An intelligent hospital operating room to improve patient health care

A systematic scoping review protocol to summarise and appraise the use of artificial intelligence in the analysis of digital videos of invasive general surgical procedures

Background

Intraoperative video recordings are a valuable addition to operative written documentation. However, the review of these videos often requires surgical expertise and takes considerable time. While a large amount of work has been undertaken to understand the role of artificial intelligence (AI) in healthcare more generally, the application of these techniques to automate the analysis of surgical videos is currently unclear. In this systematic scoping review, we sought to give a contemporary overview of the use of AI research in the analysis of digital videos of invasive general surgical procedures. We will describe and summarise the study characteristics, purpose of the applications and stage of development, to ascertain how these techniques might be applied in future research and to identify gaps in current knowledge (e.g. uncertainties about the study methods).

Methods

Systematic searches will be conducted in OVID Medline and Embase, using terms related to 'artificial intelligence', 'surgery' and 'video' to identify all potentially relevant studies published since 1st January 2012. All primary studies where AI has been applied to the analysis of videos (recorded by conventional digital cameras or laparoscopic or robotic-assisted technology) of general surgical procedures will be included. Data extraction will include study characteristics, governance, details of video datasets and AI models, measures of accuracy, validation and any reported limitations.

Ethics and dissemination

No ethical approval is required as primary data will not be collected. The results will be disseminated at relevant conferences, on social media and published in a peer-reviewed journal.

Surgical data recording in the operating room: a systematic review of modalities and metrics

INTRODUCTION

Operating room recording, via video, audio and sensor-based recordings, is increasingly common. Yet, surgical data science is a new field without clear guidelines. The purpose of this study is to examine existing published studies of surgical recording modalities to determine which are available for use in the operating room, as a first step towards developing unified standards for this field.

METHODS

Medline, EMBASE, CENTRAL and PubMed databases were systematically searched for articles describing modalities of data collection in the operating room. Search terms included 'video-audio media', 'bio-sensing techniques', 'sound', 'movement', 'operating rooms' and others. Title, abstract and full-text screening were completed to identify relevant articles. Descriptive statistical analysis was performed for included studies.

RESULTS

From 3756 citations, 91 studies met inclusion criteria. These studies described 10 unique data-collection modalities for 17 different purposes in the operating room. Data modalities included video, audio, kinematic and eye-tracking among others. Data-collection purposes described included surgical trainee assessment, surgical error, surgical team communication and operating room efficiency.

CONCLUSION

Effective data collection and utilization in the operating room are imperative for the provision of superior surgical care. The future operating room landscape undoubtedly includes multiple modalities of data collection for a plethora of purposes. This review acts as a foundation for employing operating room data in a way that leads to meaningful benefit for patient care.

Gastroenterology Procedures Generate Aerosols: An Air Quality Turnover Solution to Mitigate COVID-19's Propagation Risk

The growing fear of virus transmission during the 2019 coronavirus disease (COVID-19) pandemic has called for many scientists to look into the various vehicles of infection, including the potential to travel through aerosols. Few have looked into the issue that gastrointestinal (GI) procedures may produce an abundance of aerosols. The current process of risk management for clinics is to follow a clinic-specific HVAC formula, which is typically calculated once a year and assumes perfect mixing of the air within the space, to determine how many minutes each procedural room refreshes 99% of its air between procedures when doors are closed. This formula is not designed to fit the complex dynamic of small airborne particle transport and deposition that can potentially carry the virus in clinical conditions. It results in reduced procedure throughput as well as an excess of idle time in clinics that process a large number of short procedures such as outpatient GI centers. We present and tested a new cyber-physical system that continuously monitors airborne particle counts in procedural rooms and also at the same time automatically monitors the procedural rooms' state and flexible endoscope status without interfering with the clinic's workflow. We use our data gathered from over 1500 GI cases in one clinical suite to understand the correlation between air quality and standard procedure types as well as identify the risks involved with any HVAC system in a clinical suite environment. Thanks to this system, we demonstrate that standard GI procedures generate large quantities of aerosols, which can potentially promote viral airborne transmission among patients and healthcare staff. We provide a solution for the clinic to improve procedure turnover times and throughput, as well as to mitigate the risk of airborne transmission of the virus.

A Systems Approach to Assess Transport and Diffusion of Hazardous Airborne Particles in a Large Surgical Suite: Potential Impacts on Viral Airborne Transmission

Airborne transmission of viruses, such as the coronavirus 2 (SARS-CoV-2), in hospital systems are under debate: it has been shown that transmission of SARS-CoV-2 virus goes beyond droplet dynamics that is limited to 1 to 2 m, but it is unclear if the airborne viral load is significant enough to ensure transmission of the disease. Surgical smoke can act as a carrier for tissue particles, viruses, and bacteria. To quantify airborne transmission from a physical point of view, we consider surgical smoke produced by thermal destruction of tissue during the use of electrosurgical instruments as a marker of airborne particle diffusion-transportation. Surgical smoke plumes are also known to be dangerous for human health, especially to surgical staff who receive long-term exposure over the years. There are limited quantified metrics reported on long-term effects of surgical smoke on staff's health. The purpose of this paper is to provide a mathematical framework and experimental protocol to assess the transport and diffusion of hazardous airborne particles in every large operating room suite. Measurements from a network of air quality sensors gathered during a clinical study provide validation for the main part of the model. Overall, the model estimates staff exposure to airborne contamination from surgical smoke and biological material. To address the clinical implication over a long period of time, the systems approach is built upon previous work on multi-scale modeling of surgical flow in a large operating room suite and takes into account human behavior factors.

A Continuum of Interfaces to Engage Surgical Staff in Efficient Collaboration

Large hospital surgical suites must combine high quality of care with an efficient management of operations. However, the diversity of procedures, staff, and patients present important challenges for staff collaboration. The complexity of flows between tasks and places, such as interconnections between pre-operation, post-operation and intensive care units, led previous research to address these issues separately using checklists, scheduling, or specialized human-computer interfaces. Approaches to treat the surgical suite as a whole entity have not been explored yet. Here, we build upon a cyber-physical system comprising an electronic whiteboard and different sensors tracking the status of operating rooms to design a continuum of mobile and fixed, shared computer interfaces. The interfaces disseminate the information through different locations and devices and allow for its manipulation in order to foster appropriate collaboration on unforeseen events and decisions. We present our design rationale process, involving the different surgical suite users and stakeholders and report on the architecture of the system.

Maintaining operative efficiency while allowing sufficient time for residents to learn

BACKGROUND

Surgical residents desire independent operating experience but recognize that attendings have a responsibility to keep cases as short as possible.

METHODS

We analyzed video and interviews of attending surgeons related to more than 400 moments in which the resident was the primary operator. We examined these moments for themes related to timing and pace.

RESULTS

Our surgeons encouraged the residents to speed up when patient safety could be jeopardized by the case moving too slowly. In contrast, they encouraged the residents to slow down when performing a crucial step or granting independence. Attending surgeons encouraged speed through economical language, by substituting physical actions for words, and through the use of Intelligent Cooperation. Conversely, they encouraged slowing down via just-in-time mini-lectures and by questioning the trainee.

CONCLUSIONS

We present recommendations for safe teaching in the operating room while simultaneously maintaining overall surgical flow. Teaching residents to operate quickly can save time and is likely based on an automaticity in teaching. Slowing a resident down is vital for trainee skill development and patient safety.

A Cyber-Physical System to Improve the Management of a Large Suite of Operating Rooms

Cyber-physical systems have been deployed with considerable success in many industries. However, the implementation of cyber-physical systems in hospitals has been limited. By nature, in clinical operations, patient safety and consideration for health outcomes are of the utmost importance, thus possibly slowing the implementation of innovative solutions with limited history. Revenues from operating room (OR) time and surgery account for about 50% of the income of major hospitals (Erdogan et al. 2011; Cuschieri 2006), but the efficiency of OR utilization is often reported to be relatively low. Therefore, improving OR management with a cyber-physical system should be a priority. In this article, we will report on our experience implementing a cyber-physical system at Houston Methodist Hospital and discuss some of the difficulties and potential drivers for success. Our pilot study was done in the context of the management of a large suite of ORs. It uses the agile codevelopment of a cyber-physical system through an intense collaboration of clinicians and computational scientists. While technology remains the foundation of a cyber-physical system, this experience reinforced that the human factor is an important driving force behind the design that promotes user acceptance.