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

Larger anesthesia practitioner per operating room ratios are needed to prevent unnecessary non-operative time than to mitigate patient risk: A narrative review

When choosing the anesthesia practitioner to operating room (OR) ratio for a hospital, objectives are applied to mitigate patient risk: 1) ensuring sufficient anesthesiologists to meet requirements for presence during critical intraoperative events (e.g., anesthesia induction) and 2) ensuring sufficient numbers to cover emergencies outside the ORs (e.g., emergent reintubation in the post-anesthesia care unit). At a 24-OR suite with each anesthesiologist supervising residents in 2 ORs, because critical events overlapped among ORs, ≥14 anesthesiologists were needed to be present for all critical events on >90% of days. The suitable anesthesia practitioner to OR ratio would be 1.58, where 1.58 = (24 + 14)/24. Our narrative review of 22 studies from 17 distinct hospitals shows that the practitioner to OR ratio needed to reduce non-operative time is reliably even larger. Activities to reduce non-operative times include performing preoperative evaluations, making prompt evidence-based decisions at the OR control desk, giving breaks during cases (e.g., lunch or lactation sessions), and using induction and block rooms in parallel to OR cases. The reviewed articles counted the frequency of these activities, finding them much more common than urgent patient-care events. Our review shows, also, that 1 anesthesiologist per OR, working without assistants, is often more expensive, from a societal perspective, than having a few more anesthesia practitioners (i.e., ratio > 1.00). These results are generalizable among hundreds of hospitals, based on managerial epidemiology studies. The implication of our narrative review is that existing studies have already shown, functionally, that artificial intelligence and monitoring technologies based on increasing the safety of intraoperative care have little to no potential to influence anesthesia or OR productivity. There are, in contrast, opportunities to use sensor data and decision-support to facilitate communication among anesthesiologists outside of ORs to choose optimal task sequences that reduce non-operative times, thereby increasing production and OR efficiency.

Application of Machine Learning in Predicting Perioperative Outcomes in Patients with Cancer: A Narrative Review for Clinicians

This narrative review explores the utilization of machine learning (ML) and artificial intelligence (AI) models to enhance perioperative cancer care. ML and AI models offer significant potential to improve perioperative cancer care by predicting outcomes and supporting clinical decision-making. Tailored for perioperative professionals including anesthesiologists, surgeons, critical care physicians, nurse anesthetists, and perioperative nurses, this review provides a comprehensive framework for the integration of ML and AI models to enhance patient care delivery throughout the perioperative continuum.

Prediction of remaining surgery duration in laparoscopic videos based on visual saliency and the transformer network

BACKGROUND

Real-time prediction of the remaining surgery duration (RSD) is important for optimal scheduling of resources in the operating room.

METHODS

We focus on the intraoperative prediction of RSD from laparoscopic video. An extensive evaluation of seven common deep learning models, a proposed one based on the Transformer architecture (TransLocal) and four baseline approaches, is presented. The proposed pipeline includes a CNN-LSTM for feature extraction from salient regions within short video segments and a Transformer with local attention mechanisms.

RESULTS

Using the Cholec80 dataset, TransLocal yielded the best performance (mean absolute error (MAE) = 7.1 min). For long and short surgeries, the MAE was 10.6 and 4.4 min, respectively. Thirty minutes before the end of surgery MAE = 6.2 min, 7.2 and 5.5 min for all long and short surgeries, respectively.

CONCLUSIONS

The proposed technique achieves state-of-the-art results. In the future, we aim to incorporate intraoperative indicators and pre-operative data.

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.

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.

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.

Nonlinear regression of remaining surgery duration from videos via Bayesian LSTM-based deep negative correlation learning

In this paper, we address the problem of estimating remaining surgery duration (RSD) from surgical video frames. We propose a Bayesian long short-term memory (LSTM) network-based Deep Negative Correlation Learning approach called BD-Net for accurate regression of RSD prediction as well as estimation of prediction uncertainty. Our method aims to extract discriminative visual features from surgical video frames and model the temporal dependencies among frames to improve the RSD prediction accuracy. To this end, we propose to train an ensemble of Bayesian LSTMs on top of a backbone network by the way of deep negative correlation learning (DNCL). More specifically, we deeply learn a pool of decorrelated Bayesian regressors with sound generalization capabilities through managing their intrinsic diversities. BD-Net is simple and efficient. After training, it can produce both RSD prediction and uncertainty estimation in a single inference run. We demonstrate the efficacy of BD-Net on publicly available datasets of two different types of surgeries: one containing 101 cataract microscopic surgeries with short durations and the other containing 80 cholecystectomy laparoscopic surgeries with relatively longer durations. Experimental results on both datasets demonstrate that the proposed BD-Net achieves better results than the state-of-the-art (SOTA) methods. A reference implementation of our method can be found at: https://github.com/jywu511/BD-Net.

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.

An Intraoperative Telemedicine Program to Improve Perioperative Quality Measures: The ACTFAST-3 Randomized Clinical Trial

Importance

Telemedicine for clinical decision support has been adopted in many health care settings, but its utility in improving intraoperative care has not been assessed.

Objective

To pilot the implementation of a real-time intraoperative telemedicine decision support program and evaluate whether it reduces postoperative hypothermia and hyperglycemia as well as other quality of care measures.

Design, Setting, and Participants

This single-center pilot randomized clinical trial (Anesthesiology Control Tower-Feedback Alerts to Supplement Treatments [ACTFAST-3]) was conducted from April 3, 2017, to June 30, 2019, at a large academic medical center in the US. A total of 26 254 adult surgical patients were randomized to receive either usual intraoperative care (control group; n = 12 980) or usual care augmented by telemedicine decision support (intervention group; n = 13 274). Data were initially analyzed from April 22 to May 19, 2021, with updates in November 2022 and February 2023.

Intervention

Patients received either usual care (medical direction from the anesthesia care team) or intraoperative anesthesia care monitored and augmented by decision support from the Anesthesiology Control Tower (ACT), a real-time, live telemedicine intervention. The ACT incorporated remote monitoring of operating rooms by a team of anesthesia clinicians with customized analysis software. The ACT reviewed alerts and electronic health record data to inform recommendations to operating room clinicians.

Main Outcomes and Measures

The primary outcomes were avoidance of postoperative hypothermia (defined as the proportion of patients with a final recorded intraoperative core temperature >36 °C) and hyperglycemia (defined as the proportion of patients with diabetes who had a blood glucose level ≤180 mg/dL on arrival to the postanesthesia recovery area). Secondary outcomes included intraoperative hypotension, temperature monitoring, timely antibiotic redosing, intraoperative glucose evaluation and management, neuromuscular blockade documentation, ventilator management, and volatile anesthetic overuse.

Results

Among 26 254 participants, 13 393 (51.0%) were female and 20 169 (76.8%) were White, with a median (IQR) age of 60 (47-69) years. There was no treatment effect on avoidance of hyperglycemia (7445 of 8676 patients [85.8%] in the intervention group vs 7559 of 8815 [85.8%] in the control group; rate ratio [RR], 1.00; 95% CI, 0.99-1.01) or hypothermia (7602 of 11 447 patients [66.4%] in the intervention group vs 7783 of 11 672 [66.7.%] in the control group; RR, 1.00; 95% CI, 0.97-1.02). Intraoperative glucose measurement was more common among patients with diabetes in the intervention group (RR, 1.07; 95% CI, 1.01-1.15), but other secondary outcomes were not significantly different.

Conclusions and Relevance

In this randomized clinical trial, anesthesia care quality measures did not differ between groups, with high confidence in the findings. These results suggest that the intervention did not affect the targeted care practices. Further streamlining of clinical decision support and workflows may help the intraoperative telemedicine program achieve improvement in targeted clinical measures.

Trial Registration

ClinicalTrials.gov Identifier: NCT02830126.

Determinants of information provided by anaesthesiologists to relatives of patients during surgical procedures

Background

Data and interventions are lacking for family-centred perioperative care in adults. Perioperative information given to relatives by nurses or surgeons is associated with improved satisfaction and fewer symptoms of anxiety for relatives and the patient themselves. However, the frequency of the provision of information by anaesthesiologists to patients' relatives during surgery has never been reported.

Methods

A cross-sectional survey was sent to French anaesthesiologists in October 2020 to inquire how often they provided information to patients' family members during surgery and what factors led to them providing information frequently (i.e. in more than half of cases).

Results

Among 607 anaesthesiologists, 53% (319/607) were male, with median age 47 (36-60) yr and nearly half (43%, 260/607) reported more than 20 years of clinical experience; most responders (96%, 580/607) mainly treated adults. Forty-nine (8%) anaesthesiologists declared that they frequently provide information to relatives during surgery. After multivariate analysis, age >50 yr, female gender, and paediatric practice were associated with providing information more frequently. Reasons for not providing information included a lack of time and dedicated space to talk to relatives. Urgent surgery or surgery lasting >2 h were identified as factors associated with provision of information to relatives.

Conclusions

Giving information to relatives during surgery is not a common practice among anaesthesiologists. It depends on individual anaesthesiologists' personal characteristics and practice. Information during surgery could be provided systematically in situations identified as being the most important by anaesthesiologists in our survey. By creating new pathways of information, we could reduce stress and anxiety of patients and relatives.

Relationship between circulating senescence-associated secretory phenotype levels and severity of type 2 diabetes-associated periodontitis: A cross-sectional study

BACKGROUND

Senescence-associated secretory phenotype (SASP) has recently been found to drive comorbid diabetes and periodontitis by inducing a chronic, low-degree inflammatory state. Here, we sought to explore the relationship between circulating SASP and the severity of type 2 diabetes-associated periodontitis (DP).

METHODS

Eighty patients (middle-aged periodontitis, M-P group; aged periodontitis, A-P group; M-DP group; and A-DP group; n = 20) provided gingival epithelium, serum, and periodontal clinical parameters. Circulating levels of 12 DP-related SASP factors were analyzed by immunoassay. Correlation between periodontal clinical parameters and circulating SASP levels was analyzed by Spearman's rank correlation coefficient and back propagation artificial neural network (BPNN). Senescence markers (p16, p21, and HMGB1) in gingiva were determined by immunofluorescence assay.

RESULTS

M-DP group had increased serum levels of twelve SASP factors compared with the M-P group (p < 0.5). Serum levels of IL-6, IL-4, and RAGE were higher in the A-DP group than the A-P group (p < 0.5). The circulating concentrations of certain SASP proteins, including IL-1β, IL-4, MMP-8, OPG, RANKL, and RAGE were correlated with the clinical parameters of DP. BPNN showed that serum SASP levels had considerable predictive value for CAL of DP. Additionally, the DP group had higher expressions of p16, p21, and cytoplasmic-HMGB1 in the gingiva than the P group (p < 0.5).

CONCLUSIONS

Significantly enhanced circulating SASP levels and aggravated periodontal destruction were observed in patients with DP. Importantly, a non-negligible association between serum SASP levels and the severity of DP was found.

Tool-tissue force segmentation and pattern recognition for evaluating neurosurgical performance

Surgical data quantification and comprehension expose subtle patterns in tasks and performance. Enabling surgical devices with artificial intelligence provides surgeons with personalized and objective performance evaluation: a virtual surgical assist. Here we present machine learning models developed for analyzing surgical finesse using tool-tissue interaction force data in surgical dissection obtained from a sensorized bipolar forceps. Data modeling was performed using 50 neurosurgery procedures that involved elective surgical treatment for various intracranial pathologies. The data collection was conducted by 13 surgeons of varying experience levels using sensorized bipolar forceps, SmartForceps System. The machine learning algorithm constituted design and implementation for three primary purposes, i.e., force profile segmentation for obtaining active periods of tool utilization using T-U-Net, surgical skill classification into Expert and Novice, and surgical task recognition into two primary categories of Coagulation versus non-Coagulation using FTFIT deep learning architectures. The final report to surgeon was a dashboard containing recognized segments of force application categorized into skill and task classes along with performance metrics charts compared to expert level surgeons. Operating room data recording of > 161 h containing approximately 3.6 K periods of tool operation was utilized. The modeling resulted in Weighted F1-score = 0.95 and AUC = 0.99 for force profile segmentation using T-U-Net, Weighted F1-score = 0.71 and AUC = 0.81 for surgical skill classification, and Weighted F1-score = 0.82 and AUC = 0.89 for surgical task recognition using a subset of hand-crafted features augmented to FTFIT neural network. This study delivers a novel machine learning module in a cloud, enabling an end-to-end platform for intraoperative surgical performance monitoring and evaluation. Accessed through a secure application for professional connectivity, a paradigm for data-driven learning is established.

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.

Evolving with technology: Machine learning as an opportunity for operating room nurses to improve surgical care-A commentary

AIMS

To describe machine learning applications in an operating room setting, raise awareness of the lack of nursing inclusion on machine learning algorithm development, and show how operating room nurses can co-create this new technology.

BACKGROUND

Operating room nurses and managers perform anticipatory work on a daily basis to manage intrinsic and extrinsic factors that can cause surgical delays.

EVALUATION

Recent literature on machine learning and its potential use in operating room settings was reviewed along with literature on the role of the nurse in co-creating novel technology.

KEY ISSUE

Machine learning technology is rapidly evolving and being created for the operating room environment to improve patient safety and flow. Operating room nurses and managers are not being included in the development of machine learning algorithms, meaning products may be created that are not usable for all members of the surgical team.

CONCLUSION

This commentary highlights the ways machine learning effectively assists nurses and nursing managers, suggesting a pathway forward for surgical nursing as co-creators and implementers.

IMPLICATION FOR NURSING MANAGEMENT

Nursing managers will be exposed to machine learning programmes in the near future and need to understand the benefits they have for patient safety and patient flow.

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.