the association between commonly used efficiency metrics and scheduled end-time accuracy.

METHODS

Data from patients who underwent surgery from May 2018 to June 2019 at an academic freestanding ambulatory surgery center was extracted from the medical record. Unique operating room days (ORDs) were analyzed to determine (1) duration of first case delays, (2) turnover times (TOT), and (3) scheduled case duration accuracies. Spearman's correlation coefficients and mixed-effects multivariable linear regression were used to assess the association of each metric with scheduled end-time accuracy.

RESULTS

There were 1378 cases performed over 300 unique ORDs. There were 86 (28.7%) ORDs with a first case delay, mean (standard deviation [SD]) 11.2 minutes (15.1 minutes), range of 2-101 minutes; the overall mean (SD) TOT was 28.1 minutes (19.9 minutes), range of 6-83 minutes; there were 640 (46.4%) TOT >20 minutes; the overall mean (SD) case duration accuracy was -6.6 minutes (30.3 minutes), range of -114 to 176; and there were 389 (28.2%) case duration accuracies ≥30 minutes. The mean (SD) scheduled end-time accuracy was 6.9 minutes (68.3 minutes), range of -173 to 229 minutes; 48 (15.9%) ORDs ended ≥1 hour before scheduled end-time and 56 (18.6%) ORDs ended ≥1 hour after scheduled end-time. The total case duration accuracy was strongly correlated with the scheduled end-time accuracy (r = 0.87, 95% confidence interval [CI], 0.84-0.89, P < .0001), while the total first case delay minutes (r = 0.12, 95% CI, 0.01-0.21, P = .04) and total turnover time (r = -0.16, 95% CI, 0.21-0.05, P = .005) were less relevant. Case duration accuracy had the highest association with the dependent variable (0.95 minutes changed in the difference between actual and schedule end time per minute increase in case duration accuracy, 95% CI, 0.90-0.99, P < .0001), compared to turnover time (estimate = 0.87, 95% CI, 0.75-0.99, P < .0001) and first case delay time (estimate = 0.83, 95% CI, 0.56-1.11, P < .0001).

CONCLUSIONS

Standard efficiency metrics are similarly associated with scheduled end-time accuracy, and addressing problems in each is requisite to having an efficient ambulatory surgery center. Pursuing methods to narrow the gap between scheduled and actual case duration may result in a more productive enterprise.

Artificial Intelligence Supports Decision Making during Open-Chest Surgery of Rare Congenital Heart Defects

The human right ventricle is barely monitored during open-chest surgery due to the absence of intraoperative imaging techniques capable of elaborating its complex function. Accordingly, artificial intelligence could not be adopted for this specific task. We recently proposed a video-based approach for the real-time evaluation of the epicardial kinematics to support medical decisions. Here, we employed two supervised machine learning algorithms based on our technique to predict the patients' outcomes before chest closure. Videos of the beating hearts were acquired before and after pulmonary valve replacement in twelve Tetralogy of Fallot patients and recordings were properly labeled as the "unhealthy" and "healthy" classes. We extracted frequency-domain-related features to train different supervised machine learning models and selected their best characteristics via 10-fold cross-validation and optimization processes. Decision surfaces were built to classify two additional patients having good and unfavorable clinical outcomes. The k-nearest neighbors and support vector machine showed the highest prediction accuracy; the patients' class was identified with a true positive rate ≥95% and the decision surfaces correctly classified the additional patients in the "healthy" (good outcome) or "unhealthy" (unfavorable outcome) classes. We demonstrated that classifiers employed with our video-based technique may aid cardiac surgeons in decision making before chest closure.