Applications of Artificial Intelligence in Emergency Departments to Improve Wait Times: Protocol for an Integrative Living Review.

BACKGROUND: Long wait times in the emergency department (ED) are a major issue for health care systems all over the world. The application of artificial intelligence (AI) is a novel strategy to reduce ED wait times when compared to the interventions included in previous research endeavors. To date, comprehensive systematic reviews that include studies involving AI applications in the context of EDs have covered a wide range of AI implementation issues. However, the lack of an iterative update strategy limits the use of these reviews. Since the subject of AI development is cutting edge and is continuously changing, reviews in this area must be frequently updated to remain relevant. OBJECTIVE: This study aims to provide a summary of the evidence that is currently available regarding how AI can affect ED wait times; discuss the applications of AI in improving wait times; and periodically assess the depth, breadth, and quality of the evidence supporting the application of AI in reducing ED wait times. METHODS: We plan to conduct a living systematic review (LSR). Our strategy involves conducting continuous monitoring of evidence, with biannual search updates and annual review updates. Upon completing the initial round of the review, we will refine the search strategy and establish clear schedules for updating the LSR. An interpretive synthesis using Whittemore and Knafl's framework will be performed to compile and summarize the findings. The review will be carried out using an integrated knowledge translation strategy, and knowledge users will be involved at all stages of the review to guarantee applicability, usability, and clarity of purpose. RESULTS: The literature search was completed by September 22, 2023, and identified 17,569 articles. The title and abstract screening were completed by December 9, 2023. In total, 70 papers were eligible. The full-text screening is in progress. CONCLUSIONS: The review will summarize AI applications that improve ED wait time. The LSR enables researchers to maintain high methodological rigor while enhancing the timeliness, applicability, and value of the review. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/52612.

Point cloud completion in challenging indoor scenarios with human motion.

Combining and completing point cloud data from two or more sensors with arbitrarily relative perspectives in a dynamic, cluttered, and complex environment is challenging, especially when the two sensors have significant perspective differences while the large overlap ratio and feature-rich scene cannot be guaranteed. We create a novel approach targeting this challenging scenario by registering two camera captures in a time series with unknown perspectives and human movements to easily use our system in a real-life scene. In our approach, we first reduce the six unknowns of 3D point cloud completion to three by aligning the ground planes found by our previous perspective-independent 3D ground plane estimation algorithm. Subsequently, we use a histogram-based approach to identify and extract all the humans from each frame generating a three-dimensional (3D) human walking sequence in a time series. To enhance accuracy and performance, we convert 3D human walking sequences to lines by calculating the center of mass (CoM) point of each human body and connecting them. Finally, we match the walking paths in different data trials by minimizing the Fréchet distance between two walking paths and using 2D iterative closest point (ICP) to find the remaining three unknowns in the overall transformation matrix for the final alignment. Using this approach, we can successfully register the corresponding walking path of the human between the two cameras' captures and estimate the transformation matrix between the two sensors.

Assessing Road to Mental Readiness (R2MR) training among correctional workers in Canada.

BACKGROUND: Mental health frameworks, best practices, and the well-being of public safety personnel in Canada are topics of increasing interest to both researchers and organizations. To protect and improve worker mental health, different training programs have been implemented to serve this population. The Road to Mental Readiness (R2MR) training regimen is one such program specialized to build cultural awareness of mental health, reduce stigma, and mitigate the cumulative impacts of exposures to potentially psychologically traumatic events among public safety personnel. However, limited research has been conducted to evaluate the effectiveness of R2MR, especially among correctional workers. METHODS: The current study analyzed 307 open-ended survey responses to four (4) questions about R2MR garnered from 124 Canadian provincial and territorial correctional workers between 2018-2020 to reveal their understandings and perceptions of R2MR training, and to identify what learned skills they found challenging or easy to implement. RESULTS: The results suggest that R2MR training plays a significant role in decreasing stigma and increasing mental health awareness. Across jurisdictions, R2MR creates a supportive space for open dialogue around mental health meant to shift cultural and individual barriers that often hinder treatment-seeking. Some respondents also indicated that R2MR was a starting point for intervention. CONCLUSIONS: Further research is necessary to understand how R2MR and other programs could support the mental health and well-being of correctional workers.

CCWORK protocol: a longitudinal study of Canadian Correctional Workers' Well-being, Organizations, Roles and Knowledge.

INTRODUCTION: Knowledge about the factors that contribute to the correctional officer's (CO) mental health and well-being, or best practices for improving the mental health and well-being of COs, have been hampered by the dearth of rigorous longitudinal studies. In the current protocol, we share the approach used in the Canadian Correctional Workers' Well-being, Organizations, Roles and Knowledge study (CCWORK), designed to investigate several determinants of health and well-being among COs working in Canada's federal prison system. METHODS AND ANALYSIS: CCWORK is a multiyear longitudinal cohort design (2018-2023, with a 5-year renewal) to study 500 COs working in 43 Canadian federal prisons. We use quantitative and qualitative data collection instruments (ie, surveys, interviews and clinical assessments) to assess participants' mental health, correctional work experiences, correctional training experiences, views and perceptions of prison and prisoners, and career aspirations. Our baseline instruments comprise two surveys, one interview and a clinical assessment, which we administer when participants are still recruits in training. Our follow-up instruments refer to a survey, an interview and a clinical assessment, which are conducted yearly when participants have become COs, that is, in annual 'waves'. ETHICS AND DISSEMINATION: CCWORK has received approval from the Research Ethics Board of the Memorial University of Newfoundland (File No. 20190481). Participation is voluntary, and we will keep all responses confidential. We will disseminate our research findings through presentations, meetings and publications (e.g., journal articles and reports). Among CCWORK's expected scientific contributions, we highlight a detailed view of the operational, organizational and environmental stressors impacting CO mental health and well-being, and recommendations to prison administrators for improving CO well-being.

Automatic Super-Surface Removal in Complex 3D Indoor Environments Using Iterative Region-Based RANSAC.

Removing bounding surfaces such as walls, windows, curtains, and floor (i.e., super-surfaces) from a point cloud is a common task in a wide variety of computer vision applications (e.g., object recognition and human tracking). Popular plane segmentation methods such as Random Sample Consensus (RANSAC), are widely used to segment and remove surfaces from a point cloud. However, these estimators easily result in the incorrect association of foreground points to background bounding surfaces because of the stochasticity of randomly sampling, and the limited scene-specific knowledge used by these approaches. Additionally, identical approaches are generally used to detect bounding surfaces and surfaces that belong to foreground objects. Detecting and removing bounding surfaces in challenging (i.e., cluttered and dynamic) real-world scene can easily result in the erroneous removal of points belonging to desired foreground objects such as human bodies. To address these challenges, we introduce a novel super-surface removal technique for 3D complex indoor environments. Our method was developed to work with unorganized data captured from commercial depth sensors and supports varied sensor perspectives. We begin with preprocessing steps and dividing the input point cloud into four overlapped local regions. Then, we apply an iterative surface removal approach to all four regions to segment and remove the bounding surfaces. We evaluate the performance of our proposed method in terms of four conventional metrics: specificity, precision, recall, and F1 score, on three generated datasets representing different indoor environments. Our experimental results demonstrate that our proposed method is a robust super-surface removal and size reduction approach for complex 3D indoor environments while scoring the four evaluation metrics between 90% and 99%.

The Time Is Now: A FASTER Approach to Generate Research Evidence for Technology-Based Interventions in the Field of Disability and Rehabilitation.

Current approaches for generating high-quality research evidence for technology-based interventions in the field of disability and rehabilitation are inappropriate. Prevailing approaches often focus on randomized controlled trials as standard and apply clinical trial practices designed for pharmaceuticals; such approaches are unsuitable for technology-based interventions and are counterproductive to the goals of supporting people with disabilities and creating benefits for society. This communication is designed to: (1) advocate for the use of alternative approaches to generating evidence in the development and evaluation of technology-based interventions; (2) propose an alternative framework and guiding principles; and (3) stimulate action by multiple disciplines and sectors to discuss, adopt, and promote alternative approaches. Our Framework for Accelerated and Systematic Technology-based intervention development and Evaluation Research (FASTER) is informed by established innovation design processes, complex intervention development, evaluation, and implementation concepts as well as our collective experiences in technology-based interventions research and clinical rehabilitation practice. FASTER is intended to be meaningful, timely, and practical for researchers, technology developers, clinicians, and others who develop these interventions and seek evidence. We incorporate research methods and designs that better align with creating technology-based interventions and evidence for integration into practice. We propose future activities to improve the generation of research evidence, enable the selection of research methods and designs, and create standards for evidence evaluation to support rigor and applicability for technology-based interventions. With this communication we aim to improve and advance technology-based intervention integration from conception to use, thus responsibly accelerating innovation to have greater positive benefit for people and society.

Spatiotemporal Gait Measurement With a Side-View Depth Sensor Using Human Joint Proposals.

We propose a method for calculating standard spatiotemporal gait parameters from individual human joints with a side-view depth sensor. Clinical walking trials were measured concurrently by a side-view Kinect and a pressure-sensitive walkway, the Zeno Walkway. Multiple joint proposals were generated from depth images by a stochastic predictor based on the Kinect algorithm. The proposals are represented as vertices in a weighted graph, where the weights depend on the expected and measured lengths between body parts. A shortest path through the graph is a set of joints from head to foot. Accurate foot positions are selected by comparing pairs of shortest paths. Stance phases of the feet are detected by examining the motion of the feet over time. The stance phases are used to calculate four gait parameters: stride length, step length, stride width, and stance percentage. A constant frame rate was assumed for the calculation of stance percentage because time stamps were not captured during the experiment. Gait parameters from 52 trials were compared to the ground truth walkway using Bland-Altman analysis and intraclass correlation coefficients. The large spatial parameters had the strongest agreements with the walkway (ICC(2, 1) = 1.00 and 0.98 for stride and step length with normal pace, respectively). The presented system directly calculates gait parameters from individual foot positions while previous side-view systems relied on indirect measures. Using a side-view system allows for tracking walking in both directions with one camera, extending the range in which the subject is in the field of view.

Canadian Public Safety Personnel and Occupational Stressors: How PSP Interpret Stressors on Duty.

Canadian public safety personnel (e.g., correctional workers, firefighters) experience potential stressors as a function of their occupation. Occupational stressors can include organizational (e.g., job context) and operational (e.g., job content) elements. Operational stressors (e.g., exposures to potentially psychologically traumatic events) may be inevitable, but opportunities may exist to mitigate other occupational stressors for public safety personnel. Research exploring the diverse forms of stress among public safety personnel remains sparse. In our current qualitative study we provide insights into how public safety personnel interpret occupational stressors. We use a semi-grounded thematic approach to analyze what public safety personnel reported when asked to further comment on occupational stress or their work experiences in two open-ended comment fields of an online survey. We provide a more comprehensive understanding of how public safety personnel experience occupational stress and the stressors that are unique to their occupations. Beyond known operational stressors, our respondents (n = 1238; n = 828) reported substantial difficulties with organizational (interpersonal work relationship dynamics; workload distribution, resources, and administrative obligations) and operational (vigilance, work location, interacting with the public) stressors. Some operational stressors are inevitable, but other occupational stressors can be mitigated to better support our public safety personnel.

Mental health training, attitudes toward support, and screening positive for mental disorders.

Public Safety Personnel (PSP; e.g. correctional workers, dispatchers, firefighters, paramedics, police) are frequently exposed to potentially traumatic events (PTEs). Several mental health training program categories (e.g. critical incident stress management (CISM), debriefing, peer support, psychoeducation, mental health first aid, Road to Mental Readiness [R2MR]) exist as efforts to minimize the impact of exposures, often using cognitive behavioral therapy model content, but with limited effectiveness research. The current study assessed PSP perceptions of access to professional (i.e. physicians, psychologists, psychiatrists, employee assistance programs, chaplains) and non-professional (i.e. spouse, friends, colleagues, leadership) support, and associations between training and mental health. Participants included 4,020 currently serving PSP participants. Data were analyzed using cross-tabulations and logistic regressions. Most PSP reported access to professional and non-professional support; nevertheless, most would first access a spouse (74%) and many would never, or only as a last resort, access professional support (43-60%) or PSP leaders (67%). Participation in any mental health training category was associated with lower (p < .01) rates for some, but not all, mental disorders, with no robust differences across categories. Revisions to training programs may improve willingness to access professional support; in the interim, training and support for PSP spouses and leaders may also be beneficial.

System Development Guidelines From a Review of Motion-Based Technology for People With Dementia or MCI.

As the population ages and the number of people living with dementia or mild cognitive impairment (MCI) continues to increase, it is critical to identify creative and innovative ways to support and improve their quality of life. Motion-based technology has shown significant potential for people living with dementia or MCI by providing opportunities for cognitive stimulation, physical activity and participation in meaningful leisure activities, while simultaneously functioning as a useful tool for research and development of interventions. However, many of the current systems created using motion-based technology have not been designed specifically for people with dementia or MCI. Additionally, the usability and accessibility of these systems for these populations has not been thoroughly considered. This paper presents a set of system development guidelines derived from a review of the state of the art of motion-based technologies for people with dementia or MCI. These guidelines highlight three overarching domains of consideration for systems targeting people with dementia or MCI: (i) cognitive, (ii) physical, and (iii) social. We present the guidelines in terms of relevant design and use considerations within these domains and the emergent design themes within each domain. Our hope is that these guidelines will aid in designing motion-based software to meet the needs of people with dementia or MCI such that the potential of these technologies can be realized.

Human Part Segmentation in Depth Images with Annotated Part Positions.

We present a method of segmenting human parts in depth images, when provided the image positions of the body parts. The goal is to facilitate per-pixel labelling of large datasets of human images, which are used for training and testing algorithms for pose estimation and automatic segmentation. A common technique in image segmentation is to represent an image as a two-dimensional grid graph, with one node for each pixel and edges between neighbouring pixels. We introduce a graph with distinct layers of nodes to model occlusion of the body by the arms. Once the graph is constructed, the annotated part positions are used as seeds for a standard interactive segmentation algorithm. Our method is evaluated on two public datasets containing depth images of humans from a frontal view. It produces a mean per-class accuracy of 93.55% on the first dataset, compared to 87.91% (random forest and graph cuts) and 90.31% (random forest and Markov random field). It also achieves a per-class accuracy of 90.60% on the second dataset. Future work can experiment with various methods for creating the graph layers to accurately model occlusion.

Predicting the role of assistive technologies in the lives of people with dementia using objective care recipient factors.

BACKGROUND: The population of people with dementia is not homogeneous. People with dementia exhibit a wide range of needs, each characterized by diverse factors including age, sex, ethnicity, and place of residence. These needs and characterizing factors may influence the applicability, and ultimately the acceptance, of assistive technologies developed to support the independence of people with dementia. Accordingly, predicting the needs of users before developing the technologies may increase the applicability and acceptance of assistive technologies. Current methods of prediction rely on the difficult collection of subjective, potentially invasive information. We propose a method of prediction that uses objective, unobtrusive, easy to collect information to help inform the development of assistive technologies. METHODS: We develop a set of models that can predict the level of independence of people with dementia during 20 activities of daily living using simple, objective information. Using data collected from a Canadian survey conducted with caregivers of people with dementia, we create an ordered logistic regression model for each of the twenty daily tasks in the Bristol ADL scale. RESULTS: Data collected from 430 Canadian caregivers of people with dementia were analyzed to reveal: most care recipients were mothers or husbands, married, living in private housing with their caregivers, English-speaking, Canadian born, clinically diagnosed with dementia 1 to 6 years prior to the study, and were dependent on their caregiver. Next, we developed models that use 13 factors to predict a person with dementia's ability to complete the 20 Bristol activities of daily living independently. The 13 factors include caregiver relation, age, marital status, place of residence, language, housing type, proximity to caregiver, service use, informal primary caregiver, diagnosis of Alzheimer's disease or dementia, time since diagnosis, and level of dependence on caregiver. The resulting models predicted the aggregate level of independence correctly for 88 of 100 total responses categories, marginally for nine, and incorrectly for three. CONCLUSIONS: Objective, easy to collect information can predict caregiver-reported level of task independence for a person with dementia. Knowledge of task independence can then inform the development of assistive technologies for people with dementia, improving their applicability and acceptance.

Development and evaluation of a hand tracker using depth images captured from an overhead perspective.

PURPOSE: We present the development and evaluation of a robust hand tracker based on single overhead depth images for use in the COACH, an assistive technology for people with dementia. The new hand tracker was designed to overcome limitations experienced by the COACH in previous clinical trials. METHODS: We train a random decision forest classifier using ∼5000 manually labeled, unbalanced, training images. Hand positions from the classifier are translated into task actions based on proximity to environmental objects. Tracker performance is evaluated using a large set of ∼24 000 manually labeled images captured from 41 participants in a fully-functional washroom, and compared to the system's previous colour-based hand tracker. RESULTS: Precision and recall were 0.994 and 0.938 for the depth tracker compared to 0.981 and 0.822 for the colour tracker with the current data, and 0.989 and 0.466 in the previous study. CONCLUSIONS: The improved tracking performance supports integration of the depth-based tracker into the COACH toward unsupervised, real-world trials. Implications for Rehabilitation The COACH is an intelligent assistive technology that can enable people with cognitive disabilities to stay at home longer, supporting the concept of aging-in-place. Automated prompting systems, a type of intelligent assistive technology, can help to support the independent completion of activities of daily living, increasing the independence of people with cognitive disabilities while reducing the burden of care experienced by caregivers. Robust motion tracking using depth imaging supports the development of intelligent assistive technologies like the COACH. Robust motion tracking also has application to other forms of assistive technologies including gaming, human-computer interaction and automated assessments.