IntroductionMortality and morbidity following surgery are pressing public health concerns in the USA. Traditional prediction models for postoperative adverse outcomes demonstrate good discrimination at the population level, but the ability to forecast an individual patient’s trajectory in real time remains poor. We propose to apply machine learning techniques to perioperative time-series data to develop algorithms for predicting adverse perioperative outcomes.Methods and analysisThis study will include all adult patients who had surgery at our tertiary care hospital over a 4-year period. Patient history, laboratory values, minute-by-minute intraoperative vital signs and medications administered will be extracted from the electronic medical record. Outcomes will include in-hospital mortality, postoperative acute kidney injury and postoperative respiratory failure. Forecasting algorithms for each of these outcomes will be constructed using density-based logistic regression after employing a Nadaraya-Watson kernel density estimator. Time-series variables will be analysed using first and second-order feature extraction, shapelet methods and convolutional neural networks. The algorithms will be validated through measurement of precision and recall.Ethics and disseminationThis study has been approved by the Human Research Protection Office at Washington University in St Louis. The successful development of these forecasting algorithms will allow perioperative healthcare clinicians to predict more accurately an individual patient’s risk for specific adverse perioperative outcomes in real time. Knowledge of a patient’s dynamic risk profile may allow clinicians to make targeted changes in the care plan that will alter the patient’s outcome trajectory. This hypothesis will be tested in a future randomised controlled trial.
BackgroundMajor postoperative morbidity and mortality remain common despite efforts to improve patient outcomes. Health information technologies have the potential to actualize advances in perioperative patient care, but failure to evaluate the usability of these technologies may hinder their implementation and acceptance. This protocol describes the usability testing of an innovative telemedicine-based intra-operative clinical support system, the Anesthesiology Control Tower, in which a team led by an attending anesthesiologist will use a combination of established and novel information technologies to provide evidence-based support to their colleagues in the operating room.MethodsTwo phases of mixed-methods usability testing will be conducted in an iterative manner and will evaluate both the individual components of the Anesthesiology Control Tower and their integration as a whole. Phase I testing will employ two separate “think-aloud” protocol analyses with the two groups of end users. Segments will be coded and analyzed for usability issues. Phase II will involve a qualitative and quantitative in situ usability and feasibility analysis. Results from each phase will inform the revision and improvement of the Control Tower prototype throughout our testing and analysis process. The final prototype will be evaluated in the form of a pragmatic randomized controlled clinical trial.DiscussionThe Anesthesiology Control Tower has the potential to revolutionize the standard of care for perioperative medicine. Through the thorough and iterative usability testing process described in this protocol, we will maximize the usefulness of this novel technology for our clinicians, thus improving our ability to implement this innovation into the model of care for perioperative medicine.Trial registrationThe study that this protocol describes has been registered in clinicaltrials.gov as NCT02830126.
Background Despite efforts to improve patient outcomes, major morbidity and mortality remain common after surgery. Health information technologies that provide decision support for clinicians might improve perioperative and postoperative patient care. Evaluating the usability of these technologies and barriers to their implementation can facilitate their acceptance within health systems. Objective This manuscript describes usability testing and refinement of an innovative telemedicine-based clinical support system, the Anesthesiology Control Tower (ACT). It also reports stakeholders’ perceptions of the barriers and facilitators to implementation of the intervention. Methods Three phases of testing were conducted in an iterative manner. Phase 1 testing employed a think-aloud protocol analysis to identify surface-level usability problems with individual software components of the ACT and its structure. Phase 2 testing involved an extended qualitative and quantitative real-world usability analysis. Phase 3 sought to identify major barriers and facilitators to implementation of the ACT through semistructured interviews with key stakeholders. Results Phase 1 and phase 2 usability testing sessions identified numerous usability problems with the software components of the ACT. The ACT platform was revised in seven iterations in response to these usability concerns. Initial satisfaction with the ACT, as measured by standardized instruments, was below commonly accepted cutoffs for these measures. Satisfaction improved to acceptable levels over the course of revision and testing. A number of barriers to implementation were also identified and addressed during the refinement of the ACT intervention. Conclusions The ACT model can improve the standard of perioperative anesthesia care. Through our thorough and iterative usability testing process and stakeholder assessment of barriers and facilitators, we enhanced the acceptability of this novel technology and improved our ability to implement this innovation into routine practice. International Registered Report Identifier (IRRID) RR2-10.1186/s40814-018-0233-4
The management of infants and children presenting for thoracic surgery poses a variety of challenges for anesthesiologists. A thorough understanding of the implications of developmental changes in cardiopulmonary anatomy and physiology, associated comorbid conditions, and the proposed surgical intervention is essential in order to provide safe and effective clinical care. This narrative review discusses the perioperative anesthetic management of pediatric patients undergoing noncardiac thoracic surgery, beginning with the preoperative assessment. The considerations for the implementation and management of one-lung ventilation (OLV) will be reviewed, and as will the anesthetic implications of different surgical procedures including bronchoscopy, mediastinoscopy, thoracotomy, and thoracoscopy. We will also discuss pediatric-specific disease processes presenting in neonates, infants, and children, with an emphasis on those with unique impact on anesthetic management.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.