Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting.

OBJECTIVES: To distinguish histological subtypes of renal tumors using radiomic features and machine learning (ML) based on multiphase computed tomography (CT). MATERIAL AND METHODS: Patients who underwent surgical treatment for renal tumors at two tertiary centers from 2012 to 2022 were included retrospectively. Preoperative arterial (corticomedullary) and venous (nephrogenic) phase CT scans from these centers, as well as from external imaging facilities, were manually segmented, and standardized radiomic features were extracted. Following preprocessing and addressing the class imbalance, a ML algorithm based on extreme gradient boosting trees (XGB) was employed to predict renal tumor subtypes using 10-fold cross-validation. The evaluation was conducted using the multiclass area under the receiver operating characteristic curve (AUC). Algorithms were trained on data from one center and independently tested on data from the other center. RESULTS: The training cohort comprised n = 297 patients (64.3% clear cell renal cell cancer [RCC], 13.5% papillary renal cell carcinoma (pRCC), 7.4% chromophobe RCC, 9.4% oncocytomas, and 5.4% angiomyolipomas (AML)), and the testing cohort n = 121 patients (56.2%/16.5%/3.3%/21.5%/2.5%). The XGB algorithm demonstrated a diagnostic performance of AUC = 0.81/0.64/0.8 for venous/arterial/combined contrast phase CT in the training cohort, and AUC = 0.75/0.67/0.75 in the independent testing cohort. In pairwise comparisons, the lowest diagnostic accuracy was evident for the identification of oncocytomas (AUC = 0.57-0.69), and the highest for the identification of AMLs (AUC = 0.9-0.94) CONCLUSION: Radiomic feature analyses can distinguish renal tumor subtypes on routinely acquired CTs, with oncocytomas being the hardest subtype to identify. CLINICAL RELEVANCE STATEMENT: Radiomic feature analyses yield robust results for renal tumor assessment on routine CTs. Although radiologists routinely rely on arterial phase CT for renal tumor assessment and operative planning, radiomic features derived from arterial phase did not improve the accuracy of renal tumor subtype identification in our cohort.

Preventing cognitive decline via digital inclusion and virtual game management: an intervention study with older adults in the community.

OBJECTIVE: To evaluate the impact of cognitive stimulation via digital inclusion and the practice of video games on the cognition of the older population. METHOD: This is a randomized controlled intervention study, nested in a population cohort study. Based on the application of the Clinical Dementia Rating (CDR) test, individuals aged 60 years or older with scores 0 and 0.5 were included and randomly allocated in the Intervention Group (IG) or Control Group (CG). Initially, 160 participants met the selection criteria and underwent neuropsychological evaluation via the Montreal Cognitive Assessment (MoCA), applied before and after intervention. The IG (n = 62) participated in computer-based intervention once a week for one-and-a-half hours, for 4 months. The CG (n = 47) participated in the mindfulness workshops held in the same period. RESULTS: The digital literacy intervention group averaged 2.6 points more in the MoCA after 4 months. The change in the final MoCA decreased in 0.46 points at each unit in the basal MoCA. Individuals with average schooling had an increase of 0.93 points in the change of the MoCA in relation to individuals with low or high schooling. CONCLUSION: Digital inclusion combined with the practice of video games has the potential to improve the cognition of the older population.

Characterizing nursing time with patients using computer vision.

BACKGROUND: Compared to other providers, nurses spend more time with patients, but the exact quantity and nature of those interactions remain largely unknown. The purpose of this study was to characterize the interactions of nurses at the bedside using continuous surveillance over a year long period. METHODS: Nurses' time and activity at the bedside were characterized using a device that integrates the use of obfuscated computer vision in combination with a Bluetooth beacon on the nurses' identification badge to track nurses' activities at the bedside. The surveillance device (AUGi) was installed over 37 patient beds in two medical/surgical units in a major urban hospital. Forty-nine nurse users were tracked using the beacon. Data were collected 4/15/19-3/15/20. Statistics were performed to describe nurses' time and activity at the bedside. RESULTS: A total of n = 408,588 interactions were analyzed over 670 shifts, with >1.5 times more interactions during day shifts (n = 247,273) compared to night shifts (n = 161,315); the mean interaction time was 3.34 s longer during nights than days (p < 0.0001). Each nurse had an average of 7.86 (standard deviation [SD] = 10.13) interactions per bed each shift and a mean total interaction time per bed of 9.39 min (SD = 14.16). On average, nurses covered 7.43 beds (SD = 4.03) per shift (day: mean = 7.80 beds/nurse/shift, SD = 3.87; night: mean = 7.07/nurse/shift, SD = 4.17). The mean time per hourly rounding (HR) was 69.5 s (SD = 98.07) and 50.1 s (SD = 56.58) for bedside shift report. DISCUSSION: As far as we are aware, this is the first study to provide continuous surveillance of nurse activities at the bedside over a year long period, 24 h/day, 7 days/week. We detected that nurses spend less than 1 min giving report at the bedside, and this is only completed 20.7% of the time. Additionally, hourly rounding was completed only 52.9% of the time and nurses spent only 9 min total with each patient per shift. Further study is needed to detect whether there is an optimal timing or duration of interactions to improve patient outcomes. CLINICAL RELEVANCE: Nursing time with the patient has been shown to improve patient outcomes but precise information about how much time nurses spend with patients has been heretofore unknown. By understanding minute-by-minute activities at the bedside over a full year, we provide a full picture of nursing activity; this can be used in the future to determine how these activities affect patient outcomes.

Twelve tips to virtually operationalize co-creation of educational design.

Co-creation is the active involvement of all stakeholders, including students, in educational design processes to improve the quality of education by embodying inclusivity, transparency and empowerment. Virtual co-creation has the potential to expand the utility of co-creation as an inclusive approach by overcoming challenges regarding the practicality and availability of stakeholders, typically experienced in face-to-face co-creation. Drawing from the literature and our experiences of virtual co-creation activities in different educational contexts, this twelve tips paper provides guidelines on how to effectively operationalize co-creation in a virtual setting. Our proposed three-phased approach (preparation, conduction, follow-up) might help those aiming to virtually co-create courses and programs by involving stakeholders beyond institutes and across borders.

Facing up to Problem Gambling: Tracing the Emergence of Facial Recognition Technology as a means of Enforcing Voluntary Self-Exclusion.

Computer technology has long been touted as a means of increasing the effectiveness of voluntary self-exclusion schemes - especially in terms of relieving gaming venue staff of the task of manually identifying and verifying the status of new customers. This paper reports on the government-led implementation of facial recognition technology as part of an automated self-exclusion program in the city of Adelaide in South Australia-one of the first jurisdiction-wide enforcements of this controversial technology in small venue gambling. Drawing on stakeholder interviews, site visits and documentary analysis over a two year period, the paper contrasts initial claims that facial recognition offered a straightforward and benign improvement to the efficiency of the city's long-running self-excluded gambler program, with subsequent concerns that the new technology was associated with heightened inconsistencies, inefficiencies and uncertainties. As such, the paper contends that regardless of the enthusiasms of government, tech industry and gaming lobby, facial recognition does not offer a ready 'technical fix' to problem gambling. The South Australian case illustrates how this technology does not appear to better address the core issues underpinning problem gambling, and/or substantially improve conditions for problem gamblers to refrain from gambling. As such, it is concluded that the gambling sector needs to pay close attention to the practical outcomes arising from initial cases such as this, and resist industry pressures for the wider replication of this technology in other jurisdictions.

Low-Cost Imaging to Quantify Germination Rate and Seedling Vigor across Lettuce Cultivars.

The survival and growth of young plants hinge on various factors, such as seed quality and environmental conditions. Assessing seedling potential/vigor for a robust crop yield is crucial but often resource-intensive. This study explores cost-effective imaging techniques for rapid evaluation of seedling vigor, offering a practical solution to a common problem in agricultural research. In the first phase, nine lettuce (Lactuca sativa) cultivars were sown in trays and monitored using chlorophyll fluorescence imaging thrice weekly for two weeks. The second phase involved integrating embedded computers equipped with cameras for phenotyping. These systems captured and analyzed images four times daily, covering the entire growth cycle from seeding to harvest for four specific cultivars. All resulting data were promptly uploaded to the cloud, allowing for remote access and providing real-time information on plant performance. Results consistently showed the 'Muir' cultivar to have a larger canopy size and better germination, though 'Sparx' and 'Crispino' surpassed it in final dry weight. A non-linear model accurately predicted lettuce plant weight using seedling canopy size in the first study. The second study improved prediction accuracy with a sigmoidal growth curve from multiple harvests (R2 = 0.88, RMSE = 0.27, p < 0.001). Utilizing embedded computers in controlled environments offers efficient plant monitoring, provided there is a uniform canopy structure and minimal plant overlap.

A Review of Recent Hardware and Software Advances in GPU-Accelerated Edge-Computing Single-Board Computers (SBCs) for Computer Vision.

Computer Vision (CV) has become increasingly important for Single-Board Computers (SBCs) due to their widespread deployment in addressing real-world problems. Specifically, in the context of smart cities, there is an emerging trend of developing end-to-end video analytics solutions designed to address urban challenges such as traffic management, disaster response, and waste management. However, deploying CV solutions on SBCs presents several pressing challenges (e.g., limited computation power, inefficient energy management, and real-time processing needs) hindering their use at scale. Graphical Processing Units (GPUs) and software-level developments have emerged recently in addressing these challenges to enable the elevated performance of SBCs; however, it is still an active area of research. There is a gap in the literature for a comprehensive review of such recent and rapidly evolving advancements on both software and hardware fronts. The presented review provides a detailed overview of the existing GPU-accelerated edge-computing SBCs and software advancements including algorithm optimization techniques, packages, development frameworks, and hardware deployment specific packages. This review provides a subjective comparative analysis based on critical factors to help applied Artificial Intelligence (AI) researchers in demonstrating the existing state of the art and selecting the best suited combinations for their specific use-case. At the end, the paper also discusses potential limitations of the existing SBCs and highlights the future research directions in this domain.

Trajectories of Problem Behaviors and Information Technology Use Among Adolescents: A Latent Growth Model Using the Korean Children and Youth Panel Survey.

We investigated the association between computer and mobile phone online activities and adolescents' problem behaviors (e.g., depressive symptoms, withdrawal, somatic complaints, attention deficit, and aggression) using data from the Korean Children and Youth Panel Survey and latent growth model analysis. The results demonstrated that text-related activities lowered withdrawal and attention deficit. Higher use of online communities or personal websites was associated with higher depressive symptoms, withdrawal, somatic symptoms, and aggression. Online gaming increased both attention deficit' initial value and its decrease rate. Taking photos decreased withdrawal. Watching videos increased depressive symptoms, withdrawal, and attention deficit. Listening to music lowered attention deficit' initial value and somatic symptoms' decrease rate. Accessing adult websites increased attention deficit and aggression. Educational information searches reduced attention deficit and aggression. Online transactions increased somatic symptoms. This study indicates that adolescents' problem behaviors may appear differently depending on the type of information technology use.

The application of virtual reality and augmented reality in dentistry - a literature review.

In recent times, dentistry has seen significant technological advancements that have transformed various specialized areas within the field. Developed into applications for mobile devices, augmented reality (AR) seamlessly merges digital components with the physical world, enhancing both realms while maintaining their individual separateness. On the other hand, virtual reality (VR) relies on advanced, tailored software to visualize a digital 3D environment stimulating the operator's senses through computer generated sensations and feedback. The current advances use the application of VR, haptic simulators, the use of an AI algorithm and many more that provides new opportunities for smart learning and enhance the teaching environment. As this technology continues to evolve, it is poised to become even more remarkable, enabling specialists to potentially visualize both soft and hard tissues within the patient's body for effective treatment planning. This literature aims to present the newest advancements and ongoing development of AR and VR in dentistry and medicine. It highlights their diverse applications while identifying areas needing further research for effective integration into clinical practice.

A narrative review of the development and performance characteristics of electronic delirium-screening tools.

BACKGROUND: Electronic delirium-screening tools are an emergent area of research. OBJECTIVE: The objective of this study was to summarise the development and performance characteristics of electronic screening tools in delirium. METHODS: Searches were conducted in Pubmed, Embase, and CINAHL Complete databases to identify electronic delirium-screening tools. RESULTS: Five electronic delirium-screening tools were identified and reviewed. Two were designed for and tested within a medical setting, and three were applied to intensive care. Adaptive design features, such as skip function to reduce test burden, were variably integrated into instrument design. All tools were shown to have acceptable psychometric properties, but validation studies were largely incomplete. CONCLUSIONS: Electronic delirium-screening tools are an exciting area of development and may offer hope for improved uptake of delirium screening.

Development and transfer of automated methods in neuroscience: The DADTA.

In the second half of the 20th century, neuroscientists across North America developed automated systems for use in their research laboratories. Their decisions to do so were complex and contingent, partly a result of global reasons, such as the need to increase efficiency and flexibility, and partly a result of local reasons, such as the need to amend perceived biases of earlier research methodologies. Automated methods were advancements but raised several challenges. Transferring a system from one location to another required that certain components of the system be standardized, such as the hardware, software, and programming language. This proved difficult as commercial manufacturers lacked incentives to create standardized products for the few neuroscientists working towards automation. Additionally, investing in automated systems required massive amounts of time, labor, funding, and computer expertise. Moreover, neuroscientists did not agree on the value of automation. My brief history investigates Karl Pribram's decisions to expand his newly created automated system by standardizing equipment, programming, and protocols. Although he was an eminent Stanford neuroscientist with strong institutional support and computer know-how, the development and transfer of his automated behavioral testing system was riddled with challenges. For Pribram and neuroscience more generally, automation was not so automatic.

Quantum computing in pharma: A multilayer embedding approach for near future applications.

Quantum computers are special purpose machines that are expected to be particularly useful in simulating strongly correlated chemical systems. The quantum computer excels at treating a moderate number of orbitals within an active space in a fully quantum mechanical manner. We present a quantum phase estimation calculation on F2 in a (2,2) active space on Rigetti's Aspen-11 QPU. While this is a promising start, it also underlines the need for carefully selecting the orbital spaces treated by the quantum computer. In this work, a scheme for selecting such an active space automatically is described and simulated results obtained using both the quantum phase estimation (QPE) and variational quantum eigensolver (VQE) algorithms are presented and combined with a subtractive method to enable accurate description of the environment. The active occupied space is selected from orbitals localized on the chemically relevant fragment of the molecule, while the corresponding virtual space is chosen based on the magnitude of interactions with the occupied space calculated from perturbation theory. This protocol is then applied to two chemical systems of pharmaceutical relevance: the enzyme [Fe] hydrogenase and the photosenzitizer temoporfin. While the sizes of the active spaces currently amenable to a quantum computational treatment are not enough to demonstrate quantum advantage, the procedure outlined here is applicable to any active space size, including those that are outside the reach of classical computation.

The uncovered biases and errors in clinical determination of bone age by using deep learning models.

OBJECTIVES: To evaluate AI biases and errors in estimating bone age (BA) by comparing AI and radiologists' clinical determinations of BA. METHODS: We established three deep learning models from a Chinese private dataset (CHNm), an American public dataset (USAm), and a joint dataset combining the above two datasets (JOIm). The test data CHNt (n = 1246) were labeled by ten senior pediatric radiologists. The effects of data site differences, interpretation bias, and interobserver variability on BA assessment were evaluated. The differences between the AI models' and radiologists' clinical determinations of BA (normal, advanced, and delayed BA groups by using the Brush data) were evaluated by the chi-square test and Kappa values. The heatmaps of CHNm-CHNt were generated by using Grad-CAM. RESULTS: We obtained an MAD value of 0.42 years on CHNm-CHNt; this result indicated an appropriate accuracy for the whole group but did not indicate an accurate estimation of individual BA because with a kappa value of 0.714, the agreement between AI and human clinical determinations of BA was significantly different. The features of the heatmaps were not fully consistent with the human vision on the X-ray films. Variable performance in BA estimation by different AI models and the disagreement between AI and radiologists' clinical determinations of BA may be caused by data biases, including patients' sex and age, institutions, and radiologists. CONCLUSIONS: The deep learning models outperform external validation in predicting BA on both internal and joint datasets. However, the biases and errors in the models' clinical determinations of child development should be carefully considered. KEY POINTS: • With a kappa value of 0.714, clinical determinations of bone age by using AI did not accord well with clinical determinations by radiologists. • Several biases, including patients' sex and age, institutions, and radiologists, may cause variable performance by AI bone age models and disagreement between AI and radiologists' clinical determinations of bone age. • AI heatmaps of bone age were not fully consistent with human vision on X-ray films.

Computer vision syndrome and associated factors in university students and teachers in Nampula, Mozambique.

BACKGROUND: Computer Vision Syndrome (CVS) is a complex of eye and visual problems that arise while using a computer or other Video Display Terminal (DVT). With the advent of the COVID-19 pandemic, the use of these DVTs has become indispensable in the lives of students and teachers. This study aims to identify the prevalence of CVS and associated factors in students and teachers at Lúrio University, in Nampula, during the pandemic period. METHODS: This is a cross-sectional study, carried out between November 2020 and March 2021. The validated CVS questionnaire (CVS-Q) and another semi-structured questionnaire on ergonomic risk factors were applied. Odds ratios (OR) and adjusted odds ratios (aOR) were calculated to measure the association between CVS and computer use conditions. RESULTS: The prevalence of CVS was 76.6%, and the female gender, age ≤ 20 years, levels I, II, III of course, lack of knowledge about ergonomics, use the computer to study, use more than 6 hours daily, absence of anti-reflex treatment, use of other devices and sitting in an inappropriate chair were risk factors for the occurrence of CVS, while being a teacher was a protective factor. CONCLUSION: The prevalence of CVS found in this study was high, due to several factors, especially not using ergonomic principles when using computers and other DVTs. There is a need to adopt intervention strategies focused on the most vulnerable groups such as women, age group ≤20 years and students, especially at the first year level, right after entering the University.

Usability and feasibility of a tablet-based e-coach for older adults in rehabilitation units to improve nutrition and physical activity: a prospective pilot study.

BACKGROUND: For older adults (≥ 70 years), it is often challenging to maintain new nutrition and physical activity behaviours learned in rehabilitation. To minimize the risk of negative health consequences when returning home, an e-coach can be helpful. Aligning the program with an established concept such as the Transtheoretical Model of Behaviour Change (TTM) and guidance from healthcare professionals can optimize behaviour change. OBJECTIVE: This prospective single-arm pilot study aimed to assess the usability and feasibility of a nutrition and mobility e-coach for older adults during and after rehabilitation for a period of 9 weeks. In addition, we examined the change in the TTM phase as an indicator of the participant's readiness to change or the changes made. METHODS: Older adults (≥ 70 years) with nutrition deficits and/ or mobility limitations were recruited in a rehabilitation centre. Participants' phases of behaviour change in the TTM were identified by comparing current nutrition and physical activity habits via self-report with age-specific nutrition and physical activity recommendations. They received a tablet with the e-coach containing educational and interactive elements on the topics of nutrition and physical activity in older age. Participants used the e-coach and received support from healthcare professionals. The TTM phases were assessed at five times; the e-coach content was adjusted accordingly. Usability was assessed using the System Usability Scale (SUS, Score range: 0-100). Timestamps were used to evaluate how frequently participants used the e-coach: high (≥ 67% of the days), medium (66 - 33% of the days), and low (< 33% of the days). RESULTS: Approximately 140 patients were approached and n = 30 recruited. Complete data sets of n = 21 persons were analysed (38% female, mean age 79.0 ± 6.0 years). The SUS was 78.6 points, 11 participants (42%) were classified as high users, 6 (39%) as medium users and 4 (19%) as low users. After nine weeks, 15 participants (71%) achieved the physical activity recommendations (baseline: 33%, n = 7). Nutrition recommendations were achieved by 14 participants (66%) after nine weeks (baseline: 24%, n = 5). CONCLUSION: The e-coach seems to be usable and feasible for older adults. We identified some optimization potentials for our application that can be transferred to the development of comparable e-health interventions for vulnerable older adults.

Use of electronic devices in leisure time modifies the prevalence and factors associated with sedentary behavior derived exclusively from excessive television viewing among Brazilian adults.

The growing interest in the study of sedentary behavior is justified by its increasing presence in people's daily lives, particularly in leisure time. The aim of this study was to compare the prevalence and factors associated with sedentary behavior derived exclusively from TV time and from its combination with the time spent using other electronic devices among Brazilian adults (n = 52,443). This cross-sectional study used data from the Vigitel survey (2019), which included subjects ≥ 18 years old who resided in the capitals of the 26 Brazilian states and Federal District. High TV time (≥ 4 h/day), and its combination with computer, tablet, or cell phone use (≥ 4 h/day), as well as sociodemographic, behavioral, and health characteristics were self-reported. Adjusted logistic regression was used to estimate odds ratios and 95% confidence intervals (95%CI). The prevalence of high sedentary behavior almost tripled when TV viewing was added to the time spent using other electronic devices (from 12.2%; 95%CI: 11.6; 12.8, to 34.7%; 95%CI: 33.8; 35.6), notably among the youngest (32.0 percentage points). Individuals living without a partner, who smoked, consumed alcohol and processed foods excessively, were physically inactive, and had hypertension were more likely to have both outcomes than their counterparts. Older and less educated individuals were more likely to spend excessive time watching TV and less likely to have high use of other electronic devices in addition to TV viewing than their peers. Including computer, tablet, or cell phone led to an increase in the prevalence of high sedentary behavior. The magnitude and direction of the associations of age and education with high sedentary behavior varied according to the method how high sedentary behavior was defined. Projects, programs, and policies must consider the different indicators of sedentary behavior in monitoring and promoting a healthier lifestyle.

eHealth Technologies for Monitoring Pediatric Asthma at Home: Scoping Review.

BACKGROUND: eHealth monitoring technologies offer opportunities to more objectively assess symptoms when they appear in daily life. Asthma is the most common chronic disease in childhood with an episodic course, requiring close follow-up of pediatric asthma control to identify disease deterioration, prevent exacerbations, and enhance quality of life. eHealth technologies in pediatric asthma care show promising results regarding feasibility, acceptability, and asthma-related health outcomes. However, broad systematic evaluations of eHealth technologies in pediatric asthma are lacking. OBJECTIVE: The objective of this scoping review was to identify the types and applications of eHealth technologies for monitoring and treatment in pediatric asthma and explore which monitoring domains show the most relevance or potential for future research. METHODS: A scoping review was conducted using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A systematic and comprehensive search was performed on English papers that investigated the development, validation, or application of eHealth technologies for home monitoring or treatment of pediatric asthma in the following databases: PubMed, Cochrane Library, IEEE, Scopus, CINAHL, PsycINFO, and ACM Digital Library. Two authors independently assessed eligibility and extracted data. Data were presented by a descriptive analysis of characteristics and a narrative report for each eHealth domain. RESULTS: The review included 370 manuscripts. The following 10 monitoring domains were identified: air quality, airway inflammation markers, lung function, physical activity, sleep, audiovisual, other physiological measurements, questionnaires, medication monitoring, and digital environment (ie, digital platforms, applications, websites, and software tools to monitor or support monitoring). Rising numbers of studies were seen, and the numbers accelerated in the last few years throughout most domains, especially medication monitoring and digital environment. Limited studies (35/370, 9.5%) of multiparameter monitoring strategies, using three or more domains, were found. The number of monitoring validation studies remained stable, while development and intervention studies increased. Intervention outcomes seemed to indicate the noninferiority and potential superiority of eHealth monitoring in pediatric asthma. CONCLUSIONS: This systematic scoping review provides a unique overview of eHealth pediatric asthma monitoring studies, and it revealed that eHealth research takes place throughout different monitoring domains using different approaches. The outcomes of the review showed the potency for efficacy of most monitoring domains (especially the domains of medication monitoring, lung function, and digital environment). Future studies could focus on modifying potentially relevant hospital-based diagnostics for the home setting to investigate potential beneficial effects and focus on combining home-monitoring domains to facilitate multiparameter decision-making and personalized clinical decision support.

Twelve tips for teaching in virtual reality.

Virtual reality (VR) is a technology that is seeing increasing use in medical education as a means to complement or prepare students for clinical practice in a safe space. Whilst effective for learning, it can be difficult to use effectively and requires significant planning to avoid the technological tail wagging the educational dog. We have run educational sessions using the technology to teach anatomy and clinical reasoning that have been well received by students at Queen Mary, University of London. In this article, we share 12 practical tips from our experiences on how to create and deliver learning using VR.

Twelve tips for conducting medical education research via videoconference.

The demand for current practical advice in how to conduct research by videoconference is internationally recognised. Many researchers in medical education are transitioning to using online methods for the first time, through design or necessity. This paper aims to provide practical advice on utilising videoconference technology for research, from design to execution. The tips include how to manage important elements such as ethics approval, online etiquette, contingency planning, technology management, and data capture. Recommendations include how to promote participant engagement with online data collection methods, in some cases paralleling the literature around synchronous online learning. The tried and tested tips have been developed by the authors based on their research experience, a literature review and the results of a post-participation survey of medical students on their experiences engaging in research online via videoconference.

Lessons learnt from a community-driven digital social connection pilot program for people living with dementia: A qualitative interview study with key stakeholders.

INTRODUCTION: In response to COVID-19 and mandated physical distancing, a new digital social connection program was developed and implemented by the local community in a large regional town in western Victoria, Australia. This pilot program, the Digital Inclusion-Social Connections (DI-SC) program, aimed to support people living with dementia to use a digital device to access social connection activities. OBJECTIVE: The objective of this study is to inform the local community implementing the DI-SC program of key stakeholder experience of DI-SC process and outcomes to support future development and potential translation of digital social connections programs for people living with dementia. DESIGN: Three semi-structured focus groups and two interviews were conducted with a total of fifteen participants. Data was transcribed verbatim and thematically analysed. FINDINGS: Three main themes were identified describing factors as influencing the process and outcomes of the DI-SC program: understanding dementia; personal choice and control; and service planning and coordination. Six sub-themes were identified: matching capability; establishing a relationship; creating opportunities for different interactions; ownership of the device, program coordination and defining the volunteer digital mentor role. CONCLUSION: Key stakeholders perceived the DI-SC program as an acceptable way of supporting people living with dementia to engage in activities they found enjoyable promoting social connection with care partners and others. DI-SC program outcomes were impacted by inappropriate training and a lack of program coordination. The findings of this study may inform future development and implementation of digital social connection programs for vulnerable populations at risk of social isolation.