Notification Time Research Articles

Measles cluster in Northern Portugal: enhancing surveillance strengths

Abstract Although measles was declared eliminated in Portugal in 2015, outbreaks persist, despite high vaccination coverage. The last outbreak in the northern region was in 2017. Portugal has a Surveillance System implemented for mandatory communicable diseases (SINAVE) integrating clinical, epidemiological and laboratory data. In 2021, WHO expressed concern about the low sensitivity of measles surveillance and urged Portugal to strengthen its surveillance practices. Our study aims to describe a measles cluster in northern Portugal during the first trimester of 2024. Data from measles cases from the first trimester of 2024 were collected from SINAVE. Contact tracing and Public Health (PH) intervention data was sent by Local Public Health Authorities through a survey designed for that purpose. A total of 70 suspected cases were reported and investigated: 6 cases were laboratory confirmed and 64 were discarded. The confirmed cases had a mean age of 28 years (all adults), with 50% female. The mean notification time was 0,3 days. The index case was imported (Mauritania) and unvaccinated, leading to 2 secondary cases. Five cases had 2 doses of a measles vaccine, with 1 case being a health professional. Additionally, 1 case was imported from France. For 2 cases the source of infection could not be unequivocally identified and no travel history during incubation period. A total of 851 contacts of confirmed cases were identified. Although sustainable transmission is not evident in our region, measles is being introduced through migration and tourism. Despite clinical awareness, strengthening early case detection is essential to enforce effective control measures. PH teams have been working tirelessly to trace clusters origins, gathering large number of contacts and adapting strategies for sustained control. In a globalized world, ensuring surveillance sensitivity is paramount. Integrating other data sources in surveillance routine is crucial for upholding Measles-Free Status compliance. Key messages • Measles must take centre stage on our agenda. • Reinforcing surveillance, integrating additional data sources, is crucial for heightened sensitivity and prompt response.

Classification and Communication of Critical Findings in Emergency Radiology: A Scoping Review

PurposeTo identify the published standards for the classification and communication of critical actionable findings in emergency radiology and the associated facilitators and barriers to communication and message management or dissemination of such findings. Materials and methodsSearch terms for resources pertaining to critical findings (CFs) in emergency radiology were applied to two databases (PubMed, Embase). Screening of hits using the following pre-established inclusion and exclusion criteria were performed by three analysts with subsequent consensus discussion for discrepancies: (1) the resources include any standards for the classification and communication of imaging findings as critical, or (2) the resource discusses any facilitators to the communication of CFs, or (3) the resource discusses any barriers to the communication of CFs. Resources with explicit focus on a pediatric population or predominant focus on artificial intelligence or natural language processing were omitted. Accompanying gray literature search was used to expand included resources. Data extraction included year, country, resource type, scope or purpose, participants, context, standards to identifying or communicating CFs, facilitators and barriers, method type, recommendations, applicability, and disclosures. ResultsSeventy-six resources were included in the final analysis, including 16 societal or commission guidelines. Among the guidelines, no standardized list of CFs was identified, with typical recommendations suggesting application of a local policy. Communication standards included direct closed-loop communication for high acuity findings, with more flexible communication channels for less acute findings. Applied interventions for CFs management most frequently fell into four categories: electronic (n = 10), hybrid (ie, electronic or administrative) (n = 3), feedback or education (n = 5), and administrative (n = 4). ConclusionThere are published standards, policies and interventions for the management of CFs in emergency radiology. Three-tier stratification (eg, critical, urgent, incidental) based on time sensitivity and severity is most common with most CFs necessitating closed-loop communication. Awareness of systemic facilitators and barriers should inform local policy development. Electronic and administrative communication pathways are useful adjuncts. Further research should offer comparative analyses of different CF interventions with regards to cost-effectiveness, notification time, and user feedback.

Malaria reporting timeliness analysis and factors associated with delayed notification, 2018-2022, Nepal.

In order to monitor public health trends and identify disease outbreaks early, efficient and reliable notification and surveillance systems are essential. Nepal uses a 1-3-7 malaria surveillance approach. The Short Message System (SMS) -based system for timely notification has been established. However, knowledge gaps exist regarding the timeliness of notification, treatment initiation, and case-based investigations. Hence, this study identifies the timeliness of notification and factors associated with delayed notification. This study used a cross-sectional approach and used secondary malaria surveillance data from Nepal's national malaria elimination program for the period of 2018 to 2022. The study revealed that the majority (79.9%) of malaria cases were male, with a male-to-female ratio of 3.96:1. Occupation was found to be significantly associated with delayed notification. Repatriate workers had 0.60 times lower odds of experiencing delayed notification compared to the reference occupation. Similarly, individuals diagnosed in the Sudurpaschim and Lumbini provinces had significantly lower odds (0.48 and 0.38, respectively) of encountering delayed notification compared to the reference province. Furthermore, relying on a single laboratory tool for malaria diagnosis (either RDT or microscopy only) was significantly associated with delayed notification. Individuals diagnosed solely with RDT or microscopy had 2.04 and 1.79 times higher odds of experiencing delayed notification, respectively, compared to those diagnosed using both laboratory tools. This study provides insight into the timeliness of surveillance system approach by assessing delayed notification and the factors associated with it. No delays are identified in median notification, treatment time and in case investigation. Improvement in the timeliness of malaria reporting over the years was observed. Provinces with high burden of malaria and repatriate workers showed lower delayed notification and conversely, cases diagnosed with single laboratory tool showed delayed notification time.

Towards malaria elimination: a reflection about digital notification modules to improve malaria cases notification speed and follow-up in the Brazilian Amazon region

BackgroundHealth information systems (HIS) are a pivotal element in epidemiological surveillance. In Brazil, malaria persists as a public health challenge, with 99% of its occurrences concentrated in the Amazon region, where cases are reported through the HIS Sivep-Malaria. Recent technological advancements indicate that case notifications can be expedited through more efficient systems with broader coverage. The objective of this study is to analyse opportunities for notification within Sivep-Malaria and explore the implementation of mobile electronic devices and applications to enhance the performance of malaria case notifications and use.MethodsThis descriptive study analyses data on malaria-positive cases in the Brazilian Amazon from 2004 to 2022. Malaria Epidemiological Surveillance System (Sivep-Malaria) data were used. The Brazilian Amazon region area is approximately 5 million km2 across nine different states in Brazil. Data entry opportunities were assessed by considering the time difference between the 'date of data entry' and the 'date of notification.' Descriptive statistics, including analyses of means and medians, were conducted across the entire Amazon region, and for indigenous population villages and gold mining areas.ResultsBetween 2004 and 2022, 6,176,878 new malaria cases were recorded in Brazil. The average data entry opportunity throughout the period was 17.9 days, with a median of 8 days. The most frequently occurring value was 1 day, and 99% of all notifications were entered within 138 days, with 75.0% entered within 20 days after notification. The states with the poorest data entry opportunities were Roraima and Tocantins, with averages of 31.3 and 31.0 days, respectively. For indigenous population villages and gold mining areas, the median data entry opportunities were 23 and 15 days, respectively.ConclusionsIn malaria elimination, where surveillance is a primary strategy for evaluating each reported case, reducing notification time, enhancing data quality and being able to follow-up cases through computerized reports offer significant benefits for cases investigation. Technological improvements in Sivep-Malaria could yield substantial benefits for malaria control in Brazil, aiding the country in achieving disease elimination and fulfilling the Sustainable Development Goals.

The impact of artificial intelligence on large vessel occlusion stroke detection and management: A systematic review meta-analysis

IntroductionStroke remains the second leading cause of death worldwide, with many survivors facing significant disabilities. In acute stroke care, the timeless adage 'Time is brain' underscores the vital need for quick action. Innovative Artificial Intelligence (AI) technology potentially enables swift detection and management of acute ischemic strokes, revolutionizing acute stroke care towards enhanced automation. MethodsThe study is registered with Prospero under CRD42024496716 and adheres to the Problem, Intervention, Comparison, and Outcomes framework (PICO). The analysis used Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We searched Embase, PubMed, DBLP, Google Scholar, IEEE Xplore, Cochrane database, IEEE, Web of Science, ArXiv, MedRxiv, and Semantic Scholar. The articles included were published between 2019 and 2023. Out of 1528 articles identified, thirty-seven met the inclusion criteria. ResultsWe compared AI-augmented Large Vessel Occlusion (LVO) detection and non-AI LVO detection in various patient processing times related to emergent endovascular therapy in acute ischemic strokes. Triage Time, Door-to-Intervention Notification Time (INR), and Door-to -Arterial Puncture Time revealed an odds ratio (OR) of 0.39 (95 % CI: 0.29–0.54, p < 0.001), 0.30 (95 % CI: 0.21–0.42, p < 0.001), and 0.50 (95 % CI: 0detection 0.30–0.82, p = 0.007), respectively -- all of which had negligible heterogeneity (I^2 = 0). CT-to-Puncture-Time and Door-to-CTA-Time yielded an OR of 0.57 (95 % CI: 0.31–1.04, p = 0.065) and 0.77 (95 % CI: 0.37–1.60, p = 0.489), respectively -- both of which had negligible heterogeneity (I^2 = 0). The Last Known Well (LWK) to Time of Arrival resulted in an OR of 1.15 (95 % CI: 0.83–1.59, p = 0.409, I^2 = 0). AI stroke detection sensitivity OR of 0.91 (95 % CI: 0.88–0.95, p < 0.001) should be interpreted with potential heterogeneity in mind (I^2 = 69.3). National Institute of Health score (NIHSS) mean of 16.20 (95 % CI: 14.96–17.45, p = 0.001, I^2 = 0). Patient Transfer-Times between primary and comprehensive stroke centers generated an OR of 0.98 (95 % CI: 0.73–1.32, p = 893, I^2 = 0). Similarly, Door-in-Door-Out Time (DIDO) had an OR of 1.19 (95 % CI: 0.21–6.88, p = 0.848) and low heterogeneity (I^2 = 5.1). The results indicated significant differences across several parameters between the AI augmentation and non-AI groups. ConclusionOur findings highlight how AI augments healthcare providers' ability to detect and manage strokes swiftly and accurately within acute care settings. As these technologies progress, healthcare organizations mature, and AI becomes more integrated into healthcare systems, longitudinal studies are critical in evaluating its impact on workflow efficiency, cost-effectiveness, and clinical outcomes.

Testing the Feasibility of Selected, Commercially Available Wearable Devices in Detecting Agricultural-Related Incidents

HighlightsThe purpose of this research was to validate a test procedure for using commercially available smart technologies in detecting an agricultural-related incident.A convenient selection of commercially available wearable devices was used to measure the inertial qualities of simulated incidents.Simulated ejections, falls, and upsets were performed to recreate leading causes of agricultural injuries and fatalities using an anthropomorphic test device.Only 2 of 27 simulated incidents triggered detection on the selected wearable devices tested.The results of this study were inconclusive in determining the feasibility of commercially available wearable devices in detecting agricultural-related incidents. More research is needed to develop an improved testing procedure.Additional collaboration is needed with manufacturers of wearable incident detection devices to clearly identify potential applications and limitations of their devices.Abstract. A study was conducted to test a selection of commercially available wearable devices to determine their feasibility for triggering incident detection during a variety of simulated agricultural incidents with high risk of causing injury. The goal was to ultimately increase survivability outcomes for victims by enhancing notification and reducing response time from emergency services. A 50th percentile adult male anthropomorphic test device (ATD). was fitted with a convenient selection of commercially available wearable smart technologies to measure the responsiveness of the technology’s incident detection software. Devices used for this testing were: (1) Garmin Vivoactive 4 smartwatch; (2) Apple Watch Series 7 (Bluetooth only and cellular models); and (3) Movesense Active tracking device. A Samsung Galaxy S22 smartphone and an Apple iPhone 12 smartphone were used to connect the wearable devices and measured impact through their internal inertial measurement unit (IMU) sensors. Simulated ejections from equipment, vertical falls, and vehicle overturns were performed with the ATD. Side upsets were simulated with the ATD positioned in the operator station of a 52-drawbar horsepower (dbp), two-wheel drive, standard front axle, diesel tractor, weighing 6500 pounds. The tractor was equipped with an approved ROPS. Side upsets were also simulated using a 22-horsepower zero-turn mower, with the ATD positioned in the operator seat. Falls were simulated from heights of up to 4.57 meters. After each simulated incident, devices were examined to determine whether or not incident detection was successfully triggered. Data was then collected from an internal sensor logging application installed on the selected devices. It was found that the incident detection feature on the identified wearable devices only triggered in specific scenarios. Only 2 of the 27 simulated incidents successfully triggered incident detection on one device. Only the Garmin Vivoactive 4 smartwatch triggered incident detection. No device was triggered during the ATD impact in simulated tractor upset testing or in simulated zero-turn mower upset testing. It was concluded that these devices, in their current form, are not reliable for use in detecting serious agricultural-related injuries, especially considering the lack of adequate cell phone coverage in the areas in which these incidents are most likely to occur. Keywords: Agricultural incident simulation, ATD, G-force, Incident detection, Sensor fusion, Smart watch.

AgroGuardian: An All-Terrain Vehicle Crash Detection and Notification System

Highlights Off-road ATV incidents can be problematic due to long EMS alert times. An ATV crash-detection-and-report system is expected to reduce EMS response time. The developed system can accurately detect ATV rollovers. The alert time of our system is 10 times faster than the national U.S. average. Any rider using our system is 3 times more likely to survive an off-road crash. Abstract. All-Terrain Vehicle (ATV) incidents are a common cause of injury and death in the agricultural industry in the United States. Many ATV off-road crashes on farms and ranches may result in trauma requiring immediate care, but the injured rider is unable to seek help due to their injuries. Moreover, many of these crashes occur in isolated areas that may be difficult to access and have unreliable cellular phone service, making contact with emergency medical services (EMS) challenging. This study aimed at developing and testing a low-cost ATV crash detection device (AgroGuardian) that immediately alerts EMS and emergency contacts, even when the rider is unable to take action and/or there is no cellular phone service available. AgroGuardian includes an embedded data logging system, a smartphone application, and a remote database. The embedded system includes an Inertial Measurement Unit (IMU) for attitude estimation, a Global Positioning System (GPS) for location estimation, and a Rock7 modem for off-board communication. A smartphone application was developed for the users to input information about their vehicle (e.g., make and model) and emergency contacts. Also, it allows them to interact with their ATV data. An emergency signal along with the ATV’s coordinates is transmitted through the Rock7 modem and received in the remote database when a rollover is detected by the system. This emergency signal is then processed and sent to EMS and emergency contacts. Our results indicated that the device: (1) is unlikely to miss an ATV rollover; (2) has a fast EMS notification time (40.7 s); and (3) the ATV localization system presented an average error of 2.34 m. Keywords: ATV, EMS alert time, Farm, Off-road incidents, Quadbike, Rollover.

Motorcycle Detection and Collision Warning Using Monocular Images from a Vehicle

Motorcycle detection and collision warning are essential features in advanced driver assistance systems (ADAS) to ensure road safety, especially in emergency situations. However, detecting motorcycles from videos captured from a car is challenging due to the varying shapes and appearances of motorcycles. In this paper, we propose an integrated and innovative remote sensing and artificial intelligence (AI) methodology for motorcycle detection and distance estimation based on visual data from a single camera installed in the back of a vehicle. Firstly, MD-TinyYOLOv4 is used for detecting motorcycles, refining the neural network through SPP (spatial pyramid pooling) feature extraction, Mish activation function, data augmentation techniques, and optimized anchor boxes for training. The proposed algorithm outperforms eight existing YOLO versions, achieving a precision of 81% at a speed of 240 fps. Secondly, a refined disparity map of each motorcycle’s bounding box is estimated by training a Monodepth2 with a bilateral filter for distance estimation. The proposed fusion model (motorcycle’s detection and distance from vehicle) is evaluated with depth stereo camera measurements, and the results show that 89% of warning scenes are correctly detected, with an alarm notification time of 0.022 s for each image. Outcomes indicate that the proposed integrated methodology provides an effective solution for ADAS, with promising results for real-world applications, and can be suitable for running on mobility services or embedded computing boards instead of the super expensive and powerful systems used in some high-tech unmanned vehicles.

Enhancing bicyclist survival time in fatal crashes: Investigating the impact of faster crash notification time through explainable machine learning

Bicyclists are recognized as vulnerable road users, with the escalating fatalities posing a safety concern. While fatal crashes involving bicyclists are often assumed to be similar, there is a crucial distinction between instant death and death occurring several days later, with the former being substantially more severe. This study delves into the analysis of bicyclists’ time-to-death, spanning from immediate fatalities to deaths within 30 days, using data from the Fatality Analysis Reporting System from 2015 to 2019. Employing the Haddon Matrix approach, the variables are categorized into pre-crash, during-crash, and postcrash phases. This study considers crash notification time as the key postcrash measure. An explainable XGBoost model is developed using the SHAP technique to investigate the associations between variables and bicyclist time-to-death. The results show that substantial delays in crash notification time considerably reduce bicyclists’ time-to-death and increase the likelihood of early death. Specifically, hit-and-run crashes, crashes in rural areas, and crashes during late-night hours exhibit notably longer crash notification times compared to non-hit-and-run crashes, urban areas, and other hours, respectively. In such cases, when no witnesses or survivors can notify emergency responders, on-road vehicle technologies like the advanced automatic collision notification system can promptly inform responders, reducing notification delays.

SAT107 Assessing Continuous Glucose Monitor Alarm Use By Families Of Children With Diabetes

Abstract Disclosure: V.S. Ochs: None. S.E. Woerner: Employee; Self; Lilly USA, LLC. A. Ustyol: None. L.A. DiMeglio: Advisory Board Member; Self; Merck, Abata. Consulting Fee; Self; Vertex. Background: Continuous glucose monitors (CGM) offer customizable alarms which alert persons with diabetes and their caregivers of current or pending glycemic changes. However, there has been little work studying real-world CGM alert setting use in large clinical populations. We sought to understand CGM alarm use through report analyses. Methods: After IRB approval we analyzed data from two-week CGM reports obtained clinically to determine common settings and compared those to target guidelines. Results: CGM download data from 150 children using a Dexcom® G6 were analyzed (median age 14y, (range: 1-19), 89% white, 9.5% black, and 1.5% Asian, 47% female, 51% pump users). Median A1c was 7.8% (range: 5.4-15). Median CGM glucose was 190 (range: 56-374). Average time in range was 47.7% (range: 3.4-99.1).A Low Alarm alert was set for 131 participants (87%) with a median sensor glucose alert threshold of 74 mg/dL (range: 60-100). The High Alarm was used by 109 children (73%) with a median threshold of 272 mg/dL (range: 120-400). The Signal Loss alarm was used by 103 (69%) participants with a median time until notification of 20 min (range: 20-240). Low Repeat and High Repeat alarms were used by only 50 (33%) and 36 (24%) of children, respectively. Rise Rate and Fall Rate alarms were used by 18 (12%) and 34 (23%). There was a significant difference between the median High alarm cutoff of 272 mg/dL and a recommended standard (e.g. PantherProgram.org) of 250 mg/dL (p=0.0016). The same was true with the median Low alarm cutoff of 74 mg/dL and a recommended 70 mg/dL (p&amp;lt;0.0001). There was significant difference between the median High Repeat notification time of 1 hour and the recommended 2 hours (p&amp;lt;0.0001). Pump users were 2.2x more likely to use High Repeat alarms compared to injection users (95% CI: 1.18-4.15, p&amp;lt;0.01). The same was true with the Low Repeat alarm being 1.8x more likely to be used by pumpers compared to injection users (95% CI: 1.12-2.99, p=0.01). There were no significant differences in Low, High, Rise Rate, Fall Rate, Urgent Low Soon, Urgent Low Soon Repeat, or Signal Loss alarms.When the group was divided based on age, above 12 and &amp;lt;=12, younger CGM users were 1.2 times more likely to use the Low alarm compared to older users (95% CI: 1.03-1.30). Also, younger CGM users were more likely to use the Rise Rate (RR=3.6, 95% CI:1.37-9.67), Low Repeat (RR=1.7, 95% CI:1.09-2.71), Signal Loss (RR=1.3, 95% CI:1.04-1.60), Urgent Low Soon (RR=1.2, 95% CI:1.07-1.41), and Urgent Low Soon Repeat (RR=1.2, 95% CI:1.05-1.38) alarms. There were no significant differences in High, High Repeat, or Fall Rate alarm settings. Conclusions: The wide variability of alarm settings used by patients indicates likely educational gaps in CGM onboarding and use. Ensuring CGM alarm best practices will help children with diabetes and their caregivers get needed real-time glycemic data while minimizing alarm fatigue. Presentation: Saturday, June 17, 2023

An Assistive Model for the Visually Impaired Integrating the Domains of IoT, Blockchain and Deep Learning

Internet of Things, blockchain and deep learning are emerging technologies that have recently gained popularity due to their various benefits and applications. All three domains have had success independently in various applications such as automation, agriculture, travel, finance, image recognition, speech recognition, and many others. This paper proposes an efficient, lightweight, and user-friendly solution to help visually impaired individuals navigate their way by taking advantage of modern technologies. The proposed method involves the usage of a camera lens attached to a Raspberry Pi device to capture live video frames of the user’s environment, which are then transmitted to cloud storage. The link to access these images is stored within a symmetrical private blockchain network (no superior access), where all deep learning servers act as nodes. The deep learning model deployed on these servers analyses the video frames to detect objects and feeds the output back to the cloud service. Ultimately, the user receives audio notifications about obstacles through an earphone plugged into the Raspberry Pi. In particular, when running the model on a high-performing network and an RTX 3090 GPU, the average obstacle notification time is reported within 2 s, highlighting the proposed system’s responsiveness and effectiveness in aiding visually impaired individuals.

Optimizing Forecasted Activity Notifications with Reinforcement Learning

In this paper, we propose the notification optimization method by providing multiple alternative times as a reminder for a forecasted activity with and without probabilistic considerations for the activity that needs to be completed and needs notification. It is important to consider various factors when sending notifications to people after obtaining the results of the forecasted activity. We should not send notifications only when we have forecasted results because future daily activities are unpredictable. Therefore, it is important to strike a balance between providing useful reminders and avoiding excessive interruptions, especially for low probabilities of forecasted activity. Our study investigates the impact of the low probability of forecasted activity and optimizes the notification time with reinforcement learning. We also show the gaps between forecasted activities that are useful for self-improvement by people for the balance of important tasks, such as tasks completed as planned and additional tasks to be completed. For evaluation, we utilize two datasets: the existing dataset and data we collected in the field with the technology we have developed. In the data collection, we have 23 activities from six participants. To evaluate the effectiveness of these approaches, we assess the percentage of positive responses, user response rate, and response duration as performance criteria. Our proposed method provides a more effective way to optimize notifications. By incorporating the probability level of activity that needs to be done and needs notification into the state, we achieve a better response rate than the baseline, with the advantage of reaching 27.15%, as well as than the other criteria, which are also improved by using probability.

Ventricular Arrhythmia Alerts in Remotely Monitored Implantable Cardioverter Defibrillator Patients: Impact of Manufacturer Differences in Notification Times on Alert Frequency and Patient Management

The early notification of alert events via remote monitoring (RM) is associated with improved patient outcomes and is the standard of care for device patients. This retrospective review aimed to investigate manufacturer differences in the timing, type and frequency of alert notifications, and their impact on patient management and clinic workload. The frequency of alerts for shocks, anti-tachycardia pacing, and non-sustained ventricular tachycardia was retrospectively reviewed in 557 RM implantable cardioverter defibrillator patients followed between January and December 2021. Manufacturer, alert notification time, and action taken by the clinic were analysed. Descriptive statistical analyses were performed using Pearson’s Chi-squared test. Of 2,666 transmissions, 1,263 (47.4%) were alert transmissions, with 540 (42.8%) alerts for ventricular arrhythmia (VA). Alert frequency for VA was significantly different between device manufacturers: Abbott 40.6%, Biotronik 47.0%, Boston 9.8%, and Medtronic 2.6% (p<0.001). Overall, VA notification times varied by manufacturer: 3.04 days (Abbott), 2.18 days (Biotronik), 28.27 days (Boston Scientific), and 46.72 days (Medtronic) (p<0.001). Shock notification timing did not significantly vary between manufacturers. Referral for clinician review occurred in 14.3% of VA alert transmissions. No action was required for 78.3% of VA alerts. Unplanned RM alert transmissions comprise a significant proportion of device clinic workload, with most VA alerts requiring no action. There is variation in alert frequency and notification time based on manufacturer, which highlights challenges for clinics in managing this unplanned workload.

Determinants of door-in-door-out time in patients with ischaemic stroke transferred for endovascular thrombectomy.

Long door-in-door-out (DIDO) times are an important cause of treatment delay in patients transferred for endovascular thrombectomy (EVT) from primary stroke centres (PSC) to an intervention centre. Insight in causes of prolonged DIDO times may facilitate process improvement interventions. We aimed to quantify different components of DIDO time and to identify determinants of DIDO time. We performed a retrospective cohort study in a Dutch ambulance region consisting of six PSCs and one intervention centre. We included consecutive adult patients with anterior circulation large vessel occlusion, transferred from a PSC for EVT between October 1, 2019 and November 31, 2020. We subdivided DIDO into several time components and quantified contribution of these components to DIDO time. We used univariable and multivariable linear regression models to explore associations between potential determinants and DIDO time. We included 133 patients. Median (IQR) DIDO time was 66 (52-83) min. The longest component was CTA-to-ambulance notification time with a median (IQR) of 24 (16-37) min. DIDO time increased with age (6 min per 10 years, 95% CI: 2-9), onset-to-door time outside 6 h (20 min, 95% CI: 5-35), M2-segment occlusion (15 min, 95% CI: 4-26) and right-sided ischaemia (12 min, 95% CI: 2-21). The CTA-to-ambulance notification time is the largest contributor to DIDO time. Higher age, onset-to-door time longer than 6 h, M2-segment occlusion and right-sided occlusions are independently associated with a longer DIDO time. Future interventions that aim to decrease DIDO time should take these findings into account.

Children's and Caregivers' Review of a Guided Imagery Therapy Mobile App Designed to Treat Children With Functional Abdominal Pain Disorders: Leveraging a Mixed Methods Approach With User-Centered Design.

Functional abdominal pain disorders (FAPDs) are highly prevalent and associated with substantial morbidity. Guided imagery therapy (GIT) is efficacious; however, barriers often impede patient access. Therefore, we developed a GIT mobile app as a novel delivery platform. Guided by user-centered design, this study captured the critiques of our GIT app from children with FAPDs and their caregivers. Children aged 7 to 12 years with Rome IV-defined FAPDs and their caregivers were enrolled. The participants completed a software evaluation, which assessed how well they executed specific app tasks: opening the app, logging in, initiating a session, setting the reminder notification time, and exiting the app. Difficulties in completing these tasks were tallied. After this evaluation, the participants independently completed a System Usability Scale survey. Finally, the children and caregivers were separately interviewed to capture their thoughts about the app. Using a hybrid thematic analysis approach, 2 independent coders coded the interview transcripts using a shared codebook. Data integration occurred after the qualitative and quantitative data were analyzed, and the collective results were summarized. We enrolled 16 child-caregiver dyads. The average age of the children was 9.0 (SD 1.6) years, and 69% (11/16) were female. The System Usability Scale average scores were above average at 78.2 (SD 12.6) and 78.0 (SD 13.5) for the children and caregivers, respectively. The software evaluation revealed favorable usability for most tasks, but 75% (12/16) of children and 69% (11/16) of caregivers had difficulty setting the reminder notification. The children's interviews confirmed the app's usability as favorable but noted difficulty in locating the reminder notification. The children recommended adding exciting scenery and animations to the session screen. Their preferred topics were animals, beaches, swimming, and forests. They also recommended adding soft sounds related to the session topic. Finally, they suggested that adding app gamification enhancements using tangible and intangible rewards for listening to the sessions would promote regular use. The caregivers also assessed the app's usability as favorable but verified the difficulty in locating the reminder notification. They preferred a beach setting, and theme-related music and nature sounds were recommended to augment the session narration. App interface suggestions included increasing the font and image sizes. They also thought that the app's ability to relieve gastrointestinal symptoms and gamification enhancements using tangible and intangible incentives would positively influence the children's motivation to use the app regularly. Data integration revealed that the GIT app had above-average usability. Usability challenges included locating the reminder notification feature and esthetics affecting navigation. Children and caregivers rated our GIT app's usability favorably, offered suggestions to improve its appearance and session content, and recommended rewards to promote its regular use. Their feedback will inform future app refinements.

Abstract WP81: Validation Of Artificial Intelligence To Limit Delays In Acute Stroke Treatment And Endovascular Therapy (VALIDATE)

Introduction: Analyses from early- and late-window thrombectomy trials for acute large vessel occlusion (LVO) stroke have consistently demonstrated a strong time-dependent treatment effect for best outcomes. The utilization of an artificial intelligence (AI)-based care coordination platform to support LVO diagnosis and treatment has the potential to assist in reducing door to puncture times and improve outcomes. Hypothesis: Utilization of an AI-based care platform in the management of LVO patients may significantly decrease door to Neurointerventionalist (NIR) notification time. Methods: Acute stroke consultations seen by TeleSpecialists, LLC physicians in the emergency department in 166 facilities (17 states) that utilized VIZ.AI software or did not have an AI software from December 1, 2021 through March 31, 2022 were extracted from the Telecare TM database. Facilities that neurology does not initiate contact with NIR were excluded. The encounters were analyzed by age, ethnicity, last known normal, arrival time, initial telemedicine stroke code activation time (TCA), candidacy for thrombolytics, door to needle time (DTN), advanced imaging, presence of LVO, time NIR accepted, premorbid modified Rankin Score, and NIHSS score. Patients were divided into two groups (utilization and non-utilization of the AI platform) and median door to NIR notification times were compared. There was a 4 minute shorter time to TCA at AI hospitals. Results: A total of 14,116 patients (8,557 AI and 5,559 non-AI) were included. The median door to NIR notification time for AI was 50 minutes (40, 82) and non-AI was 89.5 minutes (59.3, 122), p &lt;0.001. There was a small but significantly shorter time (3 minutes) from door to TCA at AI hospitals. Median DTN times for thrombolytics was also lower with AI, 40 minutes (30, 52) vs 44 minutes (32, 57.5) for non-AI, p=0.018. The AI group had more advanced imaging performed, a higher percentage of LVOs identified, and a higher percentage accepted by NIR. Conclusion: Hospital utilization of an AI-based care coordination platform was associated with a significant decrease of 39.5 minutes in the time to NIR contact, increase in patients taken for intervention, and lower DTN times for thrombolytics.

S324 Positive Fecal Immunochemical Testing (+FIT) in the COVID-19 Pandemic: Resilient Systems in Troubled Times

Introduction: Colorectal cancer screening via colonoscopy decreased significantly due to the COVID-19 pandemic, with mail-out fecal immunochemical testing (FIT) initiated to maintain screening. Due to concerns surrounding +FIT follow-up we added FIT navigation (FITNav) via a nurse practitioner who followed +FIT to colonoscopy in August 2020. After implementation we noted little improvement in colonoscopy < 180 days compliance. This prompted a quality improvement (QI) project which resulted in a centralized database. Here we report a subgroup analysis to answer the question: were there racial disparities in +FIT follow-up prior to FITNav implementation? Methods: We queried +FIT from patients 45-85 y/o from 3/1/2019/20-9/3/2019/20, defined as the pre-pandemic and pandemic cohorts respectively. Patients with dementia & >65 y/o, diagnostic/inpatient FIT, or provider-initiated cancellation of colonoscopy due to comorbidities were excluded. Chart review retrieved FIT indications, patient/navigator notification time, GI consult placement time, and colonoscopy. We added Area deprivation index (ADI) to evaluate neighborhood-level disparities. An adjusted and unadjusted cox regression model was used to evaluate colonoscopy < 180 days between pandemic/pre-pandemic, summarizing via hazard ratios (HR) and 95% confidence intervals (CI). (Figure) Results: There were 121 & 103 +FIT meeting criteria in the pandemic & pre-pandemic respectively. Demographics (age, marital status, race, ADI, and sex) between periods showed no statistically significant differences. Proportion receiving colonoscopy < 180 days in the pre-pandemic and pandemic periods was 53.7% and 60.2% (unadjusted HR 1.08, 95% CI 0.76-1.54, p=0.676). This remained insignificant when adjusted for race/ethnicity, marital status, priority group, ADI, time to notification, and age (adjusted HR 1.03, 95% CI 0.71-1.50, p=0.872). While Black, non-Hispanic individuals had a univariate HR of 2.09 (95% CI 1.33-3.29 p=0.001), multivariate HR was 1.59 (95% CI 0.92-2.74, p=0.093). ADI did not show a statistically significant difference upon univariate or multivariate analysis. (Table) Conclusion: No findings were present which suggested new or exacerbated racial disparities. Additionally, neighborhood-level disparities did not modify these findings; however, this evaluation is limited by sample size.Figure 1.: Kaplan-Meier Plot Colonoscopy in <180 days Pre-pandemic vs. Pandemic y-axis= Probability Blue= Pre-pandemic Red= Pandemic Table 1. - Hazard Ratios Obtained on Cox Regression for Pre-pandemic/Pandemic Cohorts Total HR (univariable)* HR (multivariable)* Cohort Pre-pandemic 114 (53%) Pandemic 101 (47%) 1.08 (0.76-1.54, p=0.676) 1.03 (0.71-1.50, p=0.872) Race/Ethnicity Caucasian/ Non-Hispanic 162 (75%) Black/ Non-Hispanic 26 (12%) 2.09 (1.33-3.29, p=0.001) 1.59 (0.92-2.74, p=0.093) Hispanic 15 (7%) 0.80 (0.37-1.73, p=0.573) 0.74 (0.33-1.64, p=0.454) Others 6 (4%) 0.74 (0.33-1.64, p=0.454) 0.82 (0.25-2.67, p=0.741) Declined/Unknown 6 (4%) 0.55 (0.13-2.22, p=0.398) 0.47 (0.11-1.98, p=0.304) Marital Status Married 113 (52.6%) Not Married 102 (47.4%) 0.68 (0.47-0.97, p=0.033) 0.74 (0.51-1.10, p=0.136) ADI National Rank Mean (SD) 64.1 (22.7) 0.99 (0.99-1.00, p=0.127) 1.00 (0.99-1.01, p=0.441) Days to FIT Notification Mean (SD) 9.0 (12.7) 0.98 (0.96-1.01, p=0.141) 0.98 (0.95-1.01, p=0.131) Age Mean (SD) 66.4 (8.4) 0.98 (0.96-1.00, p=0.035) 0.98 (0.96-1.01, p=0.133) *Blank Cells represent reference groups.

Combining AI Techniques for Recognizing Aerobics Sport Videos.

In order to improve the recognition accuracy of aerobics athletes' action features, a multifeature fusion-supported aerobics footprint recognition framework was proposed in this work. By extracting and constructing the 3D peripheral structure reconstruction scheme of the concept of aerobics footprint, we combine the fuzzy feature decomposition method to decompose the aerobics footprint image with multi-pane and suggest fusion. We further realize the similarity identification of aerobics athlete's trajectory through the wear polymorphic liquefaction method. Simulation results have shown that our proposed method has better effect on the similarity recognition of bodybuilders' footprints, a higher accuracy of behavior location, a satisfactory notification time, and an accurate recognition of bodybuilders' footprints. Experiments have shown that our designed system has a small mean square error of aerobics movements and a confirmation of absolute failure. It also has a high recognition fidelity. Noticeably, the reason for the difficulty of aerobics coordination of 10 athletes and the confusion of actual coordination is small, and the accuracy of the Beer effect is high. Our method can be applied for body building, and it can provide the foundation for Game Bill.

Real Time Threat Assessment of Truck Cargos Carrying Dangerous Goods for Preventing Terrorism Attacks on Neighboring Critical Infrastructures

Critical infrastructures are assets of invaluable importance, essential for the whole world. Since they serve core functions of our societies, they often become targets of terrorists. Many critical infrastructures are vulnerable, due to their short distance from public roads and in the past years, several vehicle-bomb incidents have been recorded. This paper focuses on the case of truck-bombs, which can either be created from scratch, or terrorists can easily hijack truck cargos carrying dangerous goods and turn them into bombs. The latter are typically called ADR truck cargos, according to the respective agreement of the 30th of September 1957, concerning the international carriage of dangerous goods by road. The proposed scheme performs threat assessment of neighboring critical infrastructures, aiming at preventing explosions of truck-bombs. To do so, each crucial point of a critical infrastructure is initially associated with a level of importance. Next, three scenarios are analyzed: (a) single-attack single-infrastructure, (b) multiple-attack single-infrastructure, and (c) multiple-attack multiple-infrastructure. To reduce computational complexity, the third scenario is simplified to one of the two other scenarios, by introducing a novel fusion technique for the non-overlapping segments of the Voronoi tessellation. By this way, an area of threat assessment is estimated for each critical infrastructure. Then, the threat level is assessed in real time by an innovative algorithm, which: (a) estimates the impact of multiple consecutive explosions, (b) uses five adapted threat levels and (c) introduces multiple criteria and minimum classification conditions based on the number of crucial points and their levels of importance. Extensive real world experimental results and comparisons to other works, exhibit the pros and cons of the proposed scheme. In particular the proposed scheme improves: (a) computational time by 74.5%, compared to [69], (b) threat notification time by 86.9% compared to [70] and (c) estimated surveillance cost by 98.6% compared to [71].

Research on Optimal Scheduling Algorithm for Interruptible Load for Clean Electric Energy

The rapid growth of electric energy demand and the power construction of the lag have led to the problem of electricity shortage. At the same time, the idea of energy conservation and emission reduction and low-carbon environmental protection is gradually deepening in people’s hearts, making it inhibited by improving the development model of the installed capacity of the fire generator set. As an important measure to respond to the demand side response, the interrupt load is an effective means of solving this problem. In this context, this paper proposes an interrupting load management method that considers the advance notification time and uses a priority order method. Solving, making the application of interrupt load more secure and reliable and economic goals.