Use of artificial intelligence for decision-support to avoid high-risk behaviors during laparoscopic cholecystectomy.

INTRODUCTION: Bile duct injuries (BDIs) are a significant source of morbidity among patients undergoing laparoscopic cholecystectomy (LC). GoNoGoNet is an artificial intelligence (AI) algorithm that has been developed and validated to identify safe ("Go") and dangerous ("No-Go") zones of dissection during LC, with the potential to prevent BDIs through real-time intraoperative decision-support. This study evaluates GoNoGoNet's ability to predict Go/No-Go zones during LCs with BDIs. METHODS AND PROCEDURES: Eleven LC videos with BDI (BDI group) were annotated by GoNoGoNet. All tool-tissue interactions, including the one that caused the BDI, were characterized in relation to the algorithm's predicted location of Go/No-Go zones. These were compared to another 11 LC videos with cholecystitis (control group) deemed to represent "safe cholecystectomy" by experts. The probability threshold of GoNoGoNet annotations were then modulated to determine its relationship to Go/No-Go predictions. Data is shown as % difference [99% confidence interval]. RESULTS: Compared to control, the BDI group showed significantly greater proportion of sharp dissection (+ 23.5% [20.0-27.0]), blunt dissection (+ 32.1% [27.2-37.0]), and total interactions (+ 33.6% [31.0-36.2]) outside of the Go zone. Among injury-causing interactions, 4 (36%) were in the No-Go zone, 2 (18%) were in the Go zone, and 5 (45%) were outside both zones, after maximizing the probability threshold of the Go algorithm. CONCLUSION: AI has potential to detect unsafe dissection and prevent BDIs through real-time intraoperative decision-support. More work is needed to determine how to optimize integration of this technology into the operating room workflow and adoption by end-users.

What is the educational value and clinical utility of artificial intelligence for intraoperative and postoperative video analysis? A survey of surgeons and trainees.

INTRODUCTION: Surgical complications often occur due to lapses in judgment and decision-making. Advances in artificial intelligence (AI) have made it possible to train algorithms that identify anatomy and interpret the surgical field. These algorithms can potentially be used for intraoperative decision-support and postoperative video analysis and feedback. Despite the very early success of proof-of-concept algorithms, it remains unknown whether this innovation meets the needs of end-users or how best to deploy it. This study explores users' opinion on the value, usability and design for adapting AI in operating rooms. METHODS: A device-agnostic web-accessible software was developed to provide AI inference either (1) intraoperatively on a live video stream (synchronous mode), or (2) on an uploaded video or image file (asynchronous mode) postoperatively for feedback. A validated AI model (GoNoGoNet), which identifies safe and dangerous zones of dissection during laparoscopic cholecystectomy, was used as the use case. Surgeons and trainees performing laparoscopic cholecystectomy interacted with the AI platform and completed a 5-point Likert scale survey to evaluate the educational value, usability and design of the platform. RESULTS: Twenty participants (11 surgeons and 9 trainees) evaluated the platform intraoperatively (n = 10) and postoperatively (n = 11). The majority agreed or strongly agreed that AI is an effective adjunct to surgical training (81%; neutral = 10%), effective for providing real-time feedback (70%; neutral = 20%), postoperative feedback (73%; neutral = 27%), and capable of improving surgeon confidence (67%; neutral = 29%). Only 40% (neutral = 50%) and 57% (neutral = 43%) believe that the tool is effective in improving intraoperative decisions and performance, or beneficial for patient care, respectively. Overall, 38% (neutral = 43%) reported they would use this platform consistently if available. The majority agreed or strongly agreed that the platform was easy to use (81%; neutral = 14%) and has acceptable resolution (62%; neutral = 24%), while 30% (neutral = 20%) reported that it disrupted the OR workflow, and 20% (neutral = 0%) reported significant time lag. All respondents reported that such a system should be available "on-demand" to turn on/off at their discretion. CONCLUSIONS: Most found AI to be a useful tool for providing support and feedback to surgeons, despite several implementation obstacles. The study findings will inform the future design and usability of this technology in order to optimize its clinical impact and adoption by end-users.

Genomics4RD: An integrated platform to share Canadian deep-phenotype and multiomic data for international rare disease gene discovery.

Despite recent progress in the understanding of the genetic etiologies of rare diseases (RDs), a significant number remain intractable to diagnostic and discovery efforts. Broad data collection and sharing of information among RD researchers is therefore critical. In 2018, the Care4Rare Canada Consortium launched the project C4R-SOLVE, a subaim of which was to collect, harmonize, and share both retrospective and prospective Canadian clinical and multiomic data. Here, we introduce Genomics4RD, an integrated web-accessible platform to share Canadian phenotypic and multiomic data between researchers, both within Canada and internationally, for the purpose of discovering the mechanisms that cause RDs. Genomics4RD has been designed to standardize data collection and processing, and to help users systematically collect, prioritize, and visualize participant information. Data storage, authorization, and access procedures have been developed in collaboration with policy experts and stakeholders to ensure the trusted and secure access of data by external researchers. The breadth and standardization of data offered by Genomics4RD allows researchers to compare candidate disease genes and variants between participants (i.e., matchmaking) for discovery purposes, while facilitating the development of computational approaches for multiomic data analyses and enabling clinical translation efforts for new genetic technologies in the future.

Expanding the Boundaries of RNA Sequencing as a Diagnostic Tool for Rare Mendelian Disease.

Gene-panel and whole-exome analyses are now standard methodologies for mutation detection in Mendelian disease. However, the diagnostic yield achieved is at best 50%, leaving the genetic basis for disease unsolved in many individuals. New approaches are thus needed to narrow the diagnostic gap. Whole-genome sequencing is one potential strategy, but it currently has variant-interpretation challenges, particularly for non-coding changes. In this study we focus on transcriptome analysis, specifically total RNA sequencing (RNA-seq), by using monogenetic neuromuscular disorders as proof of principle. We examined a cohort of 25 exome and/or panel "negative" cases and provided genetic resolution in 36% (9/25). Causative mutations were identified in coding and non-coding exons, as well as in intronic regions, and the mutational pathomechanisms included transcriptional repression, exon skipping, and intron inclusion. We address a key barrier of transcriptome-based diagnostics: the need for source material with disease-representative expression patterns. We establish that blood-based RNA-seq is not adequate for neuromuscular diagnostics, whereas myotubes generated by transdifferentiation from an individual's fibroblasts accurately reflect the muscle transcriptome and faithfully reveal disease-causing mutations. Our work confirms that RNA-seq can greatly improve diagnostic yield in genetically unresolved cases of Mendelian disease, defines strengths and challenges of the technology, and demonstrates the suitability of cell models for RNA-based diagnostics. Our data set the stage for development of RNA-seq as a powerful clinical diagnostic tool that can be applied to the large population of individuals with undiagnosed, rare diseases and provide a framework for establishing minimally invasive strategies for doing so.

EpigenCentral: Portal for DNA methylation data analysis and classification in rare diseases.

Epigenetic processes play a key role in regulating gene expression. Genetic variants that disrupt chromatin-modifying proteins are associated with a broad range of diseases, some of which have specific epigenetic patterns, such as aberrant DNA methylation (DNAm), which may be used as disease biomarkers. While much of the epigenetic research has focused on cancer, there is a paucity of resources devoted to neurodevelopmental disorders (NDDs), which include autism spectrum disorder and many rare, clinically overlapping syndromes. To address this challenge, we created EpigenCentral, a free web resource for biomedical researchers, molecular diagnostic laboratories, and clinical practitioners to perform the interactive classification and analysis of DNAm data related to NDDs. It allows users to search for known disease-associated patterns in their DNAm data, classify genetic variants as pathogenic or benign to assist in molecular diagnostics, or analyze patterns of differential methylation in their data through a simple web form. EpigenCentral is freely available at http://epigen.ccm.sickkids.ca/.

Phenotate: crowdsourcing phenotype annotations as exercises in undergraduate classes.

PURPOSE: Computational documentation of genetic disorders is highly reliant on structured data for differential diagnosis, pathogenic variant identification, and patient matchmaking. However, most information on rare diseases (RDs) exists in freeform text, such as academic literature. To increase availability of structured RD data, we developed a crowdsourcing approach for collecting phenotype information using student assignments. METHODS: We developed Phenotate, a web application for crowdsourcing disease phenotype annotations through assignments for undergraduate genetics students. Using student-collected data, we generated composite annotations for each disease through a machine learning approach. These annotations were compared with those from clinical practitioners and gold standard curated data. RESULTS: Deploying Phenotate in five undergraduate genetics courses, we collected annotations for 22 diseases. Student-sourced annotations showed strong similarity to gold standards, with F-measures ranging from 0.584 to 0.868. Furthermore, clinicians used Phenotate annotations to identify diseases with comparable accuracy to other annotation sources and gold standards. For six disorders, no gold standards were available, allowing us to create some of the first structured annotations for them, while students demonstrated ability to research RDs. CONCLUSION: Phenotate enables crowdsourcing RD phenotypic annotations through educational assignments. Presented as an intuitive web-based tool, it offers pedagogical benefits and augments the computable RD knowledgebase.

Correction: Phenotate: crowdsourcing phenotype annotations as exercises in undergraduate classes.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Development, deployment and scaling of operating room-ready artificial intelligence for real-time surgical decision support.

Deep learning for computer vision can be leveraged for interpreting surgical scenes and providing surgeons with real-time guidance to avoid complications. However, neither generalizability nor scalability of computer-vision-based surgical guidance systems have been demonstrated, especially to geographic locations that lack hardware and infrastructure necessary for real-time inference. We propose a new equipment-agnostic framework for real-time use in operating suites. Using laparoscopic cholecystectomy and semantic segmentation models for predicting safe/dangerous ("Go"/"No-Go") zones of dissection as an example use case, this study aimed to develop and test the performance of a novel data pipeline linked to a web-platform that enables real-time deployment from any edge device. To test this infrastructure and demonstrate its scalability and generalizability, lightweight U-Net and SegFormer models were trained on annotated frames from a large and diverse multicenter dataset from 136 institutions, and then tested on a separate prospectively collected dataset. A web-platform was created to enable real-time inference on any surgical video stream, and performance was tested on and optimized for a range of network speeds. The U-Net and SegFormer models respectively achieved mean Dice scores of 57% and 60%, precision 45% and 53%, and recall 82% and 75% for predicting the Go zone, and mean Dice scores of 76% and 76%, precision 68% and 68%, and recall 92% and 92% for predicting the No-Go zone. After optimization of the client-server interaction over the network, we deliver a prediction stream of at least 60 fps and with a maximum round-trip delay of 70 ms for speeds above 8 Mbps. Clinical deployment of machine learning models for surgical guidance is feasible and cost-effective using a generalizable, scalable and equipment-agnostic framework that lacks dependency on hardware with high computing performance or ultra-fast internet connection speed.

Assessment of Machine Learning-Based Medical Directives to Expedite Care in Pediatric Emergency Medicine.

Importance: Increased wait times and long lengths of stay in emergency departments (EDs) are associated with poor patient outcomes. Systems to improve ED efficiency would be useful. Specifically, minimizing the time to diagnosis by developing novel workflows that expedite test ordering can help accelerate clinical decision-making. Objective: To explore the use of machine learning-based medical directives (MLMDs) to automate diagnostic testing at triage for patients with common pediatric ED diagnoses. Design, Setting, and Participants: Machine learning models trained on retrospective electronic health record data were evaluated in a decision analytical model study conducted at the ED of the Hospital for Sick Children Toronto, Canada. Data were collected on all patients aged 0 to 18 years presenting to the ED from July 1, 2018, to June 30, 2019 (77 219 total patient visits). Exposure: Machine learning models were trained to predict the need for urinary dipstick testing, electrocardiogram, abdominal ultrasonography, testicular ultrasonography, bilirubin level testing, and forearm radiographs. Main Outcomes and Measures: Models were evaluated using area under the receiver operator curve, true-positive rate, false-positive rate, and positive predictive values. Model decision thresholds were determined to limit the total number of false-positive results and achieve high positive predictive values. The time difference between patient triage completion and test ordering was assessed for each use of MLMD. Error rates were analyzed to assess model bias. In addition, model explainability was determined using Shapley Additive Explanations values. Results: There was a total of 42 238 boys (54.7%) included in model development; mean (SD) age of the children was 5.4 (4.8) years. Models obtained high area under the receiver operator curve (0.89-0.99) and positive predictive values (0.77-0.94) across each of the use cases. The proposed implementation of MLMDs would streamline care for 22.3% of all patient visits and make test results available earlier by 165 minutes (weighted mean) per affected patient. Model explainability for each MLMD demonstrated clinically relevant features having the most influence on model predictions. Models also performed with minimal to no sex bias. Conclusions and Relevance: The findings of this study suggest the potential for clinical automation using MLMDs. When integrated into clinical workflows, MLMDs may have the potential to autonomously order common ED tests early in a patient's visit with explainability provided to patients and clinicians.

Prospective observational study and serosurvey of SARS-CoV-2 infection in asymptomatic healthcare workers at a Canadian tertiary care center.

Health care workers (HCWs) are at higher risk for SARS-CoV-2 infection and may play a role in transmitting the infection to vulnerable patients and members of the community. This is particularly worrisome in the context of asymptomatic infection. We performed a cross-sectional study looking at asymptomatic SARS-CoV-2 infection in HCWs. We screened asymptomatic HCWs for SARS-CoV-2 via PCR. Complementary viral genome sequencing was performed on positive swab specimens. A seroprevalence analysis was also performed using multiple assays. Asymptomatic health care worker cohorts had a combined swab positivity rate of 29/5776 (0.50%, 95%CI 0.32-0.75) relative to a comparative cohort of symptomatic HCWs, where 54/1597 (3.4%) tested positive for SARS-CoV-2 (ratio of symptomatic to asymptomatic 6.8:1). SARS-CoV-2 seroprevalence among 996 asymptomatic HCWs with no prior known exposure to SARS-CoV-2 was 1.4-3.4%, depending on assay. A novel in-house Coronavirus protein microarray showed differing SARS-CoV-2 protein reactivities and helped define likely true positives vs. suspected false positives. Our study demonstrates the utility of routine screening of asymptomatic HCWs, which may help to identify a significant proportion of infections.

Quality Indicators as Predictors of Future Inspection Performance in Ontario Nursing Homes.

OBJECTIVES: There are several mechanisms for monitoring the quality of care in long-term care (LTC), including the use of quality indicators derived from resident assessments and formal inspections. The LTC inspection process is time and resource-intensive, and there may be opportunities to better target inspections. In this study, we aimed to examine whether quality indicators could predict future inspection performance in LTC homes across Ontario, Canada. SETTING AND PARTICIPANTS: In total, 594 LTC homes across Ontario. METHODS: Using a database compiling detailed inspection reports for the period from 2017 to 2018, we classified each home into 1 of 3 categories (in good standing, needing improvement, needing significant improvement). Machine learning techniques were used to examine whether publicly available Resident Assessment Instrument‒Minimum Data Set quality indicators for the period 2016‒2017 could predict facility classification based on inspection results. RESULTS: After running a wide range of models, only a weak relationship was found between quality indicators and future inspection performance. The best-performing model was able to achieve a classification accuracy of 40.1%. Feature analysis was performed on the final model to identify which quality indicators were most indicative of predicted poor performance. Experiencing worsened pain, restraint use, and worsened pressure ulcers were correlated with homes predicted as needing significant improvement. Counterintuitively, improved physical functioning had an inverse relationship with homes predicted as being in good standing. CONCLUSIONS AND IMPLICATIONS: Most quality indicators are poor predictors of inspection performance. Further work is required to explore the limited relationship between these 2 measures of LTC quality, and to identify other quality measures that may be useful as predictors of facilities facing difficulty in meeting quality standards.