Contributors to Operating Room Underutilization and Implications for Hospital Administrators

Improving case duration accuracy of orthopedic surgery using bidirectional encoder representations from Transformers (BERT) on Radiology Reports

PURPOSE

A major source of inefficiency in the operating room is the mismatch between scheduled versus actual surgical time. The purpose of this study was to demonstrate a proof-of-concept study for predicting case duration by applying natural language processing (NLP) and machine learning that interpret radiology reports for patients undergoing radius fracture repair.

METHODS

Logistic regression, random forest, and feedforward neural networks were tested without NLP and with bag-of-words. Another NLP method tested used feedforward neural networks and Bidirectional Encoder Representations from Transformers specifically pre-trained on clinical notes (ClinicalBERT). A total of 201 cases were included. The data were split into 70% training and 30% test sets. The average root mean squared error (RMSE) were calculated (and 95% confidence interval [CI]) from 10-fold cross-validation on the training set. The models were then tested on the test set to determine proportion of times surgical cases would have scheduled accurately if ClinicalBERT was implemented versus historic averages.

RESULTS

The average RMSE was lowest using feedforward neural networks using outputs from ClinicalBERT (25.6 min, 95% CI: 21.5-29.7), which was significantly (P < 0.001) lower than the baseline model (39.3 min, 95% CI: 30.9-47.7). Using the feedforward neural network and ClinicalBERT on the test set, the percentage of accurately predicted cases, which was defined by the actual surgical duration within 15% of the predicted surgical duration, increased from 26.8 to 58.9% (P < 0.001).

CONCLUSION

This proof-of-concept study demonstrated the successful application of NLP and machine leaning to extract features from unstructured clinical data resulting in improved prediction accuracy for surgical case duration.

Analysis of hospital and payer costs of care: aggressive warming versus routine warming in abdominal major surgery

Background

Hypothermia is common and active warming is recommended in major surgery. The potential effect on hospitals and payer costs of aggressive warming to a core temperature target of 37°C is poorly understood.

Methods

In this sub-analysis of the PROTECT trial (clinicaltrials.gov, NCT03111875), we included patients who underwent radical procedures of colorectal cancer and were randomly assigned to aggressive warming or routine warming. Perioperative outcomes, operation room (OR) scheduling process, internal cost accounting data from the China Statistical yearbook (2022), and price lists of medical and health institutions in Beijing were examined. A discrete event simulation (DES) model was established to compare OR efficiency using aggressive warming or routine warming in 3 months. We report base-case net costs and sensitivity analyses of intraoperative aggressive warming compared with routine warming. Costs were calculated in 2022 using US dollars (USD).

Results

Data from 309 patients were analyzed. The aggressive warming group comprised 161 patients and the routine warming group comprised 148 patients. Compared to routine warming, there were no differences in the incidence of postoperative complications and total hospitalization costs of patients with aggressive warming. The potential benefit of aggressive warming was in the reduced extubation time (7.96 ± 4.33 min vs. 10.33 ± 5.87 min, p < 0.001), lower incidence of prolonged extubation (5.6% vs. 13.9%, p = 0.017), and decreased staff costs. In the DES model, there is no add-on or cancelation of operations performed within 3 months. The net hospital costs related to aggressive warming were higher than those related to routine warming in one operation (138.11 USD vs. 72.34 USD). Aggressive warming will have an economic benefit when the OR staff cost is higher than 2.37 USD/min/person, or the cost of disposable forced-air warming (FAW) is less than 12.88 USD/piece.

Conclusion

Despite improving OR efficiency, the economic benefits of aggressive warming are influenced by staff costs and the cost of FAW, which vary from different regions and countries.

Clinical trial registration

clinicaltrials.gov, identifier (NCT03111875).

Using Machine Learning to Predict Operating Room Case Duration: A Case Study in Otolaryngology

OBJECTIVE

Optimizing operating room (OR) efficiency depends on accurate case duration estimates. Machine learning (ML) methods have been used to predict OR case durations in other subspecialties. We hypothesize that ML methods improve projected case lengths over existing non-ML techniques for otolaryngology-head and neck surgery cases.

METHODS

Deidentified patient information from otolaryngology surgical cases at 1 academic institution were reviewed from 2016 to 2020. Variables collected included patient, surgeon, procedure, and facility data known preoperatively so as to capture all realistic contributors. Available case data were divided into a training and testing data set. Several ML algorithms were evaluated based on best performance of predicted case duration when compared to actual case duration. Performance of all models was compared by the average root mean squared error and mean absolute error (MAE).

RESULTS

In total, 50,888 otolaryngology surgical cases were evaluated with an average case duration of 98.3 ± 86.9 minutes. Most cases were general otolaryngology (n = 16,620). Case features closely associated with OR duration included procedure performed, surgeon, subspecialty of case, and postoperative destination of the patient. The best-performing ML models were CatBoost and XGBoost, which reduced operative time MAE by 9.6 minutes and 8.5 minutes compared to current methods, respectively.

DISCUSSION

The incorporation of other easily identifiable features beyond procedure performed and surgeon meaningfully improved our operative duration prediction accuracy. CatBoost provided the best-performing ML model.

IMPLICATIONS FOR PRACTICE

ML algorithms to predict OR case time duration in otolaryngology can improve case duration accuracy and result in financial benefit.

Impact of ENT resource nurses in improving operating room efficiency

BACKGROUND

Operating room (OR) efficiency is related to minutes spared from surgical time and has been linked to the make up of surgical teams and operating room workplace. The research on the efficiency of surgical nursing staff members is scant. The current study evaluates the effect of ENT trained OR resource nurses on the efficiency of operating time during ENT procedures.

METHODS

Five hundred seventy-three ENT surgery cases from 4 surgeons were retrospectively reviewed. Two hundred forty-two cases had ENT OR nursing staff and 331 cases had non-ENT OR nursing staff. Requested operative times (ROT) and true operative times (TOT) were analyzed. The difference between the TOT and ROT was used to measure operating time efficiency.

RESULTS

Cases with ROT < 30 min (M = -1.19, SD = 5.01) required 3.34 min less than planned for when an ENT nurse was present compared to those with non-ENT nursing staff which required on average 2.15 min (M = 2.15, SD = 5.68) longer than ROT. Furthermore, cases with ROT > 30 min (M = -4.32, SD = 10.85) required 10.85 min less than planned for when an ENT nurse was present. Conversely with non-ENT nursing staff cases with a ROT > 30 min required on average 6.53 min (M = 6.53, SD = 11.85) longer than ROT.

CONCLUSION

ENT resource nurses were shown to improve OR efficiency in cases less than 30 min and greater than 30 min. Cases that were greater than 30 min showed the largest increase in efficiency. Specialized ENT nursing staff improved efficiency during common ENT surgeries.

Applying Performance Frontiers in Operating Room Management: A Tutorial Using Data From an Academic Medical Center

Although the primary goal of operating room (OR) management is to minimize inefficiencies, it may be difficult for OR managers to track metrics when one extrapolates possible scenarios across every OR on a daily basis. With the ability to visualize the statistical relationships to help simplify the analysis of large datasets, a more elaborate efficiency framework can be established using Pareto optimality (or performance frontiers), a multicriteria framework that includes variables that serve as proxies for a variety of outcomes. Applied to OR management, performance frontiers allow for the evaluation of common and well-understood issues of under- and over-utilized time.

Machine Learning Can Improve Estimation of Surgical Case Duration: A Pilot Study

Operating room (OR) utilization is a significant determinant of hospital profitability. One aspect of this is surgical scheduling, which depends on accurate predictions of case duration. This has been done historically by either the surgeon based on personal experience, or by an electronic health record (EHR) based on averaged historical means for case duration. Here, we compare the predicted case duration (pCD) accuracy of a novel machine-learning algorithm over a 3-month period. A proprietary machine learning algorithm was applied utilizing operating room factors such as patient demographic data, pre-surgical milestones, and hospital logistics and compared to that of a conventional EHR. Actual case duration and pCD (Leap Rail vs EHR) was obtained at one institution over the span of 3 months. Actual case duration was defined as time between patient entry into an OR and time of exit. pCD was defined as case time allotted by either Leap Rail or EHR. Cases where Leap Rail was unable to generate a pCD were excluded. A total of 1059 surgical cases were performed during the study period, with 990 cases being eligible for the study. Over all sub-specialties, Leap Rail showed a 7 min improvement in absolute difference between pCD and actual case duration when compared to conventional EHR (p < 0.0001). In aggregate, the Leap Rail method resulted in a 70% reduction in overall scheduling inaccuracy. Machine-learning algorithms are a promising method of increasing pCD accuracy and represent one means of improving OR planning and efficiency.