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.

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. 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.

Abstract The purpose of this document is to highlight practical recommendations to assist acute care hospitals to prioritize and implement strategies to prevent ventilator-associated pneumonia (VAP), ventilator-associated events (VAE), and non-ventilator hospital-acquired pneumonia (NV-HAP) in adults, children, and neonates. This document updates the Strategies to Prevent Ventilator-Associated Pneumonia in Acute Care Hospitals published in 2014. This expert guidance document is sponsored by the Society for Healthcare Epidemiology (SHEA), and is the product of a collaborative effort led by SHEA, the Infectious Diseases Society of America, the American Hospital Association, the Association for Professionals in Infection Control and Epidemiology, and The Joint Commission, with major contributions from representatives of a number of organizations and societies with content expertise.

/pdf/strategies-to-prevent-ventilator-associated-pneumonia-186mtlas.pdf

Strategies to prevent ventilator-associated pneumonia, ventilator-associated events, and nonventilator hospital-acquired pneumonia in acute-care hospitals: 2022 Update

Airway management techniques are aimed at reducing complications associated with artificial airways and mechanical ventilation, such as retained secretions. The impact of airway management techniques on ventilator-associated events (VAEs) varies considerably by modality. Closed-suction techniques are generally recommended but have limited, if any, impact on VAEs. Normal saline instillation during suctioning is not recommended. Devices designed specifically to remove biofilm from the inside of endotracheal tubes appear to be safe, but their role in VAE prevention is uncertain. Subglottic secretion clearance by artificial cough maneuvers is promising, but more research is needed to assess its clinical feasibility. Continuous cuff-pressure management appears to be effective in reducing microaspiration of subglottic secretions.

http://rc.rcjournal.com/content/respcare/64/8/986.full.pdf

Airway Management and Ventilator-Associated Events

Objective In the present study, we aimed to retrospectively evaluate the preoperative characteristics, intraoperative and postoperative results of patients who underwent laparoscopic obesity surgeries Methods After obtaining the approval of the Ethics Committee, records of patients who underwent laparoscopic obesity surgery from January 2013 to December 2016 were reviewed Demographic characteristics, medications used in anaesthesia and analgesia, the duration of recovery unit/hospital stay, intensive care unit/mechanical ventilation requirements and complications were recorded Results A total of 329 ASA II-III patients over a 3-year period were operated Thiopental and propofol were administered at induction, sevoflurane, isoflurane and desflurane were administered for the maintenance, and vecuronium and rocuronium were administered to aid in neuromuscular blockage The mean durations of recovery unit and hospital stays were 3080±601 minutes and 427±168 days, respectively The hypnotic agent, muscle relaxant or inhalation anaesthetics used did not have a significant effect on the duration of recovery unit and hospital stay Mask ventilation and intubation were noted to be difficult in 55% and 85% of the cases, respectively The presence of obstructive sleep apnoea syndrome and high body mass index and Mallampati scores significantly increased difficult mask ventilation and difficult intubation rates Four patients were transferred to intensive care unit for close monitoring Two patients were re-operated on, two patients had rhabdomyolysis, one patient had Wernicke's encephalopathy and two patients had peripheral neuropathy Perioperative mortality did not occur in any patient Conclusion We believe that appropriate patient selection, the use of well-designed anaesthesia and surgical protocols play important roles in increasing the success rate of patient outcomes and early and late complications in laparoscopic obesity surgery

Retrospective Evaluation of Patients who Underwent Laparoscopic Bariatric Surgery.

BACKGROUND Endotracheal tube (ETT) cuffs are designed to seal the lower airway for precise ventilation and to protect against ingress of pathogens from the pharyngeal space. Therefore, a minimal continuous cuff pressure must be maintained. Aim of this study was to analyse the course of cuff pressure in an in-vitro model during manual cuff pressure control manoeuvres.
METHODS An artificial trachea was intubated with an appropriately sized ETT and cuff pressure set to 20 cm H O. Thirty-two experienced ICU nurses each performed six cuff pressure control manoeuvres (three times in two different ETTs) using a manual cuff pressure manometer. Course of cuff pressure from connecting the manometer to disconnecting it from the cuff pilot balloon was recorded using a pressure transducer.
RESULTS There were 190 cuff pressure control manoeuvres suitable for analysis. In all control manoeuvres a cuff pressure below 20 cm H O was noted. In 20.0% of the control manoeuvres the cuff pressure dropped below 10 cm H O. Cuff pressure drops were mainly caused by initially connecting the manometer to the pilot balloon, less frequently by manipulating the pressure gauge of the manometer. Disconnecting the manometer after the control manoeuvre caused a cuff pressure drop in 78.1% of cases, contributing to a final cuff pressure below 20 cm H O in 31.3% of control manoeuvres.
CONCLUSION Routine manual cuff pressure control manoeuvres in ETT cuffs result in considerable cuff pressure drops. This may have an impact on silent aspiration of pharyngeal contents passing along the cuff into the lower airway.

Endotracheal tube cuff pressure changes during manual cuff pressure control manoeuvres: An in-vitro assessment

Background
In the field of anesthesia for bariatric surgery, a wide variety of recommendations exist, but a general consensus on the perioperative management of such patients is missing. We outline the perioperative experiences that we gained in the first two years after introducing a bariatric program.

/pdf/anesthetic-management-of-patients-undergoing-bariatric-2wcpurrvye.pdf

Bastian Lindauer

Papers

Endotracheal tube cuff pressure changes during manual cuff pressure control manoeuvres: An in-vitro assessment

Anesthetic management of patients undergoing bariatric surgery: two year experience in a single institution in Switzerland