JMIRx Med

AbstractAccurate health information is ineffective if patients cannot understand it. Large Language Model (LLM) health research values veridical precision; however, linguistic accessibility remains an under-examined component of output quality and usability. This study investigated two sources of variability in readability classification: differences across LLM systems and across readability metrics. The analysis tested 1,120 data points from seven systems in English and Portuguese, comparing baseline responses with a Wikipedia-grounded condition. Content was assessed using five standard readability metrics that measure distinct aspects of text complexity. Systems were statistically homogeneous at baseline but became significantly heterogeneous under Wikipedia grounding, indicating variability in the combination of Retrieval-Augmented Generation (differential readability effects of the same source-grounding instruction across systems). Significant metric variability was observed in all conditions, showing that readability metrics are not interchangeable. Although retrieval grounding is commonly used to improve accuracy, our findings show a trade-off: verified-source grounding can yield inconsistent readability. Therefore, evaluation protocols should use transparent, vendor-agnostic criteria, with metric-specific and language-aware thresholds, and be applied whenever models or grounding configurations change to support accessible cross-language health communication.

Background: The urgent care departments in Europe face a structural paradox: accelerating digitalisation is accompanied by a patient population that is disproportionately unable to engage with standard digital tools. An internal analysis at the Emergency Department (Akutafdelingen) of Nordsjaellands Hospital in Hilleroed, Denmark found that 43% of emergency patients struggle with digital solutions - a figure that reflects the predictable composition of acute care populations rather than any individual failing. Objective: This paper presents the design, iterative development, and secondary validation of the ED Adaptive Interface (v5): a prototype adaptive patient terminal developed in response to this challenge. The system operationalises what the author terms impairment-first design - a methodology that treats the most constrained patient experience as the primary design problem and derives the standard experience as a subset. The interface configures itself in under ten seconds via nurse-led setup, adapting across four axes of impairment: visual, motor, speech, and cognitive. System: Version 4 supports five accessibility modes, a heatmap pain assessment grid, a Privacy and Dignity panel, a live workflow tracker with care notifications, structured dual-category help requests, and plain-language medical term definitions across four languages. Version 5, reported here for the first time, introduces a Condition Worsening Escalation button, a Referral Pathway Display, a "Why Am I Waiting?" triage explainer, a Symptom Progression Log, MinSP/Yellow Card Scan simulation, expanded language support (seven languages: English, Danish, Arabic with full RTL layout, Turkish, Romanian, Polish, and Somali), and an expanded ten-item Communication Board. The entire system runs as a single 79-kilobyte HTML file with zero infrastructure requirements. Methods: To base the design on patient-generated evidence, two independent social media threads were subjected to an inductive thematic analysis (Braun and Clarke, 2006): a primary corpus of 83 entries in the Facebook group Foreigners in Denmark (collected March 2026) and a corroborating corpus in an international community group in the Aarhus region (collected April 2026). All identifiers in both datasets were fully anonymised under GDPR Article 89 research provisions prior to analysis. No participants were contacted. Generative AI tools were used to assist with drafting, writing, and prototype code development; all scientific content, data collection, analysis, and conclusions are the sole responsibility of the authors. Results: The first discourse corpus produced five major themes corresponding to the five problem areas the prototype was designed to address: system navigation and triage literacy gaps (31 entries); language and cultural barriers (6 entries); communication failures during care (5 entries); staff overload and capacity constraints (8 entries); and pain and severity assessment failures (14 entries). The corroborating dataset supported all five themes and introduced two additional themes: differential treatment of international patients and medical gaslighting as a long-term pattern of patient advocacy failure. One structural finding - the five most-liked comments incorrectly criticised the original poster for self-referring when she had received explicit 1813 telephone triage approval - directly inspired the Referral Pathway Display and "Why Am I Waiting?" features in v5. Conclusions: The convergence of design rationale and independent social evidence across all five problem categories suggests that impairment-first design is not a niche accessibility concern but a structural approach to healthcare interface quality. The prototype is ready for a structured clinical pilot using the System Usability Scale (SUS) and semi-structured staff interviews. The long-term roadmap includes full MinSP integration, hospital PMS connectivity, and clinical validation.

Electronic Health Records (EHRs) have not been widely implemented in mental health settings, representing a significant gap in digital health care transformation. A reason for underutilisation includes concerns from healthcare professionals regarding the collection and storage of patients sensitive information. Language use can positively influence clinician-patient relationships, and stigmatising language in EHRs viewed by patients could undermine trust. This is concerning as using EHRs have benefits which allow patients to feel safe and empowered regarding their care. Moreover, minority ethnic groups have been found to disengage with EHRs and are more likely to access mental health services through crisis pathways. This qualitative study in collaboration with Bradford District Care NHS Foundation Trust comprises two stages to explore minority ethnic perspectives on mental health EHRs and develop recommendations for their implementation. Stage one investigates minority ethnic service users perceptions on EHRs and explores mental health professionals understanding regarding the sharing of EHRs with service users from minority ethnic groups. The workshops in stage two will use an Experience-Based Co-Design approach to produce practical recommendations for EHR implementation in mental health settings. Participants include minority ethnic service users, mental health professionals, stakeholders, and relevant bodies such as mental health organisations and Information Technology experts utilising EHRs. Data will be gathered through semi-structured interviews, focus groups and workshops, and analysed using reflexive thematic analysis. The study was approved under the Integrated Research Application System (IRAS ID: 348764) and Health Research Authority and Health and Care Research Wales. Findings will be disseminated via social media, blogs, conferences, journals, academic articles, and community and staff meetings held by the Trust. An executive summary will be shared with participants who consented to receive the results.

Abstract: Background: Vascular access is essential in treating patients undergoing prolonged endovenous therapy such as chemotherapy, antibiotics, and parenteral nutrition. Since the 1990s, when PICCs (peripherally inserted central catheters) appeared, vascular access options have expanded significantly, revolutionizing the treatment landscape for all types of patients. Objective: To analyze and describe the profile of the use of PICCs in a Brazilian quaternary hospital over 10 years with data collected by the infusion therapy team. Evaluating the number of PICCs implanted over the years, patients epidemiology and clinical characteristics, insertion details, associated complications, and the reason for removal. Methods: A retrospective cohort study that employs a quantitative, non-experimental approach to classify and statistically analyze past events associated with 21,652 PICCs implanted from January 2012 to December 2021 in a quaternary hospital at Sao Paulo - Brazil. All the catheters were implanted, and the data was collected by a team of nurses specializing in infusion therapy. We analyzed the number of catheters implanted over the years, insertion characteristics, patients epidemiology and clinical data, possible associated complications, and the reason for removal. Statistical analyses were conducted using R software (version 4.4.1) and SPSS (version 29) for Windows (IBM Corp, Armonk, NY). Results: During the specified period, 21,652 catheters were analyzed. The patients gender distribution was nearly balanced (48.2% versus 51.8%), and the average age was 66 years. Cardiovascular and metabolic issues were the most common comorbidities, and between 2020 and 2021, 29.3% of the sample tested positive for COVID-19. The most common location of hospitalization and implantation was the medical-surgical clinic (31.6% - 41.4%), and the most used type of catheter was the Power Picc (83.9%). The estimated complication incidence density is 2.94 complications per 1,000 catheter-days. Almost all the PICCs (98,2%) were adequately located at the cavo-atrial junction after the first attempt, 82.2% of catheters were removed after therapy, and the median duration of catheter use was 12 days. Conclusion: PICCs are widely employed for drug infusion, with their use growing progressively due to specialized teams greater availability and training. The high efficiency of these devices with a relatively low risk of complications already observed in previous studies was reinforced by the findings of this study of more than 20,000 catheters.

IntroductionThe Southeastern region of Nigeria faces a severe public health challenge from hypertension due to its high prevalence. Psychological factors such as stress, anxiety, depression, coping mechanisms, and social support play essential roles in hypertension development and treatment, yet there has been limited scholarly attention to these factors in Nigerian and international qualitative research. This study addresses this evidence gap by investigating the psychological factors that influence hypertension development in adults living in Southeastern Nigeria. Materials and methodsThe sequential explanatory mixed methods study includes validated psychometric instruments assessing perceived stress, anxiety, depression, coping mechanisms, and social support. Regression analyses, correlation tests, and mediation/moderation models will be used to examine relationships among these variables. The research team will collect qualitative data through semi-structured interviews accessible to participants either online or in person. Thematic analysis following Braun and Clarkes six-phase framework will be employed to explore participants lived experiences of stress, coping, and hypertension management. Ethics and disseminationEthical approval was obtained from the University of Bradford Research Ethics Committee on 7th August 2025. The research follows all procedures based on the Declaration of Helsinki and institutional ethical guidelines. Findings will be disseminated at academic conferences and published in peer-reviewed journals and stakeholder meetings held in both the UK and Nigeria. The research aims to generate evidence to support the development of comprehensive psychosocial care plans that address both physical and mental aspects of hypertension treatment in areas with limited resources.

1.AI is already finding its way into the diagnostic radiology realm of various regions around the world, but there is still a lack of evidence on the situation in LMICs. This qualitative study examined the research problem through the perspectives of clinicians regarding the adoption of AI-Radiology in Karachi, Pakistan, using the Technology Acceptance Model and interpreting the results into practice and policy using the Problem Driven Iteration Adaptation lens. 13 clinicians (radiologists, tertiary care hospitals) were interviewed between May and August 2025. The semi structured interviews were audio recorded, transcribed and coded in NVivo 14. TAM constructs of perceived usefulness and perceived ease of use were analyzed in a deductive content analysis, and interpretation of implementation pathways was informed by PDIA. Four themes emerged. Implementation attitudes were realistic optimism. The subjects put AI in terms of an assistant and second reader, and clinical judgment and accountability could not be delegated. Issues centered on privacy of data, and over dependence. Perceived ease of use was based on training, infrastructure, fit in workflow and trust. Costs, poor connectivity, the lack of institutional capacity, and generational resistance were the barriers whereas triage acceleration, mass screening support, workload reduction, and time saving were the facilitators. For adoption, education, practical upskilling, guidelines, and local clinical approval were requirements. The greatest perceived usefulness was in situations where AI was applied to specific bottlenecks like quick screening, quantitative measurements, remote-area reporting, and trainees decision support; the constraints included data quality, generalizability, and algorithm error, the risk of confidentiality, and the impossibility to substitute contextual clinical reasoning. Such priorities as national and institutional data protection policies, formal vetting of tools, smooth integration with radiology information systems and AI literacy in the curriculum were included. The sample is limited to one city and the qualitative design does not enhance generalizability but the results provide practical recommendations. The mixed resource setting of Karachi is a potential place where AI can be a reliable collaborator in the field of radiology in case of adequate infrastructure and training of clinicians and a long-term human control. Perceived usefulness can be converted to routine and safe clinical use with strategic and staged implementation.

Abstract Background People with disabilities use technology, like search engines, to seek health information online. This health information includes information on coronavirus disease, or COVID-19. COVID-19 remains a public health concern. Research shows that people with disabilities encounter frustrations, or "pain points," when seeking online information, but little is known about these specific pain points and who encounters them. Objective The goals of this study are to determine pain points for people with disabilities who seek health information online, and to assess how pain points impact the experience of technology use and information seeking. Methods Ten participants recruited from a prior quantitative survey completed the concurrent think-aloud study over a month-long period. Participants completed four online search tasks and narrated their experiences in real-time while doing so. Transcripts were stored in Taguette; thematic analysis was performed on these transcripts. Findings Participants were predominantly white, with three identifying as Asian. All ten participants reported having disabilities. Participants with attention deficit hyperactivity disorder (ADHD) reported distracting webpage layout, whereas participants with physical disabilities reported physical fatigue while navigating online information. All participants encountered AI-generated information; only one participant indicated trust in the AI-generated information. Other common sources of information included hospital and governmental webpages, peer-reviewed articles, and news and advertising results. News and advertising results were especially common with respect to search results for "COVID-19 vaccine." Themes identified included the following: accessibility/usability, AI-generated information, government/hospital and related sources of information, peer-reviewed articles, news and advertising, and sentiment and trust. Conclusions Information can be fatiguing, distracting, or otherwise difficult to navigate for people with diverse disabilities searching for COVID-19 related information online. Further work should incorporate user feedback from people with disabilities when designing online content.

Artificial intelligence (AI) is dramatically changing the healthcare landscape by providing patients, clinicians, administrators, and public health professionals with tools aiming to improve efficiency, outcomes, and experience in health. As elsewhere, New York State (NYS) experiences high demand for - and high investment in - transformation in healthcare with AI tools, though little is known about clinicians use and interest in adopting AI tools in their work. A large share of the nations future primary care clinicians train and work in NYS, and the states ability to establish clear policies, provide tools, and elevate AI competency have implications for care delivery nationally. As a result, we undertook this analysis of NYS clinicians use of AI to better understand opportunities for its adoption and inclusion in continuing education. For this analysis, we included healthcare providers who deliver ambulatory or specialty medical care within NYS, with use/frequency/purpose of AI tools by clinicians in their work as the main outcome. Of 305 NYS clinical providers responding, 23.4% indicated they use AI tools for work, and 11.1% report monthly use, 8.5% weekly use, and 4.6% daily use. AI was primarily used to search guidelines and ask clinical questions, followed by identifying drug interactions, analyzing data, analyzing images/labs, and creating care plans and patient recommendations. AI use did not vary significantly across professional disciplines or practice types, though independent practitioners were significantly more likely than advanced practice providers to use AI in their work, as were providers using social media and digital methods for obtaining continuing education. AI use increased substantially in 2025 compared with 2024. Overall, our findings suggest that programs targeting clinicians could incorporate these findings in designing accessible and acceptable AI-related continuing education opportunities to help familiarize clinicians with opportunities and risks for integrating AI tools into their practices. Author SummaryAI tools are rapidly gaining traction in the delivery of healthcare. We found that clinician use of AI was quite limited (23%), though growing. Those using AI tools used them sparingly in their work, with only about 5% reporting daily use. The purposes for which clinicians report using AI - asking clinical questions, interpreting patient results, creating patient educational materials - could contribute substantially to healthcare outcomes if widely adopted. Designers of continuing education for clinicians should help provide opportunities for clinicians to improve their familiarity, use, and competency with AI tools, to help maximize the potential health benefits possible for patients and communities.

The present study evaluates the real-world clinical predictive performance of FDA-authorized artificial intelligence (AI) devices used in radiology, focusing on the false positive paradox (FPP) and its implications for clinical practice. To do this, we analyzed publicly available FDA data on AI radiology devices from 2024 and 2025 from 510(k) summaries, demonstrating how diagnostic accuracy metrics like sensitivity and specificity do not necessarily translate into high positive predictive value (PPV) due to the influence of target disease prevalence. We show the importance of disclosing the false discovery (FDR) and false omission rates (FOR) and argue that this transparency enables clinicians to select AI systems that balance false positive and false negative costs in a clinically, ethically, and financially appropriate manner. Finally, we provide recommendations for what data should be provided to best serve practices and radiologists.

This study analyzes the adoption, barriers, and expectations of French radiologists regarding the use of Artificial Intelligence (AI) solutions in their daily practice. Despite a recognition of AI's potential to make radiology more precise, predictive, and personalized, its adoption remains limited. The main obstacles identified are the high cost of those solutions and the insufficient equipment of French imaging centers with AI technologies. Nevertheless, the survey reveals a strong willingness to adopt, with over 70% of radiologists expressing their desire to use AI and 0% declaring a refusal to use it. Furthermore, the radiologists' fears of being replaced by AI are very low (0 to 8.8%).

Limited research has examined the use of physical mock-ups and artificial intelligence (AI) to evaluate design features in adolescent mental and behavioral health environments, such as the Crisis Stabilization Unit (CSU). This mixed-methods study investigated caregiver workflows and environmental features in adolescent CSUs (e.g., furniture and open vs. enclosed nursing station designs) through physical mock-up simulations with expert and novice clinicians/designers (N = 17). Participants feedback was obtained using questionnaires and focus groups. Simulations were video-recorded, manually coded, and an AI-driven tool was developed for automatic analysis of videos. Findings revealed that experts rated the enclosed nursing station higher in visibility, whereas novice designers reported significantly higher perceived privacy in the open nursing station (P = 0.036). AI-driven video analyses demonstrated promising, high-accuracy performance in automatic detecting, tracking, and localizing individuals (>80%) when compared with manual data. This study proposed an innovative methodology to enhance safety in future adolescent CSUs.

In the context of global health, the ability of frontline primary health providers to identify potential Drug-Drug Interactions (DDIs) is a critical component of patient safety. This is particularly true in settings like Tanzania, where drug dispensers often serve as the primary point of contact for healthcare. In this study, we establish a baseline for drug decision-making capabilities across multiple cadres of healthcare providers in Kibaha, Tanzania. We specifically distinguish between the ability to recognize safe drug combinations versus harmful ones. The findings reveal a critical asymmetry in provider performance: while professional training improves the recognition of safe combinations, it provides no advantage over lay intuition (and in some cases, a significant disadvantage) in detecting potentially harmful interactions.

Purpose: High clinical workload is associated with worse patient and hospital outcomes and is a well-established driver of clinician burnout. Trainees may be particularly exposed, shouldering both clinical and educational responsibilities. Evidence-based work design offers a data-driven approach to healthcare work but relies on robust workload measurements. Trainee workload remains poorly characterized, as commonly used metrics (e.g., duty hours, patient census) overlook cognitive and contextual dimensions. This pilot evaluated the feasibility of combining survey-based and electronic health record (EHR) data to characterize internal medicine (IM) trainee workload. Methods: A pilot study was conducted including IM and Medicine-Pediatrics residents (postgraduate years 1-4) between March 31 and June 22, 2025. Participants completed daily surveys during a seven-day inpatient schedule assessing workload and work experience domains, including environment, professional fulfillment, psychological safety, autonomy, and rounding experience, using validated instruments where available. Concurrently, EHR data captured chart review, documentation, orders, and secure messaging activity. Associations between survey and EHR data were assessed. Results: Among 37 eligible residents, 28 (76%) participated in the pilot capturing 166 shifts. Trainees spent 4.4 +/- 1.6 (mean +/- SD) minutes completing daily surveys and 8.6 +/- 2.3 minutes completing the final survey. Trainees reported working 11.6 +/- 1.0 hours/day and a median census of 9.0 (IQR 6.0-11.0). NASA-TLX score was 50.8 +/- 12.6. Positive shift ratings were associated with lower NASA-TLX scores and perceived rounding length. First-to-last EHR login duration was 15 +/- 2 hours/day, and EHR data showed 204 +/- 46 active minutes/day. Login duration correlated with self-reported hours (r=0.43, p<0.0001), and notes signed correlated with self-reported team (r=0.19, p=0.013) and personal census (r=0.34, p<0.0001). Conclusions: Integrating survey-based and EHR-derived workload measures provides multidimensional insight into trainee work. This novel approach supports scalable measurement and evidence-based work design interventions to improve trainee well-being, education, and clinical efficiency.

The recent Lancet Commission on Nigerias health system highlighted high out of pocket expenditures on health and underfunding of the public health sector as major obstacles to Nigerias achievement of the Sustainable Development Goals. Nigeria has sought to address these gaps by extending health insurance coverage. This paper measures health insurance coverage and access to care in Nigeria circa 2023, using the first round of the Peoples Voice Survey (PVS). We analyze health insurance coverage by calculating coverage rates and using multivariate logistic regression to estimate associations between insurance coverage, socioeconomic characteristics, and health system utilization. In 2023, only 2% of Nigerians had insurance from the National Health Insurance Scheme; higher education and higher income levels were the most notable predictors of NHIS access. Chronic illness and self-reported health were not associated with insurance status. Respondents with insurance were less likely to use public sector primary care providers as their usual source of care, and were more likely to use private hospitals. Those with insurance are also more likely to have had an inpatient hospitalization in the preceding year, and more likely to have received key preventive screenings. While those with insurance receive more and better care in Nigeria, insurance access has been limited to relatively advantaged population groups. Rapid mobile phone-based surveys such as PVS could help policymakers in Nigeria track insurance coverage and whether it contributes to reversal of these trends over time.

ObjectivesArtificial intelligence (AI)-enabled digital stethoscopes combine phonocardiography and electrocardiography to support detection of cardiac rhythm and structural abnormalities. This study evaluated the feasibility and exploratory diagnostic performance of AI-guided cardiac auscultation during routine general practice consultations and home visits. MethodsIn this prospective feasibility study, 50 consecutive patients aged [&ge;]65 years underwent AI-assisted auscultation using the Eko CORE 500 during routine care. Recordings were attempted at four standard cardiac positions. Feasibility outcomes included technical failure, workflow disruption, and proportion of analyzable recordings (defined as successful AI output based on combined ECG and phonocardiography signals). Exploratory diagnostic performance was assessed against previously established diagnoses of atrial fibrillation (AF), heart failure (HF), or valvular heart disease (VHD) documented in the electronic medical record. ResultsAI-guided cardiac auscultation was completed in all patients without device malfunction or meaningful workflow disruption (median acquisition time 1-2 minutes). At least one analyzable recording was obtained in 47/50 patients (94%), and complete four-position analyses in 42/50 (84%). Signal limitations were mainly attributable to obesity, chest hair, or excess breast tissue. Among 47 analyzable patients, 11 had known AF, HF, or VHD. Sensitivity for detecting these conditions was 81.8% and specificity 91.7%. One new case of clinically relevant mitral regurgitation was identified. ConclusionsAI-enabled digital auscultation was feasible in routine general practice, with high rates of analyzable recordings and minimal workflow impact. Larger studies with contemporaneous reference standards are warranted to determine clinical utility.

Despite the global prevalence of postpartum depression (PPD), current referral uptake rates are far from satisfactory. While some qualitative studies have investigated factors affecting PPD referrals, a gap in quantitative analysis remains. Addressing this, our study utilized a discrete choice experiment (DCE) to understand the procedural elements influencing PPD referral uptake among diagnosed women. The DCE was conducted via home visits by healthcare providers and a comprehensive mobile app questionnaire. We constructed seven distinct referral attributes to explore participants' preferences, analyzed using mixed logit models and latent class analysis. This analysis identified key determinants and revealed the heterogeneities in referral preferences. A total of 698 individuals completed the DCE questionnaire. All assessed attributes, except for Accompaniment (going to clinic with a family member), were important determinants of preference. Participants generally preferred referrals to psychiatric clinics, face-to-face consultations, lower costs, and shorter waiting times. Significantly, participants' personal and socio-demographic characteristics also played a critical role in their referral preferences. Latent class analysis categorized participants into four distinct groups based on their preferences, with treatment cost and waiting times being the most decisive factors. In conclusion, the preference for PPD referrals is predominantly driven by convenience and access to specialist care. To enhance referral uptake, developing flexible and personalized referral programs that cater to these preferences is crucial.

Artificial intelligence (AI) is increasingly positioned as a transformative tool in education and health. Yet empirical evidence on AI readiness in low-and middle-income countries, particularly among youth, remains scarce. This study examined patterns of adoption, equity determinants, and ethical awareness among Ghanaian youth to inform responsible AI integration in education and health systems. A cross-sectional survey was conducted among 200 youth aged 18-35 years in Ghana. Descriptive statistics, chi-square tests, and logistic-regression analyses were used to assess AI adoption, equity patterns, and predictors of readiness. Most participants reported current (89%) or prior (65%) use of AI tools. Accessibility was a significant positive predictor of adoption ({beta} = 0.142, p = 0.001), whereas limited internet connectivity ({beta} = -0.088, p = 0.049) and perceived exclusion or inequity ({beta} = -0.109, p = 0.026) were significant negative predictors. Gender and age differences indicated persistent digital inequities. Ethical concerns were widespread: 51% were somewhat concerned and 39% very concerned about data privacy, algorithmic bias, and transparency. Ghanaian youth exhibit high AI readiness, but it is distributed in structurally uneven and ethically contested contexts. Readiness is best understood as a dynamic interaction between technical access, social inclusion, and trust. Translating readiness into equitable implementation will require investments in digital infrastructure, ethical governance, and participatory design. This study provides one of the first quantitative assessments of AI readiness among African youth and offers an evidence base for developing trustworthy, inclusive AI applications, such as healthcare and educational chatbots, that are grounded in local realities. Author SummaryArtificial intelligence (AI) is often presented as a solution to challenges in healthcare and education. However, there remains limited evidence on peoples readiness to use AI in low-and middle-income countries and on the ways in which equity and ethics shape that readiness. We surveyed 200 youth in Ghana to understand their use of AI tools, perceptions of fairness and ethical concerns. Most participants were already using AI, yet adoption was uneven. Access to reliable internet and devices strongly increased use, while perceptions of exclusion and limited connectivity reduced it. Many youths expressed concern about data privacy, bias, and transparency in AI systems. These findings show that Ghanaian youth are eager but cautious adopters who value fairness and accountability. Building equitable and trustworthy AI systems in education and health will require improving access, addressing social inequalities, and involving youth directly in the design and governance of new technologies.

Safety net healthcare delivery organizations (SNOs) serve vulnerable populations but face persistent challenges in adopting new technologies, including AI. While systematic barriers to technology adoption in SNOs are well documented, little is known about how AI is implemented in these settings. This study explored real-world AI adoption in SNOs, focusing on identifying barriers encountered across the AI lifecycle and strategies used to overcome them. Five SNOs in the U.S. participated in a 12-month technical assistance program, the Practice Network, to implement AI tools of their choosing. Observed barriers and mitigation strategies were documented throughout program activities and, at the conclusion of the program, reviewed and refined with participants using a participatory research approach to ensure findings reflected lived experiences and organizational contexts. Key barriers emerged during the Integration and Lifecycle Management phases and included gaps in AI performance evaluation and impact assessments, communication with patients about AI use, foundational AI education, financial resources for purchasing and maintaining AI tools, and AI governance structures. Effective strategies for addressing these barriers were primarily supported through centralized expertise, structured guidance, and peer learning. These findings provide granular, actionable insights for SNO leaders, offering guidance for anticipating barriers and proactively planning mitigation strategies. By including SNO perspectives, the study also contributes to the broader health AI ecosystem and underscores the importance of participatory, collaborative approaches to support safe, effective, and ethical AI adoption in resource-constrained settings. Author SummarySafety net organizations (SNOs) are healthcare systems that primarily serve low-income and underinsured patients. While interest in artificial intelligence (AI) in healthcare has grown rapidly, little is known about how these organizations experience AI adoption in practice. In this study, we partnered with five SNOs over a 12-month program to document the challenges they encountered when implementing AI tools and the strategies they used to address them. We worked closely with SNO staff throughout the process to ensure our findings reflected their lived experiences with AI implementation. We found that the most common challenges arose when organizations tried to integrate AI into daily operations and monitor and maintain those tools over time. Specific barriers included difficulty evaluating whether AI was performing as expected, limited guidance on communicating with patients about AI use, a lack of resources for staff training, limited financial resources, and the absence of formal governance structures. Successful strategies for overcoming these challenges drew on shared knowledge and structured support provided by the program, as well as learning from peer organizations. These findings offer practical guidance for SNO leaders planning or managing AI adoption, and contribute to a broader conversation about what is required to implement AI safely and effectively in healthcare settings that serve the most medically and socially vulnerable patients.

Artificial intelligence (AI), particularly large language models (LLMs), is increasingly explored in healthcare, yet its real-world usability and safety in high-risk clinical pharmacy tasks remain uncertain. Vancomycin therapeutic drug monitoring (TDM), which requires precise pharmacokinetic calculations and context-sensitive interpretation within a narrow therapeutic window, provides a stringent test case for AI-assisted decision support. This proof-of-concept study developed and evaluated a hybrid clinical decision support system (TDM-AID) integrating a validated deterministic pharmacokinetic calculation engine, GPT-4o-based structured clinical interpretation, and retrieval-augmented guideline support. Thirty retrospective adult vancomycin TDM cases were assessed using a weighted six-domain rubric covering pharmacokinetic accuracy, AUC estimation, prospective prediction, timing recommendations, clinical judgment, and documentation quality. Two independent expert pharmacists evaluated system outputs against benchmark consultations. The overall median performance was 78% (IQR 12%), classified as Acceptable, and 73% (IQR 14%) when deterministic calculations were excluded. Foundational pharmacokinetic calculations achieved 100% accuracy. Clinical judgment demonstrated Good performance (83%), whereas prospective prediction was limited (58%), and timing recommendations were absent in all cases. Safety violations occurred in 17% of cases, including dose recommendations exceeding 4 g/day. Inter-rater reliability was good (ICC 0.87). These findings suggest that hybrid AI-driven decision support is technically feasible and usable as a pharmacist-augmenting draft generator; however, limitations in predictive reasoning, timing logistics, and safety enforcement necessitate deterministic safeguards and mandatory expert oversight before clinical implementation.

Objective: This preliminary public health report assessed acute and chronic health burdens, focusing on cardiovascular health, among unsheltered individuals experiencing homelessness. It aims to guide medical referrals, deliver targeted health education, and prioritize services within a community based nonprofit. Methods: A field based needs assessment used a structured questionnaire to evaluate acute and chronic health burdens. Clinical measures included blood pressure (BP), heart rate (HR), pain scores (normalized to 0 to 10), nicotine use, and diabetes prevalence. Of 72 initial responses, 59 BP, 65 HR, and 66 pain scores were usable. BP was classified per ACC/AHA (2017) guidelines [1], including Hypertensive Crisis. Nicotine and diabetes data from a secondary survey yielded 39 and 38 usable responses of 116. Ethical oversight ensured informed consent, participant capacity assessment, and emergency protocols. Data were analyzed descriptively. Results: Participants were predominantly male (N = 53 of 72) with ages ranging from 24 to 70 years (Mean = 42.96; Median = 41; N = 70). The cohort was primarily White/Caucasian (N = 30) and Black/African American (N = 27). Cardiovascular assessments revealed substantial acute risk: 72.88% (N = 43 of 59) of BP readings were classified as Total High Blood Pressure, and 10.17% (N = 6 of 59) met criteria for Hypertensive Crisis or higher, including readings of 210/137 mmHg and 286/127 mmHg. Mean and median HR were both 96 bpm (N = 65). Chronic symptom burden was notable, with a mean pain score of 3.74 and 19.70% (N = 13) reported severe pain (7 to 10). Self-reported comorbidities included current smoking in 15.38% (N = 6 of 39) and a history of diabetes in 13.16% (N = 5 of 38). Conclusion: Findings show a high prevalence of acute cardiovascular risk, particularly severe hypertension, among the unsheltered population. These results highlight the urgent need for improved outreach, targeted cardiovascular and primary care referrals, and follow up screenings. Expanding health education on the effects of uncontrolled diabetes and smoking is recommended to reduce future cardiovascular events.