Remote Settings Research Articles

Advances in the recombinase polymerase amplification platform for urogenital schistosomiasis diagnosis (ShDraI-RPA) towards implementation at the point-of-care

Accurate diagnosis of schistosomiasis is crucial to achieve disease elimination as a public health problem. Rapid and highly sensitive diagnostic tools that can be used in decentralized environments and/or at the point-of-care are needed. This work optimises and simplifies an existing isothermal molecular diagnostic platform (recombinase polymerase amplification, RPA) for urogenital schistosomiasis, the ShDraI-RPA, with a focus on delivering a more accurate diagnosis in endemic settings. The standard ShDraI-RPA oligonucleotides were modified, incorporating a phosphorothioate backbone into the reverse primer and inverting the probe fluorophore and quencher, to prevent false positive results due to secondary structure formation. The sensitivity and specificity of the modified assay were evaluated on a donor urine spiked with one S. haematobium egg and an array of other schistosomes and human urinary tract pathogens. The stability of RPA reagents was assessed by storing them at ambient temperature (± 27 °C) in a dark environment for up to 90 days. Sample preparations were explored to develop a simple, rapid and low resource methodology that would complement the ShDraI-RPA platform when used in remote settings. The modified ShDraI-RPA assay was robust, sensitive and specific to S. haematobium group species, detecting down to 10 fg of gDNA and ten synthetic Dra I copies. DNA amplification was achieved at 42 °C within 20 min and results could easily be visualized using a portable fluorometer or under blue light. RPA reagents remained stable when stored in the absence of light at ± 27 °C for up to 30 days. A two-step DNA extraction method proved optimal for extracting DNA from single S. haematobium eggs in spiked urine. The optimized ShDraI-RPA platform shows improved specificity and sensitivity and has now reached several of the target product profile requirements set out by the WHO for the ideal diagnostic test for schistosomiasis.

Evaluation of the Use of Plasma Preparation Tubes for HIV Viral Load Testing in Nigeria.

Routine viral load (VL) monitoring of persons living with HIV (PLWH) on antiretroviral therapy (ART) is imperative for improving the long-term success of treatment. Due to a limited number of PCR laboratories, VL testing is centralized, requiring cold chain storage while transporting samples from remote healthcare centers to referral PCR laboratories, which is a major challenge. The Becton Dickinson (BD) Vacutainer® Plasma Preparation Tube (PPT) was designed to mitigate cold chain transport needs and secondary tube storage of plasma. This cross-sectional study assessed the suitability of PPTs for sample transportation in remote settings, in place of EDTA non-gel Vacutainers, eliminating the need for cold chain storage. Venous blood was collected from 115 PLWH into 3 Vacutainer tubes (1 EDTA and 2 PPT). The plasma obtained from the first PPT was assayed for HIV VL along with the plasma obtained from EDTA non-gel Vacutainer within 6 h on the COBAS 6800 (Roche Diagnostics) instrument. Samples from the second PPT were stored at room temperature (20 to 28°C) for 24 h before testing on the same instrument. The Wilcoxon signed rank test and W statistic (P value 0.91) showed that VL results obtained from the EDTA were comparable to the PPT on the collection day, and after 24 h at room temperature. Sensitivity and specificity for same-day and 24-hour testing were both 100%. The BD Vacutainer PPT was shown to have similar VL results to the EDTA non-gel Vacutainer, and can therefore be deployed to remote settings for sample collection and transportation to PCR referral laboratories.

Remote Collaboration Hub

With its integrated project management, communication, and secure file sharing facilities, the Remote Collaboration Hub offers a one-stop platform designed specifically for remote teams, facilitating effective cross-border cooperation. Businesses are adopting platforms that promote productivity, optimize workflows, and guarantee data security as a result of the growing demand for strong digital collaboration solutions brought on by remote work. This study examines how well a remote collaboration hub may improve the performance of remote teams, with a particular emphasis on how it affects information sharing, task management, and real-time communication. We examine the benefits and drawbacks of remote collaboration hubs by thoroughly examining current solutions and case studies, tackling important issues including data protection, platform flexibility, and digital overload. We also look at new developments that could make these hubs even more effective tools for remote workers, such as AI-powered task automation, customized user interfaces, and improvements to data integration. The study's conclusions offer useful information and suggestions for businesses looking to set up or enhance a remote collaboration hub in order to satisfy the changing needs of contemporary remote work settings.

Adaptive Differential Privacy in Federated Edge AI for Medical IoT: Energy-Efficient, HIPAA-Compliant Frameworks for Distributed Real-Time Diagnostics

The rapid growth of Medical Internet of Things devices, such as wearable heart monitors, smart insulin pumps, and remote patient monitoring systems, has transformed healthcare by enabling real-time diagnostics and personalized treatment. However, the sensitive nature of healthcare data and the limited resources of these devices create significant challenges in ensuring data privacy, meeting regulatory requirements, and maintaining energy efficiency. Traditional cloud-based artificial intelligence solutions often fail to address these challenges because they require centralized data storage, which increases the risk of privacy breaches and violates regulations like the Health Insurance Portability and Accountability Act and the General Data Protection Regulation. To overcome these limitations, this paper proposes a novel framework that combines adaptive differential privacy with federated edge artificial intelligence to enable secure, distributed learning across medical Internet of Things networks. Consider a scenario where a hospital uses wearable heart monitors to detect irregular heartbeats in patients. These devices collect sensitive health data, which is sent to a central server for analysis. However, this centralized approach poses a risk: if the server is hacked, patient data could be exposed, leading to privacy violations and legal penalties. Additionally, the constant transmission of data to the cloud drains the battery life of the wearable devices, making them less practical for long-term use. Our framework addresses these issues by enabling the wearable devices to analyze data locally, without sending it to a central server. This not only protects patient privacy but also reduces energy consumption, extending the battery life of the devices. Our framework introduces adaptive differential privacy mechanisms that dynamically adjust the level of noise added to data based on the sensitivity of the information and the capabilities of the medical Internet of Things devices. For example, data from a cancer monitoring device would require stronger privacy protections compared to data from a fitness tracker. This ensures compliance with privacy regulations while maintaining high diagnostic accuracy. Additionally, we propose a hierarchical federated learning architecture where edge servers act as intermediaries between medical Internet of Things devices and a central server. This reduces communication overhead and enables real-time diagnostics with sub-100-millisecond latency, critical for applications like irregular heartbeat detection in wearable heart monitors. To address the energy constraints of medical Internet of Things devices, we implement lightweight lattice-based homomorphic encryption for secure model aggregation. This approach allows computations to be performed on encrypted data, ensuring privacy without requiring significant computational resources. Our experiments show that this method reduces energy consumption by 40 percent compared to traditional federated learning frameworks, making it suitable for battery-powered devices like smart insulin pumps and wearable sensors. We validate our framework using the Wearable Stress and Affect Detection dataset and synthetic heart data generated using generative adversarial networks. The results demonstrate robust performance in detecting medical anomalies, such as irregular heartbeats, while effectively resisting privacy attacks like membership inference. A case study on smart insulin pumps further highlights the practicality of our approach. By training low blood sugar prediction models across 10,000 devices in a federated manner, we achieved 92 percent diagnostic accuracy while blocking 99 percent of privacy attacks. This work bridges the gap between privacy-preserving artificial intelligence and edge computing, offering a scalable, energy-efficient solution for next-generation medical Internet of Things applications. By aligning with emerging standards like the National Institute of Standards and Technology’s Privacy Framework and the European Telecommunications Standards Institute’s edge artificial intelligence specifications, our framework sets a new benchmark for secure, real-time healthcare diagnostics. It also addresses ethical concerns by ensuring that artificial intelligence models are transparent and explainable, fostering trust among healthcare providers and patients. In conclusion, our framework provides a comprehensive solution to the challenges of privacy, compliance, and energy efficiency in medical Internet of Things networks. It enables secure, real-time diagnostics while ensuring that sensitive patient data remains private and protected. This research has significant implications for the future of healthcare, paving the way for widespread adoption of medical Internet of Things devices in clinical and remote settings. By integrating cutting-edge technologies like adaptive differential privacy, federated learning, and edge artificial intelligence, we offer a robust and scalable approach to transforming healthcare delivery.

The impact of adolescent innovation on academic resilience, distance learning self-efficacy, and academic performance

The COVID-19 pandemic introduced considerable challenges for adolescents as they adapted to the demands of remote learning, necessitating effective strategies to sustain their academic engagement and performance. This study investigates the relationship between adolescents’ self-perceived innovativeness and their academic resilience, confidence in managing distance learning, and overall academic performance. Using data from a sample of 906 Chinese middle and high school students, the study identifies three primary findings: adolescents with higher levels of self-perceived innovativeness tend to exhibit stronger academic resilience, greater confidence in handling distance learning, and better academic performance; distinct gender differences emerge, with male students reporting higher levels of self-perceived innovativeness than their female counterparts; and differences across educational stages are also evident, as high school students generally rate their innovativeness higher than middle school students. These findings point to the significance of fostering innovative thinking skills in adolescents to strengthen their capacity for adapting to dynamic educational environments and achieving improved academic outcomes. For educators and policymakers, the focus should be on encouraging creativity and adaptability among students while providing them with the necessary tools and support to develop personalized approaches for success in both blended and remote learning settings.

TAME Pain data release: using audio signals to characterize pain

Accurately assessing pain through speech remains a challenge in medical practice, with profound implications for patient care and patient health outcomes. The TAME Pain dataset addresses this challenge by providing a comprehensive dataset that captures the relationship between induced acute pain and speech in adults. Utilizing the Cold Pressor Task (CPT) method to induce pain, we recorded over 7,000 utterances from 51 participants, correlating their self-reported pain levels with vocal cues. This dataset stands as the largest of its kind to date and includes comprehensive annotations detailing background noise, speech errors, and non-speech vocal features, maximizing its utility for in-depth audio analysis. Our dataset is designed to support the development of reliable, non-invasive pain assessment technologies, particularly in telemedicine and remote healthcare settings. By releasing these data, we aim to facilitate interdisciplinary research in psychology, medical science, and AI, fostering innovations that can enhance pain management practices and improve patient outcomes across diverse clinical environments.

Trap evaluation to optimize wild pig removal efforts in remote settings

Context Invasive wild pigs (Sus scrofa) are the most abundant, widespread, and economically significant large vertebrate established in the Hawaiian Islands. Owing to their generalist diet and rooting behavior, wild pigs alter soils and watersheds, negatively affecting native biota. Aims Lethal removal of wild pigs by trapping is often the most effective and practical management action to reduce their impacts, but terrain and access are challenging. Methods We compared the effectiveness and efficiency of three trap designs (i.e. corral, box, and passive net traps) on a fenced population of wild pigs in a remote montane forest setting on the Island of Hawai‘i, where use of cellular-activated ‘smart’ traps was not possible. Key results During three high-intensity removal efforts between 30 November 2021 and 8 May 2022, we trapped and euthanized 435 wild pigs through 162 trapping events. Although each trap type effectively captured wild pigs, passive net traps captured more wild pigs per capture event than did corral and box traps. Specifically, when using passive net traps, we captured approximately four wild pigs per capture event, which was two to three times more than with corral traps and box traps respectively. Passive net traps were more effective and efficient than were box traps, although they performed similarly to corral traps. Conclusions All trap types we tested successfully captured wild pigs, but passive net traps typically captured more wild pigs per event than did traditional corral and box traps. Net traps were a valuable addition to remote trapping strategies. Implications In remote and rugged settings where smart trapping technology cannot be used, we recommend incorporating passive net traps into a trapping program to optimize removal of wild pigs.

AI in biomedical science: innovations, challenges, and ethical perspectives

Artificial intelligence (AI) increasingly influences biomedical scientific writing and clinical practice. The recent article by Fornalik et al. (Explor Digit Health Technol. 2024;2:235–48. doi: 10.37349/edht.2024.00024) explores AI’s capabilities, challenges, and ethical considerations in scientific communication, particularly highlighting tools like ChatGPT and Penelope.ai. This commentary aims to reflect on and expand the key themes presented by Fornalik et al. (Explor Digit Health Technol. 2024;2:235–48. doi: 10.37349/edht.2024.00024), emphasizing AI’s role in auditory healthcare, particularly in otolaryngology and auditory rehabilitation. The discussion is based on a critical review and synthesis of recent literature on AI applications in scientific writing and auditory healthcare. Key technologies such as generative AI platforms, machine learning algorithms, and mobile-based auditory training systems are highlighted. AI has shown promising results in enhancing manuscript preparation, literature synthesis, and peer review workflows. In clinical practice, adaptive AI models have improved cochlear implant programming, leading to up to 30% gains in speech perception accuracy. Mobile apps and telehealth platforms using AI have also improved listening effort, communication confidence, and access to care in remote settings. However, limitations include data privacy concerns, lack of population diversity in datasets, and the need for clinician oversight. AI presents transformative opportunities across biomedical science and healthcare. To ensure its responsible use, interdisciplinary collaboration among clinicians, researchers, ethicists, and technologists is essential. Such collaboration can help develop ethical frameworks that enhance innovation while safeguarding patient well-being and scientific integrity.

Enhanced Laser-Induced Graphene Microfluidic Integrated Sensors (LIGMIS) for On-Site Biomedical and Environmental Monitoring.

The convergence of microfluidic and electrochemical biosensor technologies offers significant potential for rapid, in-field diagnostics in biomedical and environmental applications. Traditional systems face challenges in cost, scalability, and operational complexity, especially in remote settings. Addressing these issues, laser-induced graphene microfluidic integrated sensors (LIGMIS) are presented as an innovative platform that integrates microfluidics and electrochemical sensors both comprised of laser-induced graphene. This study advances the LIGMIS concept by resolving issues of uneven fluid transport, increased hydrophobicity during storage, and sensor biofunctionalization challenges. Key innovations include Y-shaped reservoirs for consistent fluid flow, hydrophilic polyethyleneimine coatings to maintain wettability, and separable microfluidic and electrochemical components enabling isolated electrode nanoparticle metallization and biofunctionalization. Multiplexed electrochemical detection of the neonicotinoid imidacloprid and nitrate ions in environmental water samples yields detection limits of 707nm and 10-5.4m with wide sensing ranges of 5-100µm and 10-5-10-1m, respectively. Similarly, uric acid and calcium ions are detected in saliva, demonstrating detection limits of 217nm and 10-5.3m with sensing ranges of 10-50µm, and 10-5-10-2.5m, respectively. Overall, this biosensing demonstrates the capability of the LIGMIS platform for multiplexed detection in biologically complex solutions, with applications in environmental water quality monitoring and oral cancer screening.

Remote work, Job Quality and Work-life Balance: A Comparative Study of European Men and Women

The rapid growth of remote work, accelerated by the COVID-19 pandemic, has sparked increased interest in its effects on job quality and work-life balance. This study examines the role of job quality for work-life balance of European men and women when working remotely. While remote work offers benefits such as enhanced flexibility and autonomy, it also presents challenges including social isolation and stress management. Research indicates that these effects are not gender-neutral, with women often experiencing disproportionate challenges despite potential improvements in work-life balance. This study employs a quantitative approach, utilizing data from the 2021 European Working Conditions Survey, with a sample of over 70,000 European workers. Through multi-group analysis and Partial Least Square method, the research investigates gender differences in job quality and work-life balance in remote work settings. The study aims to contribute to the understanding of how remote work influences job quality and work-life balance, with a particular focus on gender disparities. Findings will provide insights for developing equitable remote work policies and practices.

Leadership and trust in virtual teams

Background Advances in technology and the COVID-19 pandemic have led to increased use of remote work arrangements. Yet, research studies have examined the role of trust between leaders and employees in remote working conditions, despite the general relevance of trust to collaboration. Objective Here, we aim to investigate the specifics of remote working arrangements with a focus on the concept of leadership and trust in remote settings as opposed to classical teams. Methods For this purpose, expert interviews were conducted with representatives from the automobile, pharmaceutical, and financial services industries which have been contacted for that purpose. Results The expert interviews have clearly shown that differences exist between presence and remote conditions, while there is a realm of determinants which can influence remote team performance. Leadership plays an important role in the functioning of remote teams, including creating conditions that can help build trust. Conclusions Due to the increased importance of remote working, leadership must take necessary steps to provide optimal conditions so that organizations and employees can benefit from remote working. That requires a careful approach which does consider the specific determinants and the environments that characterize the organization.

Epidemiology of Tick-Borne Diseases Among the Shepherd Community Along the Pak Baloch–Afghan Border

Background: Tick-borne diseases such as anaplasmosis and babesiosis represent emerging zoonotic threats in rural and borderland regions with limited surveillance, particularly among shepherd communities along the Pak Baloch–Afghan border. Despite increasing recognition globally, regional data on epidemiology, risk factors, and clinical burden remain scarce, hindering effective prevention and response strategies. Objective: This study aimed to investigate the epidemiological characteristics, occupational and environmental risk factors, and clinical outcomes of anaplasmosis and babesiosis among high-risk populations, with the goal of informing targeted interventions and integrated public health strategies. Methods: A cross-sectional observational study was conducted among high-risk individuals (n = 225) including shepherds, livestock handlers, butchers, and rural health workers. Participants aged 18–55 years were enrolled based on defined exposure criteria; individuals with prior confirmed infection were excluded. Data were collected via structured surveys, interviews, and laboratory diagnostics (PCR and ELISA) for Anaplasma phagocytophilum and Babesia microti. Statistical analyses including Chi-square and logistic regression were performed using SPSS v27 to identify significant associations (p < 0.05). The study received ethical approval from institutional review boards in both countries and adhered to the Helsinki Declaration. Results: Out of 225 suspected cases, 73 (33%) were confirmed for anaplasmosis and 72 (32%) for babesiosis. Males aged 20–50 years represented 86% of confirmed cases. Occupational exposure (OR = 4.2), male gender (OR = 3.5), and history of tick bites (OR = 2.8) were significantly associated with disease occurrence (p < 0.05). Spring and summer were peak transmission seasons. Immunocompromised individuals exhibited more severe symptoms, reinforcing the need for timely diagnosis and tailored care in remote settings. Conclusion: The study demonstrates a high prevalence of tick-borne diseases among occupational groups in the Baloch–Afghan borderlands, driven by vector exposure, environmental conditions, and limited protective practices. These findings underscore the importance of early detection, targeted awareness campaigns, and a One Health approach integrating human and animal health strategies to reduce disease burden in endemic rural areas.

Linking Household and Service Provisioning Assessments to Estimate a Metric of Effective Health Coverage: A Metric for Monitoring Universal Health Coverage

Background: The framework of measuring effective coverage is conceptually straightforward, yet translation into a single metric is quite intractable. An estimation of a metric linking need, access, utilization, and service quality is imperative for measuring the progress towards Universal Health Coverage. A coverage metric obtained from a household survey alone is not succinct as it only captures the service contact which cannot be considered as actual service delivery as it ignores the comprehensive assessment of provider–client interaction. The study was thus conducted to estimate a one-composite metric of effective coverage by linking varied datasets. Methods: The study was conducted in a rural, remote, and fragile setting in India. Tools encompassing a household survey, health facility assessment, and patient exit survey were administered to ascertain measures of contact coverage and quality. A gamut of techniques linking the varied surveys were employed such as (a) exact match linking and (b) ecological linking using GIS approaches via administrative boundaries, Euclidean buffers, travel time grid, and Kernel density estimates. A composite metric of effective coverage was estimated using linked datasets, adjusting for structural and process quality estimates. Further, the horizontal inequities in effective coverage were computed using Erreygers’ concentration index. The concordance between linkage approaches were examined using Wald tests and Lin’s concordance correlation. Results: A significantly steep decline in measurement estimates was found from crude coverage to effective coverage for an entire slew of linking approaches. The drop was more exacerbated for structural-quality-adjusted measures vis-à-vis process-quality-adjusted measures. Overall, the estimates for effective coverage and inequity-adjusted effective coverage were 36.4% and 33.3%, respectively. The composite metric of effective coverage was lowest for postnatal care (10.1%) and highest for immunization care (78.7%). A significant absolute deflection ranging from −2.1 to −5.5 for structural quality and −1.9 to −8.9 for process quality was exhibited between exact match linking and ecological linking. Conclusions: Poor quality of care was divulged as a major factor of decline in coverage. Policy recommendations such as bolstering the quality via the effective implementation of government flagship programs along with initiatives such as integrated incentive schemes to attract and retain workforce and community-based monitoring are suggested.

Remote working and heavy work investment across employee fulfillment-crafting profiles

PurposeThis study aims to examine how the relationship between remote work intensity and heavy work investment varies across employee profiles defined by job crafting behaviors and work-related basic need satisfaction. By integrating self-determination theory and job crafting, we provide a nuanced understanding of how remote work shapes both work engagement and workaholism.Design/methodology/approachUsing latent profile analysis on a sample of 727 employees, we identified distinct fulfillment-crafting profiles based on job crafting strategies and psychological need satisfaction. We then analyzed how remote work intensity relates to work engagement and workaholism across these profiles.FindingsThree profiles emerged: satisfied proactive, challenged optimizers and dissatisfied reactive. The relationship between remote work intensity and heavy work investment varied across these profiles. For satisfied proactive employees, higher remote work intensity was linked to lower work engagement, suggesting that these employees may rely on in-person work environments for motivation. Challenged optimizers showed a more complex pattern: cognitive workaholism initially declined with increasing remote work intensity but then increased once it exceeded a certain threshold, while behavioral workaholism was linearly negatively associated with remote work intensity. Dissatisfied reactive employees exhibited a curvilinear relationship between remote work intensity and cognitive workaholism, initially increasing with remote work intensity before declining, whereas behavioral workaholism steadily increased with higher remote work intensity, indicating potential maladaptive coping mechanisms.Originality/valueThis study extends remote work and job crafting research by highlighting how individual differences in proactive job redesign and need satisfaction shape remote work experiences. Our findings underscore the need for tailored organizational strategies that enhance need satisfaction and promote job crafting behaviors to mitigate risks associated with heavy work investment in remote settings.

Aboriginal young people's experiences of type 2 diabetes diagnosis, management and support: A qualitative study in the Kimberley region of Western Australia.

In Australia, Aboriginal and Torres Strait Islander young people in remote settings are most-affected by young onset type 2 diabetes (T2D). It is necessary to understand young people's experiences, including factors impacting on self-management, to improve models of care. A phenomenological methodology underpinned this qualitative study in Western Australia's Kimberley region. Two Aboriginal Community Controlled Health Services supported recruitment of seven Aboriginal young people aged 12-24 with T2D, who participated in interviews. A carer and health professional of one young person in each site were also interviewed and relevant medical record data reviewed to assist with triangulation of data. De-identified transcripts were inductively coded and a coding structure developed with oversight by a Kimberley Aboriginal researcher. Young people reported varied experiences and emotions relating to a T2D diagnosis. Most recounted this was upsetting and some reported current negative impact on emotional wellbeing. Challenges with understanding and managing diabetes were highlighted, particularly regarding healthy eating, physical activity and medication. Family are a prominent source of self-management support, with the intergenerational impact of diabetes being evident for each participant. Positive relationships with health professionals, entailing continuity of care, were valued. There are significant emotional and medical challenges for young people with T2D and their families. Recommendations from this work will contribute to the development of local resources and initiatives to improve diabetes-related support. SO WHAT?: Alongside broader efforts to support good health at the societal level, enhanced health education and family-oriented support structures including Aboriginal clinical staff for young people with T2D are needed.

Implementation of a best-practice model of care for cognitive impairment and dementia for first nations peoples attending primary care in Australia: a stepped-wedge cluster-randomised trial.

Implementation of a best-practice model of care for cognitive impairment and dementia for first nations peoples attending primary care in Australia: a stepped-wedge cluster-randomised trial.

Oombarl Oombarl Joorrinygor-Slowly Slowly Moving Forward: Reflections From a Cross-Cultural Team Working Together on the See, Treat, Prevent (SToP) Trial in the Kimberley Region of Western Australia.

Reflexivity is crucial for researchers and health professionals working within Aboriginal health. Reflexivity provides a tool for non-Aboriginal researchers to contribute to the broader intention of reframing historical academic positivist paradigms into Indigenous research methodologies (IRM) to privilege Aboriginal voices in knowledge construction and decision-making. This practice requires researchers to transition from safe and familiar research environments into unfamiliar and uncomfortable spaces. This uncomfortable space is often referred to as the 'third space'-the 'in-between' space that can be turbulent and difficult to navigate. However, it is also a productive space where new collaborations are created, and ideas can emerge. This manuscript provides reflections from a cross-cultural team working on a transdisciplinary healthy skin program-the See, Treat, Prevent (SToP) Trial in Aboriginal communities in the Kimberley region of Western Australia (WA). Cultural mentors guided our team to work in an Oombarl Oombarl (steady steady) way to navigate the cultural interface between familiar biomedical elements and unknown health promotion activities. Our third space was the intangible space in-between the S, T and P of the SToP Trial. Narratives were collected through semi-structured interviews and yarning sessions. All participants provided written consent for audio recording; in one instance, consent was provided to record graphically. A thematic analysis aligning with the question guide was conducted. Reflections include team members' experiences of learning the Oombarl Oombarl way, individually and collectively. Initially, most team members revealed it was challenging to work in an Oombarl Oombarl way, having to move out of the safe, familiar research environment into the unknown community-led health promotion space. This in-between space became our third space-the uncomfortable space where we relinquished 'control' of research agendas and learnt to work to the rhythm of Aboriginal communities in WA's Kimberley region. Reflexivity is necessary when working in a cross-cultural context. In Aboriginal homeland communities situated in remote settings, researchers benefit from being 'on the ground' to enable trust and genuine relationships to be developed. Visits on Country provide a rich experiential learning experience and a space for story sharing and yarning. Cultural guidance and two-way learning partnerships with cultural mentors assist non-Aboriginal researchers in understanding and adhering to cultural protocols and community processes. Allowing sufficient time to build relationships and flexible timelines are important considerations when developing research grants and protocols. SO WHAT?: Our findings demonstrate the importance of building genuine relationships and yarning on Country with Aboriginal communities to build health promotion knowledge together. Making meaning of health literacy can only evolve through two-way learning partnerships where Aboriginal people guide the process. Our research reveals a novel approach to developing meaningful health promotion initiatives and resources on Country that centralise local Aboriginal language, artwork and community context.

Implementation of A New, Mobile Diabetic Retinopathy Screening Model Incorporating Artificial Intelligence in Remote Western Australia.

Diabetic retinopathy (DR) screening rates are poor in remote Western Australia where communities rely on outdated primary care-based retinal cameras. Deep learning systems (DLS) may improve access to screening, however, require validation in real-world settings. This study describes and evaluates the implementation of a new, mobile DR screening model that incorporates artificial intelligence (AI) into routine care. Prospective, population-based study. The model was co-designed with local Aboriginal communities and implemented in the remote, Pilbara region of Western Australia. A research officer without formal healthcare qualification performed retinal screening aboard a Mercedes Sprinter Van using an automated retinal camera with integrated AI diagnostics. Patients received their diagnosis on-the-spot and completed an evaluation survey. A remote clinician provided supervision and on-the-spot telehealth consultation for referable disease. People with diabetes from the Pilbara region. Number of people screened, acceptability of AI to patients. From February to August 2024, DR screening was provided to 9 communities across the Pilbara region. 78 patients provided research consent, of which 56.4% were Aboriginal or Torres Strait Islanders. 10.3% of retinal photos had referable DR and 8.4% of photos were ungradable. 96% of patients were 'Happy with the use of AI'. Our new model for AI-assisted DR screening was culturally safe, acceptable to patients and effective, demonstrating an 11-fold increase in screening rates compared to 2023 Pilbara data. In remote Australian settings, AI-assisted DR screening may overcome historical barriers to service provision and improve minimisation of preventable blindness.

Navigating hybrid remote data collection methods (RDCM) in co-design with older adults: exploring roles, opportunities, and trade-offs

ABSTRACT Interest in remote data collection methods (RDCM) for co-design research has grown recently, accelerated by the COVID-19 pandemic’s restrictions on traditional in-person practices. Existing RDCM, which rely heavily on Internet access, often exclude marginalised groups like older people and primarily collect textual or verbal data. This paper explores enhancing RDCM’s inclusiveness and diversity of data collected in co-design by examining findings from a remote project that actively engaged older adults as co-designers to address later-life loneliness, using a hybrid approach of online sessions and tangible toolkits. The findings reveal the intertwining relationship between RDCM and co-design, identifying two types of data collected: outcomes-focused and process data. The hybrid RDCM effectively expand geographical and demographic inclusiveness, enabling older adults with limited digital skills to fully participate and collect diverse data, including tangible and non-textual forms. However, the findings indicate trade-offs, such as the exclusion of reluctant older Internet users and progress at a cost in terms of additional time, effort, and resources. This paper contributes significantly to RDCM research in co-design contexts and lays foundational insights for future research aimed at increasing democratic inclusiveness in remote co-design settings and diversifying data collection.

Artificial Intelligence-Driven Vision Therapy for Cerebral Visual Impairment in Remote Settings: A Three-Year Follow-Up Case Report

Cerebral visual impairment (CVI) is a neuro developmental disorder that affects the brain's visual processing centres. It is typically associated with perinatal hypoxia, traumatic brain injury, infections, and genetic disorders. Artificial Intelligence in vision therapy can revolutionize optometric treatment. We describe a case of AI-powered vision treatment of a patient diagnosed with CVI in a remote region. AI powered remote vision therapy was provided to a 4-year-old male with CVI in the Indian state of Himachal Pradesh. The 14-week therapy was monitored and altered using AI findings. The patient was followed up with continued home therapy. The findings were monitored on a quarterly basis.After 14 weeks of distant vision therapy, visual acuity, contrast sensitivity, and oculomotor function improved significantly, and a consistent improvement was noticed. Artificial Intelligence powered vision treatment technologies have the potential to enhance optometry care equity.