Development of an Artificial Intelligence Tool for Intraoperative Guidance During Endovascular Abdominal Aortic Aneurysm Repair.

BACKGROUND: Adverse events during surgery can occur in part due to errors in visual perception and judgment. Deep learning is a branch of artificial intelligence (AI) that has shown promise in providing real-time intraoperative guidance. This study aims to train and test the performance of a deep learning model that can identify inappropriate landing zones during endovascular aneurysm repair (EVAR). METHODS: A deep learning model was trained to identify a "No-Go" landing zone during EVAR, defined by coverage of the lowest renal artery by the stent graft. Fluoroscopic images from elective EVAR procedures performed at a single institution and from open-access sources were selected. Annotations of the "No-Go" zone were performed by trained annotators. A 10-fold cross-validation technique was used to evaluate the performance of the model against human annotations. Primary outcomes were intersection-over-union (IoU) and F1 score and secondary outcomes were pixel-wise accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: The AI model was trained using 369 images procured from 110 different patients/videos, including 18 patients/videos (44 images) from open-access sources. For the primary outcomes, IoU and F1 were 0.43 (standard deviation ± 0.29) and 0.53 (±0.32), respectively. For the secondary outcomes, accuracy, sensitivity, specificity, NPV, and PPV were 0.97 (±0.002), 0.51 (±0.34), 0.99 (±0.001). 0.99 (±0.002), and 0.62 (±0.34), respectively. CONCLUSIONS: AI can effectively identify suboptimal areas of stent deployment during EVAR. Further directions include validating the model on datasets from other institutions and assessing its ability to predict optimal stent graft placement and clinical outcomes.

Assessing the robustness of negative vascular surgery randomized controlled trials using their reverse fragility index.

OBJECTIVE: The reverse fragility index (RFI) describes the number of event conversions needed to convert a statistically nonsignificant dichotomous outcome to a significant one. The objective of the present study was to assess the RFI of vascular surgery randomized controlled trials (RCTs) comparing endovascular vs open surgery for the treatment of abdominal aortic aneurysms (AAAs), carotid artery stenosis (CAS), and peripheral artery disease (PAD). METHODS: MEDLINE and Embase were searched for RCTs that had investigated AAAs, CAS, or PAD with statistically nonsignificant binary primary outcomes. The primary outcome for the present study was the median RFI. Calculation of the RFI was performed by creating two-by-two contingency tables and subtracting events from the group with fewer events and adding nonevents to the same group until a two-tailed Fisher exact test had produced a statistically significant result (P ≤ .05). RESULTS: Of 4187 reports, 49 studies reporting 103 different primary end points were included. The overall median RFI was 7 (interquartile range [IQR], 5-13). The specific RFIs for AAA, CAS, and PAD were 10 (IQR, 6-15.5), 6 (IQR, 5-9.5), and 7 (IQR, 5.5-10), respectively. Of the 103 end points, 42 (47%) had had a loss to follow-up greater than the RFI, of which 10 were AAA trials (24%), 23 were CAS trials (55%), and 9 were PAD trials (21%). The Pearson correlation demonstrated a significant positive relationship between a study's RFI and the impact factor of its publishing journal (r = 0.38; 95% confidence interval [CI], 0.20-0.54; P < .01), length of follow-up (r = 0.43; 95% CI, 0.26-0.58; P < .01), and sample size (r = 0.28; 95% CI, 0.09-0.45; P < .01). CONCLUSIONS: A small number of events (median, 7) was required to change the outcome of negative RCTs from statistically nonsignificant to significant, with 47% of the studies having missing data that could have reversed the finding of its primary outcome. Reporting of the RFI relative to the loss to follow-up could be of benefit in future trials and provide confidence regarding the robustness of the P value.

A Systematic Review and Bibliometric Analysis of Applications of Artificial Intelligence and Machine Learning in Vascular Surgery.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) have seen increasingly intimate integration with medicine and healthcare in the last 2 decades. The objective of this study was to summarize all current applications of AI and ML in the vascular surgery literature and to conduct a bibliometric analysis of published studies. METHODS: A comprehensive literature search was conducted through Embase, MEDLINE, and Ovid HealthStar from inception until February 19, 2021. Reporting of this study was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Title and abstract screening, full-text screening, and data extraction were conducted in duplicate. Data extracted included study metadata, the clinical area of study within vascular surgery, type of AI/ML method used, dataset, and the application of AI/ML. Publishing journals were classified as having either a clinical scope or technical scope. The author academic background was classified as clinical, nonclinical (e.g., engineering), or both, depending on author affiliation. RESULTS: The initial search identified 7,434 studies, of which 249 were included for a final analysis. The rate of publications is exponentially increasing, with 158 (63%) studies being published in the last 5 years alone. Studies were most commonly related to carotid artery disease (118, 47%), abdominal aortic aneurysms (51, 20%), and peripheral arterial disease (26, 10%). Study authors employed an average of 1.50 (range: 1-6) distinct AI methods in their studies. The application of AI/ML methods broadly related to predictive models (54, 22%), image segmentation (49, 19.4%), diagnostic methods (46, 18%), or multiple combined applications (91, 37%). The most commonly used AI/ML methods were artificial neural networks (155/378 use cases, 41%), support vector machines (64, 17%), k-nearest neighbors algorithm (26, 7%), and random forests (23, 6%). Datasets to which these AI/ML methods were applied frequently involved ultrasound images (87, 35%), computed tomography (CT) images (42, 17%), clinical data (34, 14%), or multiple datasets (36, 14%). Overall, 22 (9%) studies were published in journals specific to vascular surgery, with the majority (147/249, 59%) being published in journals with a scope related to computer science or engineering. Among 1,576 publishing authors, 46% had exclusively a clinical background, 48% a nonclinical background, and 5% had both a clinical and nonclinical background. CONCLUSIONS: There is an exponentially growing body of literature describing the use of AI and ML in vascular surgery. There is a focus on carotid artery disease and abdominal aortic disease, with many other areas of vascular surgery under-represented. Neural networks and support vector machines composed most AI methods in the literature. As AI/ML continue to see expanded applications in the field, it is important that vascular surgeons appreciate its potential and limitations. In addition, as it sees increasing use, there is a need for clinicians with expertise in AI/ML methods who can optimize its transition into daily practice.

Quality of Reporting on Guideline, Protocol, or Algorithm Implementation in Adult Trauma Centers: A Systematic Review.

OBJECTIVE: To appraise the quality of reporting on guideline, protocol, and algorithm implementations in adult trauma settings according to the Revised Standards for Quality Improvement Reporting Excellence (SQUIRE 2.0). BACKGROUND: At present we do not know if published reports of guideline implementations in trauma settings are of sufficient quality to facilitate replication by other centers wishing to implement the same or similar guidelines. METHODS: A systematic review of the literature was conducted. Articles were identified through electronic databases and hand searching relevant trauma journals. Studies meeting inclusion criteria focused on a guideline, protocol, or algorithm that targeted adult trauma patients ≥18 years and/or trauma patient care providers, and evaluated the effectiveness of guideline, protocol, or algorithm implementation in terms of change in clinical practice or patient outcomes. Each included study was assessed in duplicate for adherence to the 18-item SQUIRE 2.0 criteria. The primary endpoint was the proportion of studies meeting at least 80% (score ≥15) of SQUIRE 2.0. RESULTS: Of 7368 screened studies, 74 met inclusion criteria. Thirty-nine percent of studies scored ≥80% on SQUIRE 2.0. Criteria that were met most frequently were abstract (93%), problem description (93%), and specific aims (89%). The lowest scores appeared in the funding (28%), context (47%), and results (54%) criteria. No study indicated using SQUIRE 2.0 as a guideline to writing the report. CONCLUSIONS: Significant opportunity exists to improve the utility of guideline implementation reports in adult trauma settings, particularly in the domains of study context and the implications of context for study outcomes.

The International Federation for Emergency Medicine report on emergency department crowding and access block: A brief summary.

OBJECTIVE: To develop comprehensive guidance that captures international impacts, causes and solutions related to emergency department (ED) crowding and access block. METHODS: Emergency physicians representing 15 countries from all International Federation of Emergency Medicine (IFEM) regions composed the Task Force. Monthly meetings were held via video-conferencing software to achieve consensus for report content. The report was submitted and approved by the IFEM Board on June 1, 2020. RESULTS: A total of 14 topic dossiers, each relating to an aspect of ED crowding, were researched and completed collaboratively by members of the Task Force. CONCLUSIONS: The IFEM report is a comprehensive document intended to be used in whole or by section to inform and address aspects of ED crowding and access block. Overall, ED crowding is a multifactorial issue requiring systems-wide solutions applied at local, regional, and national levels. Access block is the predominant contributor of ED crowding in most parts of the world.

Factors relating to the publication rate of abstracts presented from 2012 to 2015 at the Society for Vascular Surgery Annual Meeting.

OBJECTIVE: The Society for Vascular Surgery's Annual Meeting acts as a means of disseminating research findings among vascular surgeons through the presentation of research abstracts. Following presentation at the meeting, research is often compiled into a full-text manuscript and submitted to a peer-reviewed journal. However, not all abstracts accepted to the Vascular Annual Meeting (VAM) eventually have a corresponding full-text publication. The objectives of this study were to establish the publication rate of abstracts presented between 2012 and 2015 to the VAM and to identify factors correlating with publication status. METHODS: Abstracts presented at the VAM were available through the Journal of Vascular Surgery. Data extracted from eligible abstracts included level of evidence according to the Oxford Centre for Evidence-Based Medicine 2011 Levels of Evidence scheme, type of study (prognostic, therapeutic/harm, diagnostic), sample size, and status of outcome (positive, negative, or descriptive findings). Publication status of the abstracts was determined through a comprehensive literature review of PubMed (MEDLINE), Ovid (MEDLINE), and Embase. A multivariable logistic regression was conducted to determine factors correlating with publication status. RESULTS: The publication rate during the study period was 43.0% with a median time to publication of 9 months, with 412 of the 958 abstracts having a corresponding full-text publication in 48 journals with weighted mean impact factor of 3.40. Eleven journals collectively published 372 (90.3%) of the articles, with the Journal of Vascular Surgery publishing 280 (68.0%) of the manuscripts. Our logistic regression model demonstrated that factors positively affecting publication status were a positive status of outcome (odds ratio, 2.59; 95% confidence interval, 1.56-4.28) and a logarithmic increase in the sample size of the study (odds ratio, 1.35; 95% confidence interval, 1.13-1.60). In addition, studies with a corresponding full-text publication had a greater median sample size (250) compared with those without one (143; P < .001). CONCLUSIONS: From 2012 to 2015, 43.0% of VAM abstracts had a corresponding full-text publication, with greater sample size and a positive status of outcome positively correlating with likelihood of publication. Studies with negative findings made up a small proportion of conference abstracts (9.6%) and were the least likely to be published. Given the relatively small size of the specialty of vascular surgery, it may be particularly important to be mindful of publication bias. It may be worthwhile to give additional consideration to acceptance of abstracts or publication of studies with negative results that meaningfully contribute to the literature.

Implementing the IMIST-AMBO tool for paramedic to trauma team handovers: a video review analysis.

OBJECTIVE: Patient handover between paramedics and the trauma team is vulnerable to communication errors that may adversely affect patient care. This study assesses the feasibility of a handover tool, IMIST-AMBO (acronym of categories), implementation in the trauma bay and evaluates the degree to which it improves handover metrics. METHODS: This is a prospective observational cohort study conducted at Canada's largest level-one trauma center. Feasibility of the tool implementation and improvement in handover metrics were assessed. Strategies for implementation included distribution of an educational video and posters, and point-of-care reminders in the trauma bay. Two reviewers independently assessed video recordings of handovers to evaluate handover metrics. Findings were compared to data obtained during a knowledge gap analysis conducted prior to the initiation of this study at the same institution. RESULTS: Over 13 weeks (August to November 2020), 140 videos were recorded, of which 80 used the IMIST-AMBO tool (compliance of 57%). Paramedic adherence to the handover structure occurred in 70.4% of cases, with greater adherence to the IMIST (82.2%) compared to the AMBO (47.1%) section. The mean (± standard deviation) handover duration was shorter (1 min:58 s ± 0:44 s during implementation vs. 2 min:47 s ± 1:14 s pre-implementation, [p < 0.001]). Frequency of parallel conversations and informal handovers improved (61% to 30% and 65% to 13%, [p < 0.001], respectively). Interruptions during the handover decreased from 3.05 (± 1.95) to 1.5 (± 1.7), p < 0.001. The tool was received favorably among study participants. CONCLUSION: The IMIST-AMBO tool reduced the frequency of interruptions, parallel conversations, and informal handovers during paramedic-trauma team handovers at our institution. The quality and amount of information communicated per handover improved, all with a decrease in handover duration. The IMIST-AMBO tool may be applied to other trauma centers across Canada, or more broadly on an international scale.

RéSUMé: OBJECTIFS: Le transfert des patients entre les ambulanciers paramédicaux et l'équipe de traumatologie est vulnérable aux erreurs de communication qui peuvent nuire aux soins aux patients. Cette étude évalue la faisabilité d'un outil de transfert, IMIST-AMBO (acronyme des catégories), mis en œuvre dans le service de traumatologie et évalue dans quelle mesure il améliore les paramètres de transfert. MéTHODES: Il s'agit d'une étude de cohorte observationnelle prospective menée dans le plus grand centre de traumatologie de niveau 1 du Canada. La faisabilité de la mise en œuvre de l'outil et l'amélioration des paramètres de transfert ont été évaluées. Les stratégies de mise en œuvre comprenaient la distribution d'une vidéo et d'affiches éducatives, ainsi que des rappels au point de service dans la salle de traumatologie. Deux examinateurs ont évalué indépendamment les enregistrements vidéo des transferts pour évaluer les paramètres de transfert. Les résultats ont été comparés aux données obtenues lors d'une analyse des lacunes en matière de connaissances réalisée avant le lancement de cette étude dans le même établissement. RéSULTATS: Sur 13 semaines (août à novembre 2020), 140 vidéos ont été enregistrées, dont 80 ont utilisé l'outil IMIST-AMBO (conformité de 57%). L'adhésion des ambulanciers paramédicaux à la structure de transfert s'est produite dans 70.4% des cas, avec une plus grande adhésion à l'IMIST (82.2%) que l'AMBO (47,1%). La durée moyenne (± écart-type) du transfert était plus courte (1 min: 58 s ± 0: 44 s pendant la mise en œuvre contre 2 min: 47 s ± 1: 14 s avant la mise en œuvre, p < 0.001). La fréquence des conversations parallèles et des transferts informels s'est améliorée (de 61% à 30% et de 65% à 13%, [p < 0.001], respectivement). Les interruptions pendant le transfert ont diminué de 3.05 (± 1.95) à 1.5 (± 1.7), p < 0.001. L'outil a été accueilli favorablement par les participants à l'étude. CONCLUSION: L'outil IMIST-AMBO a réduit la fréquence des interruptions, des conversations parallèles et des transferts informels pendant les transferts de l'équipe paramédicale de traumatologie dans notre établissement. La qualité et la quantité d'informations communiquées par transfert se sont améliorées, tout en réduisant la durée du transfert. L'outil IMIST-AMBO peut être appliqué à d'autres centres de traumatologie à travers le Canada, ou plus largement à l'échelle internationale.

The International Federation for Emergency Medicine report on emergency department crowding and access block: A brief summary.

OBJECTIVE: To develop comprehensive guidance that captures international impacts, causes, and solutions related to ED crowding and access block. METHODS: Emergency physicians representing 15 countries from all the International Federation for Emergency Medicine (IFEM) regions composed the task force. Monthly meetings were held via video-conferencing software to achieve consensus for report content. The report was submitted and approved by the IFEM Board on June 1, 2020. RESULTS: A total of 14 topic dossiers, each relating to an aspect of ED crowding, were researched and completed collaboratively by members of the task force. CONCLUSIONS: The IFEM report is a comprehensive document intended to be used in whole or by section to inform and address aspects of ED crowding and access block. Overall, ED crowding is a multifactorial issue requiring systems-wide solutions applied at local, regional, and national levels. Access block is the predominant contributor of ED crowding in most parts of the world.

How prepared are Canadian trauma centres for mass casualty incidents?

OBJECTIVES: Mass Casualty Incidents (MCIs) are rare but devastating events that require extensive planning in order to minimize morbidity and mortality. There are two broad categories limiting a hospital's response: physical assets (e.g., critical care beds, operating rooms, food, communication devices) as well as operating procedures (e.g., MCI committees, regional coordination, provider training). The purpose of this study is to provide an examination of MCI preparedness according to these categories in Level 1 Trauma Centre across Canada. METHODS: This study surveyed all Level 1 Trauma Centres across Canada in order to assess the physical assets and operating procedures they had in place in the event of a hypothetical MCI on one of the busiest days of the year for trauma care. RESULTS: Of the 28 Trauma Centres contacted, 13 completed surveys (46%). Most hospitals had sufficient food (9/13) water (9/13), fuel (7/13), and communication assets (8/13) for a hypothetical MCI. A median of 38 mechanical ventilators could be mobilized. No hospitals mandated physician training for MCIs, and 6/13 centres were certain that they had a Strategic Emergency Management Plan (SEMP). Only 6/13 hospitals had dedicated MCI committees, Overall, 4/13 hospitals had explicit plans developed with community hospitals. CONCLUSION: This study demonstrated that physical assets are generally less limiting than operating procedures. Four key areas of potential improvement have been identified: 1) provider training (especially physicians), 2) coordination with small hospitals, 3) mechanical ventilator availability, and 4) MCI committees with explicit Strategic Emergency Management Plans.

The International Federation for Emergency Medicine report on emergency department crowding and access block: A brief summary.

OBJECTIVE: To develop comprehensive guidance that captures international impacts, causes, and solutions related to emergency department crowding and access block. METHODS: Emergency physicians representing 15 countries from all IFEM regions composed the Task Force. Monthly meetings were held via video-conferencing software to achieve consensus for report content. The report was submitted and approved by the IFEM Board on June 1, 2020. RESULTS: A total of 14 topic dossiers, each relating to an aspect of ED crowding, were researched and completed collaboratively by members of the Task Force. CONCLUSIONS: The IFEM report is a comprehensive document intended to be used in whole or by section to inform and address aspects of ED crowding and access block. Overall, ED crowding is a multifactorial issue requiring systems-wide solutions applied at local, regional, and national levels. Access block is the predominant contributor of ED crowding in most parts of the world.

RéSUMé: OBJECTIFS: Développer des directives détaillées qui saisissent les impacts internationaux, les causes et les solutions liés au surpeuplement et blocages d'accès des urgences. MéTHODES: Des médecins d'urgence représentant 15 pays de toutes les régions de la Fédération Internationale de Médecine d'Urgence (IFEM) ont composé le groupe de travail. Des réunions mensuelles ont été organisées par le biais d'un logiciel de visioconférence afin de parvenir à un consensus sur le contenu du rapport. Le rapport a été soumis et approuvé par le Conseil d'administration de l'IFEM le 1er juin 2020. RéSULTATS : Au total, 14 dossiers thématiques, chacun se rapportant à un aspect de l'engorgement des urgences, ont été documentés et complétés conjointement par les membres du groupe de travail. CONCLUSIONS: Le rapport IFEM est un document détaillé destiné à être utilisé dans son intégralité ou par section pour renseigner et aborder les aspects du surpeuplement et du blocage d'accès des urgences. Dans l'ensemble, l'encombrement dans les services d'urgence est un problème multifactoriel qui nécessite des solutions à l'échelle systémique appliquées aux niveaux local, régional et national. Le blocage d'accès est le principal contributeur à l'engorgement des urgences dans la plupart des régions du monde.

Assessing effective mask use by the public in two countries: an observational study.

OBJECTIVES: During the COVID-19 pandemic wearing a mask in public has been recommended in some settings and mandated in others. How often this advice is followed, how well, and whether it inadvertently leads to more disease transmission opportunities due to a combination of improper use and physical distancing lapses is unknown. DESIGN: Cross-sectional observational study performed in June-August 2020. SETTING: Eleven outdoor and indoor public settings (some with mandated mask use, some without) each in Toronto, Ontario, and in Portland, Oregon. PARTICIPANTS: All passers-by in the study settings. OUTCOME MEASURES: Mask use, incorrect mask use, and number of breaches (ie, coming within 2 m of someone else where both parties were not properly masked). RESULTS: We observed 36 808 persons, the majority of whom were estimated to be aged 31-65 years (49%). Two-thirds (66.7%) were wearing a mask and 13.6% of mask-wearers wore them incorrectly. Mandatory mask-use settings were overwhelmingly associated with mask use (adjusted OR 79.2; 95% CI 47.4 to 135.1). Younger age, male sex, Torontonians, and public transit or airport settings (vs in a store) were associated with lower adjusted odds of wearing a mask. Mandatory mask-use settings were associated with lower adjusted odds of mask error (OR 0.30; 95% CI 0.14 to 0.73), along with female sex and Portland subjects. Subjects aged 81+ years (vs 31-65 years) and those on public transit and at the airport (vs stores) had higher odds of mask errors. Mask-wearers had a large reduction in adjusted mean number of breaches (rate ratio (RR) 0.19; 95% CI 0.17 to 0.20). The 81+ age group had the largest association with breaches (RR 7.77; 95% CI 5.32 to 11.34). CONCLUSIONS: Mandatory mask use was associated with a large increase in mask-wearing. Despite 14% of them wearing their masks incorrectly, mask users had a large reduction in the mean number of breaches (disease transmission opportunities). The elderly and transit users may warrant public health interventions aimed at improving mask use.

Clinical handover from emergency medical services to the trauma team: A gap analysis.

OBJECTIVES: There has been limited evaluation of handover from emergency medical services (EMS) to the trauma team. We sought to characterize these handover practices to identify areas of improvement and determine if handover standardization might be beneficial for trauma team performance. METHODS: Data were prospectively collected over a nine-week period by a trained observer at a Canadian level one trauma centre. A randomized scheduled was used to capture a representative breadth of handovers. Data collected included outcome measures such as duration of handover, structure of the handover, and information shared, process measures such as questions and interruptions from the trauma team, and perceptions of the handover from nurses, trauma team leaders and EMS according to a bidirectional Likert scale. RESULTS: 79 formal verbal handovers were observed. Information was often missing regarding airway (present 22%), breathing (54%), medications (59%), and allergies (54%). Handover structure lacked consistency beyond the order of identification and mechanism of injury. Of all questions asked, 35% were questioning previously given information. The majority of handovers (61%) involved parallel conversations between team members while EMS was speaking. There was a statistically significant disparity between the self-evaluation of EMS handovers and the perceived quality determined by nurses and trauma team leaders. CONCLUSIONS: We have identified the need to standardize handover due to poor information content, a lack of structure and active listening, information repetition, and discordant expectations between team members. These data will guide the development of a co-constructed framework integrating the perspectives of all team members.

Early lessons from COVID-19 that may reduce future emergency department crowding.

The COVID-19 pandemic has produced significant changes in emergency medicine patient volumes, clinical practice, and has accelerated a number of systems-level developments. Many of these changes produced efficiencies in emergency care systems and contributed to a reduction in crowding and access block. In this paper, we explore these changes, analyse their risks and benefits and examine their sustainability for the future to the extent that they may combat crowding. We also examine the necessity of a system-wide approach in addressing ED crowding and access block.