Accurate surgery duration estimation is necessary for optimal OR planning, which plays an important role in patient comfort and safety as well as resource optimization. It is, however, challenging to preoperatively predict surgery duration since it varies significantly depending on the patient condition, surgeon skills, and intraoperative situation. In this paper, we propose a deep learning pipeline, referred to as RSDNet, which automatically estimates the remaining surgery duration (RSD) intraoperatively by using only visual information from laparoscopic videos. Previous state-of-the-art approaches for RSD prediction are dependent on manual annotation, whose generation requires expensive expert knowledge and is time-consuming, especially considering the numerous types of surgeries performed in a hospital and the large number of laparoscopic videos available. A crucial feature of RSDNet is that it does not depend on any manual annotation during training, making it easily scalable to many kinds of surgeries. The generalizability of our approach is demonstrated by testing the pipeline on two large datasets containing different types of surgeries: 120 cholecystectomy and 170 gastric bypass videos. The experimental results also show that the proposed network significantly outperforms a traditional method of estimating RSD without utilizing manual annotation. Further, this work provides a deeper insight into the deep learning network through visualization and interpretation of the features that are automatically learned.

pdf/rsdnet-learning-to-predict-remaining-surgery-duration-from-3cx2fp573d.pdf

RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations

Accurate surgery duration estimation is necessary for optimal OR planning, which plays an important role in patient comfort and safety as well as resource optimization. It is, however, challenging to preoperatively predict surgery duration since it varies significantly depending on the patient condition, surgeon skills, and intraoperative situation. In this paper, we propose a deep learning pipeline, referred to as RSDNet, which automatically estimates the remaining surgery duration (RSD) intraoperatively by using only visual information from laparoscopic videos. The previous state-of-the-art approaches for RSD prediction are dependent on manual annotation, whose generation requires expensive expert knowledge and is time-consuming, especially considering the numerous types of surgeries performed in a hospital and the large number of laparoscopic videos available. A crucial feature of RSDNet is that it does not depend on any manual annotation during training, making it easily scalable to many kinds of surgeries. The generalizability of our approach is demonstrated by testing the pipeline on two large datasets containing different types of surgeries: 120 cholecystectomy and 170 gastric bypass videos. The experimental results also show that the proposed network significantly outperforms a traditional method of estimating RSD without utilizing manual annotation. Further, this paper provides a deeper insight into the deep learning network through visualization and interpretation of the features that are automatically learned.

In many hospitals there are patients who receive surgery later than what is medically indicated. In one of Europe’s largest hospitals, the University Hospital Leuven, this is the case for approximately every third patient. Serving patients late cannot always be avoided as a highly utilized OR department will sometimes suffer capacity shortage, occasionally leading to unavoidable delays in patient care. Nevertheless, serving patients late is a problem as it exposes them to an increased health risk and hence should be avoided whenever possible. In order to improve the current situation, the delay in patient scheduling had to be quantified and the responsible mechanism, the scheduling process, had to be better understood. Drawing from this understanding, we implemented and tested realistic patient scheduling methods in a discrete event simulation model. We found that it is important to model non-elective arrivals and to include elective rescheduling decisions made on surgery day itself. Rescheduling ensures that OR related performance measures, such as overtime, will only loosely depend on the chosen patient scheduling method. We also found that capacity considerations should guide actions performed before the surgery day such as patient scheduling and patient replanning. This is the case as those scheduling strategies that ensure that OR capacity is efficiently used will also result in a high number of patients served within their medically indicated time limit. An efficient use of OR capacity can be achieved, for instance, by serving patients first come, first served. As applying first come, first served might not always be possible in a real setting, we found it is important to allow for patient replanning.

/pdf/due-time-driven-surgery-scheduling-3dlkh0tcxl.pdf

Due time driven surgery scheduling

Background A new method of scheduling anesthesia-controlled time (ACT) was implemented on July 1, 2012 in an academic inpatient operating room (OR) department. This study examined the relationship between this new scheduling method and OR performance. The new method comprised the development of predetermined time frames per anesthetic technique based on historical data of the actual time needed for anesthesia induction and emergence. Seven "anesthesia scheduling packages" (0 to 6) were established. Several options based on the quantity of anesthesia monitoring and the complexity of the patient were differentiated in time within each package. Study Design This was a quasi-experimental time-series design. Relevant data were divided into 4 equal periods of time. These time periods were compared with ANOVA with contrast analysis: an intervention, pre-intervention, and post-intervention contrast were tested. All emergency cases were excluded. A total of 34,976 inpatient elective cases performed from January 1, 2010 to December 31, 2014 were included for statistical analyses. Results The intervention contrast showed a significant decrease (p Conclusions Scheduling the 2 major components of a procedure (anesthesia- and surgeon-controlled time) more accurately leads to fewer case cancellations, lower prediction errors, and smoother OR workflow in a university hospital setting.

https://www.journalacs.org/article/S1072-7515(16)30041-2/pdf

Scheduling Anesthesia Time Reduces Case Cancellations and Improves Operating Room Workflow in a University Hospital Setting

OBJECTIVE This study analyzes multiple factors and their significance in determining the operative timing for cochlear implants at one institution over a 10-year period. STUDY DESIGN Retrospective case review. SETTING Tertiary referral center. PATIENTS All patients including both adult and pediatric undergoing cochlear implantation from 2002 through January 2012. INTERVENTION(S) Cochlear implantation. MAIN OUTCOME MEASURE(S) The overall operative room time and surgical duration for patients undergoing cochlear implantation. Individual factors analyzed for influence on timing included center experience, surgeon experience, location (main OR, children's OR, outpatient OR), patient age, patient sex, bilaterality, anatomical consideration, complications, and the involvement of residents and fellows. RESULTS ANOVA analysis of individual factors. Factors associated with increased surgical duration included bilateral implants, abnormal inner ear anatomy, and intraoperative complications. Factors associated with time outside the operation included surgical duration, the surgical suite type, and the availability of a fellow. Total operating room time was significantly reduced in an outpatient setting and in quicker performed procedures. CONCLUSIONS The influence of factors affecting both surgical duration and time in the operating room can be predicted and used to provide more accurate estimates of operating room time.

The Utility of a Predictive Model for Cochlear Implant Operating Time.

Objective To assess the accuracy of surgeons and anaesthetists in predicting the time it will take them to complete an operation or procedure and therefore explain some of the difficulties encountered in operating theatre scheduling.

Design Single centre, prospective observational study.

Setting Plastic, orthopaedic, and general surgical operating theatres at a level 1 trauma centre serving a population of about 370 000.

Participants 92 operating theatre staff including surgical consultants, surgical registrars, anaesthetic consultants, and anaesthetic registrars.

Intervention Participants were asked how long they thought their procedure would take. These data were compared with actual time data recorded at the end of the case.

Primary outcome measure Absolute difference between predicted and actual time.

Results General surgeons underestimated the time required for the procedure by 31 minutes (95% confidence interval 7.6 to 54.4), meaning that procedures took, on average, 28.7% longer than predicted. Plastic surgeons underestimated by 5 minutes (−12.4 to 22.4), with procedures taking an average of 4.5% longer than predicted. Orthopaedic surgeons overestimated by 1 minute (−16.4 to 14.0), with procedures taking an average of 1.1% less time than predicted. Anaesthetists underestimated by 35 minutes (21.7 to 48.7), meaning that, on average, procedures took 167.5% longer than they predicted. The four specialty mean time overestimations or underestimations are significantly different from each other (P=0.01). The observed time differences between anaesthetists and both orthopaedic and plastic surgeons are significantly different (P<0.05), but the time difference between anaesthetists and general surgeons is not significantly different.

Conclusion The inability of clinicians to predict the necessary time for a procedure is a significant cause of delay in the operating theatre. This study suggests that anaesthetists are the most inaccurate and highlights the potential differences between specialties in what is considered part of the “anaesthesia time.”

https://www.bmj.com/content/bmj/349/bmj.g7182.full.pdf

Operating theatre time, where does it all go? A prospective observational study.

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Jason Donovan

Author Tools

Chat about Author

Papers

Operating theatre time, where does it all go? A prospective observational study.