JMIRx Med

Background: Electrolyte replacement is ubiquitous in the acute care setting, but its familiarity cannot belie that even small dosing errors with potassium can cause lethal cardiac arrhythmias. Recently, MedAgentBench offered a benchmark for agentic artificial intelligence (AI) including the ability to correctly dose potassium based on a single rule; however, this does not adequately reflect the clinical complexity or safety concerns of an agent that has been used as the lethal injection. The purpose of this analysis was to a probe leaderboard large language model (LLM) capabilities to follow basic dosing rules to safely replace potassium in a series of clinician-annotated cases. Methods: Using a clinician panel, we developed a series of dosing principles and 20 clinical cases reflective of the complexity of potassium replacement. External clinicians were surveyed to assess practice variability and agreement to clinician panel answers. We tested GPT-5-chat with each case in triplicate, with and without the clinician curated dosing principles, and prompted the model to answer six questions involving potassium goals, dosing, route, lab frequency, concurrent interventions, and the model's perceived level of confidence for the output and complexity of the case. The primary outcome was the rate of appropriate recommendations in comparison to clinician answers. Results: A total of 54 clinicians reviewed the 20 hypokalemia cases and hypokalemia dosing guideline. Clinicians expressed "highly agree" or "somewhat agree" for 66.8% of the cases evaluated when asked if they agree with the guideline-recommended management. When given the potassium dosing guideline, total errors dropped from 165 to 104, and average accuracy improved from 45% to 65% with GPT-5-Chat. GPT-5-Chat conveyed a high level of confidence for 100% of responses, while labeling 80% and 76% of cases as highly complex with and without the criteria, respectively. Potential harm scores were considerable in both groups, however, a notable reduction in severity scores occurred with the dosing guidance document. Recommendations on concurrent interventions and dosing had the highest rate of errors in both groups. Conclusions: Benchmarks must appropriately reflect clinical complexity to be considered valuable for the deployment of agentic artificial intelligence tools in the healthcare domain. GPT-5-Chat assessment on a comprehensive medication management task for potassium replacement showed improvement with dosing guidance, yet unfit benchmarking performance.

BackgroundThe 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 Hillerod, 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. ObjectiveThis 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. SystemVersion 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. MethodsTo 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 in the preparation of this manuscript; all scientific content, data collection, analysis, and conclusions are the sole responsibility of the authors. ResultsThe first discourse corpus produced five major themes in relation to the five general problem areas that the prototype was intended to cover: 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 supportive dataset supported all five themes on its own and presented two new themes: the different treatment of international patients and medical gaslighting as a long-term trend of patient advocacy failure. One of the major structural discoveries the five most-liked comments were critical of the original poster being self-referring to the ED when she had in fact been explicitly triaged to receive 1813 telephone referral to the ED directly inspired the Referral Pathway Display and Why Am I Waiting? features in v5. ConclusionsThe 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.

Background: Concerns about "AI psychosis" have swirled in the media since ChatGPT's release, but few systematic analyses exist. We therefore conducted an electronic health record (EHR) analysis to identify the frequency, clinical characteristics, and quality of AI interactions in patients experiencing psychosis treated in a medical center. Methods: AI keywords (e.g., ChatGPT, AI) were used to search Vanderbilt University Medical Center's EHR from 12/1/2022-4/1/2026. Records were discarded if they were not AI-related or if the primary diagnosis did not include psychosis. Three raters read notes to determine if a patient was experiencing AI psychosis and classified the interactions using 4 a-priori categories (Catalyst, Amplifier, Co-Author, Object) formulated to explain how AI-related negative outcomes emerge. Findings: 73 patients met our criteria. 28 patients were rated as experiencing AI psychosis, 17 had neutral interactions, and 28 expressed delusional content related to AI without documented evidence of conversational AI use. ChatGPT was the matching keyword for 53.6% patients experiencing AI psychosis. The majority of AI psychosis cases were documented after ChatGPT's "4o" model was released in May 2024. Notably, the AI Psychosis group had significantly more patients experiencing a first psychotic episode (60.7%) compared to the other two groups. Amplifier was the most common (64.3%) qualitative rating in the AI Psychosis group. Interpretation: "AI psychosis" is an infrequent but real phenomenon observed in clinical practice. Most affected patients were experiencing their first psychotic episode and presented with AI psychosis following the release of the more sycophantic GPT-4o. Among the affected patients, AI most often exacerbated an existing condition by reinforcing distorted ideas.

Introduction: The use of artificial intelligence (AI) by clinicians has increased rapidly in recent years, with large language models (LLMs) emerging as tools that can equal clinician diagnostic performance in simulated settings. However, limited data exist regarding physicians use of LLMs in real-world clinical practice. This study aimed to evaluate the frequency of LLM use among practicing hospitalists, identify which LLMs are most commonly utilized, and assess hospitalists' perceptions of the benefits and limitations of LLM use in clinical care. Methods: We conducted a cross-sectional survey study of academic hospital medicine faculty across 8 institutions within the Hospital Medicine Reengineering Network (HOMERuN), a collaborative research consortium. Eligible participants included hospitalists practicing within participating HOMERuN sites during the study period. The survey assessed the frequency of LLM use, types of LLMs used, clinical applications, and physician perceptions regarding usefulness, efficiency, and concerns associated with LLM adoption. Results: 170 respondents (67.1%) reported ever using an LLM in clinical practice. Among LLM users, OpenEvidence was the most used tool (88.9%), followed by ChatGPT (58.5%), Google Gemini (26.9%), and Microsoft Copilot (20.5%). Only a minority of hospitalists reported using LLMs daily while seeing patients. The most common use cases of LLMs were answering diagnostic (77.1%) and management (77.6%) questions. A majority also reported using LLMs to identify or summarize primary literature (60.0%). Lack of trust in outputs (49.8%), uncertainty around institutional policies (48.6%), and lack of access to secure applications (43.1%) were cited as the most frequent barriers to using LLMs in practice. Discussion: The use of LLMs in clinical practice is already widespread, though regular or daily use is not yet typical. Concerns regarding reliability, patient privacy, and safe integration into clinical workflows remain significant barriers to broader adoption. The responsible implementation of LLMs in hospital medicine will require addressing these barriers.

More than 100,000 people in the UK have an ischaemic stroke every year. This means a blood clot blocks an artery supplying blood to their brain. Patients with ischaemic stroke often have sudden weakness affecting half of their body or face, and problems with speech, although other stroke symptoms are possible. Treatment with a clot-busting drug (thrombolysis) can reduce the amount of disability and death caused by ischaemic stroke by restoring the blood supply to the brain. Thrombolysis usually needs to be given within four and a half hours of stroke occurring. Unfortunately, nearly three quarters of patients with ischaemic stroke arrive in hospital later than this, or it is not clear when their stroke started. For these patients, it may still be possible to treat them with thrombolysis if the hospital can provide an additional advanced type of brain scan. However, many hospitals in the UK and worldwide cannot offer this advanced scan to patients with stroke, particularly hospitals that are not in major cities or developed nations. Patients arriving at these hospitals therefore do not currently have the same access to effective treatment for stroke. We have developed a simple method for identifying which patients can be given thrombolysis even if they arrive at hospital later than four and a half hours, or where there is uncertainty about when their stroke started. Our method does not require any additional or advanced imaging, only the standard computed tomography (CT or CAT) scan that all patients with stroke get when they arrive at hospital. Our method is called the CT Clock. We ask doctors to look for stroke changes indicating ischaemic stroke in the brain on CT. If they find these stroke changes, they measure them compared to normal brain. If the stroke changes on CT are minor (less than 20% darker than normal brain), or the scan appears normal despite quite severe stroke symptoms, we would consider these patients suitable for treatment with thrombolysis. This study proposes to test the safety of our CT Clock method in an analysis of existing NHS data from patients who have previously been treated with thrombolysis. We aim to show that when doctors who provide stroke care use our CT Clock method to identify suitable patients for treatment with thrombolysis, it is safe for these patients. If successful, this study will allow us to plan for and deliver future clinical testing where we would use the CT Clock to identify patients for treatment with thrombolysis in hospitals where advanced imaging for stroke is unavailable. Successful clinical testing is needed before our method can be used routinely in hospitals around the world. Data Study Protocol O_TBL View this table: org.highwire.dtl.DTLVardef@18a7b6corg.highwire.dtl.DTLVardef@ad2388org.highwire.dtl.DTLVardef@f7ea61org.highwire.dtl.DTLVardef@3cc038org.highwire.dtl.DTLVardef@6faf1e_HPS_FORMAT_FIGEXP M_TBL C_TBL

Objectives: Older adults with comorbidities and polypharmacy have disproportionately high risk of hospitalization as well as readmission from adverse drug events (ADEs), of which 28%-71% are preventable (pADEs). This paper introduces an LLM application, CommunicADE, designed to support risk-mitigation of pADE-related readmission for the aforementioned population. We aim to evaluate CommunicADE's technical performance with OpenAI's HealthBench criteria: accuracy, completeness, communication quality, context awareness, and instruction following. Materials and Methods: Our technical validation study used an LLM (KimiK2.5) to simulate interviews between CommunicADE and nine high-fidelity synthetic patients hospitalized and at increased risk for pADE-related readmission (65+ years, comorbidities, 5+ medications). Some pADE risk mechanisms clues were visible to CommunicADE in patient H&Ps, but most mechanisms were solely discoverable in interviews. Two pharmacists evaluated CommunicADE's interview questions and EHR notes with HealthBench-informed variables. Analyzes used descriptive statistics. Results: For 35 mechanisms across 9 patients (avg=3.89 mechanisms/patient), CommunicADE's precision and recall were 0.92 and 0.63, respectively. Hallucinations were absent. Coherence and person-centeredness scored 4.28 and 4.44 on a 5-point scale (5=highest). On average, communication was at a 5th grade level and objective for 78% of patients. Most patient-reported quotes included in notes (92%) supported detected mechanisms. CommunicADE followed all instructions regarding interview length and patient approvals. Discussion: CommunicADE's strongest performance was in accuracy (precision, hallucinations), communication quality (coherence, readability), context awareness (person-centeredness). Completeness (recall) and instruction following (objectivity, pADE mechanism/quote alignment) show room for improvement. Conclusion: Findings suggest technical readiness for a feasibility pilot with real-world patients, and key areas for performance improvement.

BackgroundVascular 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. ObjectiveTo 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. MethodsA 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). ResultsDuring 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 ward (31.6% - 44.2%), 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 in the end of therapy, and the median duration of catheter use was 12 days. ConclusionPICCs 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.

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.

Background: With growing impetus to integrate artificial intelligence (AI) tools into radiology, clinical practices must navigate workflow redesign. This carries implications for medical malpractice liability. Methods: We conducted an online vignette experiment with United States adults who acted as hypothetical jurors in a malpractice case involving a missed intracranial hemorrhage. Participants (n=2,347) were randomized to one of 22 conditions: a no-AI control and 21 conditions involving a hypothetical AI system. These twenty-one conditions varied by whether (1) a single-read or double-read workflow was used, (2) the radiologist's initial interpretation was documented, (3) the radiologist changed their interpretation after viewing AI output, (4) the AI detected the abnormality, and (5) the AI error rate--False Discovery Rate (FDR) or False Omission Rate (FOR--was provided to participants only, both participants and radiologist, or neither. The primary outcome was perceived liability, assessed by whether the radiologist met their duty of care. Findings: Perceived liability differed across conditions (p<0.0001). Double-read workflows (p<0.0001), documenting initial interpretations (p=0.0125), and providing participants with AI error rates, including the FDR (p=0.0038) or FOR (p=0.0035), reduced perceived liability. Liability was also lower when AI was incorrect (p<0.0001). Radiologists' awareness of AI error rates did not significantly impact liability. Notably, we observed an erroneous change penalty: the greatest liability occurred when radiologists initially identified an abnormality but later changed their interpretation to normal after seeing that AI identified the case as normal; conversely, perceived liability was lowest with documented, double-read workflows. Interpretation: Double-read workflows with documented initial interpretations and disclosure of AI error rates reduce perceived liability, though changing a correct initial interpretation increases it. Strategic workflow design is critical for successful AI implementation that can mitigate malpractice risk.

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%).

INTRODUCTION In the multiple-risk approach of cardiovascular disease management, communication of cardiovascular disease risk and its prevention play a significant role. in Sri Lanka, this function is conducted via Healthy Lifestyle Centres. METHODOLOGY A clinical audit was conducted to describe communication quality in 79 healthy lifestyle centers. A checklist developed based on Patient-Centered Communication Tools with the support of an expert panel. Two trained observers independently conducted the observations while the healthcare provider at the Healthy Lifestyle Centre revealed details of cardiovascular disease risk communication and health education sessions. RESULTS: The majority of Healthy Lifestyle Centers involved patients in decision-making (n = 228, 92.0%), explained patient choices (n = 230, 92.8%) and responded to patients' interest in decision-making (n =2 35, 99.2%). Most patients received a summary (n =159,67.1%), a follow-up plan (n =212,89.5%) and were communicated in a jargon-free language (n =127,53.6%). The majority of sessions demonstrated satisfactory use of examples (95.7%, n = 22), and responsiveness to questions (73.9%, n =17). However, most sessions were unsatisfactory regarding provision of a follow-up plan (95.7%, n = 22), encouragement of questions (95.7%, n = 22), allowing clients to talk (87.0%, n = 20), and active listening (69.6%, n = 16). CONCLUSIONS: Strengthening healthcare worker training in patient-centred communication especially shared decision-making, active listening, and encouraging patient questions are essential to improve cardiovascular disease risk communication and patient adherence to preventive guidelines at Healthy Lifestyle Centres. Key words Communication, Cardiovascular disease risk, health communication, effective communication, paternalistic healthcare

Youth in the United States are experiencing growing mental health challenges, yet many face barriers to accessing timely, affordable, and stigma-free support. At the same time, artificial intelligence (AI) chatbots have become widely available and are increasingly being used by young people as tools for information seeking, coping, and self-reflection. This brief report explores how youth are engaging with AI chatbots for mental health support, drawing from qualitative interviews conducted in New Jersey. Nine semi-structured interviews were completed with participants ages 19-22. Thematic analysis revealed five core themes: (1) generational change, peer communication, and humor as coping and normalization tools; (2) internal and external barriers to self-recognition and help-seeking; (3) AI chatbots as a safe and accessible first step; (4) AI chatbots as a tool for filling information gaps; and (5) limits of AI chatbots and the preference for human connection. These findings indicate that young people see AI chatbots as private, judgment-free starting points for exploring their emotions and seeking early support. However, they also recognize that these tools cannot replace human connection or professional care. For public health, this presents both challenges and opportunities in utilizing the accessibility of AI chatbots while ensuring ethical design, cultural responsiveness, and protections that safeguard youth privacy and equity.

Background: Despite the significant risks associated with online substance procurement (SP), few researchers have examined this practice in U.S. youth. The studies that do exist are cross-sectional and cannot temporally connect specific digital behaviors to online SP. This longitudinal cohort study examined youth SP and digital media habits to determine whether use of certain smartphone applications correlated with increased odds of online SP or being contacted online about procuring drugs or alcohol. Methods: A cohort of U.S. youth (aged 15-20) with a history of non-daily substance use in the 3 months prior to enrollment was recruited to use the digital phenotyping smartphone application EARS for 90 days. On a nightly basis, participants were asked to complete surveys about online experiences related to SP and instances of substance use. Smartphone-generated screen use data were also collected passively each day. Results: Out of 112 enrolled participants, 106 were able to be included in analyses. Over approximately 3 months, 28.3% of participants (n=30) reported a collective 91 instances where they used social media to acquire drugs or alcohol. Screen use data demonstrated temporal relationships between social media SP and applications previously connected to the social media drug-purchasing process (e.g., TikTok, encrypted apps), as well as other school-specific social media. Discussion: Our results provide critically needed research evidence to support a body of literature composed predominantly of anecdotal reports. Despite measures taken by social media companies to prevent use of their platforms for drug procurement, underage youth continue to engage in this practice.

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 patients. 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.

Although large language models (LLMs) have shown promise for discharge summary generation, their value may be greater in longer hospitalizations, where increasing documentation volume and complexity increase both clinician burden and the risk of communication failures during transitions of care. Prior evaluations of LLM-generated discharge summaries have largely involved shorter stays and have rarely examined receiving-clinician priorities or incidental finding reporting. We compared LLM-generated and human-authored discharge summaries for 60 Internal Medicine hospitalizations lasting 7 to 21 days, with paired assessment by hospitalists and primary care physicians (PCPs). Clinician reviewers preferred LLM-generated summaries for 95% of encounters and rated them higher for quality, readability, factuality and completeness. PCPs, the primary recipients responsible for post-discharge care, found that LLM-generated summaries were better for understanding and communicating hospital care to patients, and providing follow-up care. LLM-generated summaries had fewer annotated errors, primarily due to fewer omissions, without increased estimated harm potential or likelihood compared with human-authored summaries. Benefits of LLM-generated summaries were especially salient for PCPs, who identified more omissions with greater downstream likelihood of harm than hospitalists. This underscores the importance of designing transition documents around the needs of clinicians assuming care post-discharge. LLM identification of radiology incidental findings was generally accurate and appropriate, suggesting potential to improve follow-up of clinically relevant findings. These findings extend prior work by demonstrating clinical value of LLMs in summarizing longer, complex hospitalizations and highlighting the value of stakeholder-centered design in clinical AI systems. Together, they support supervised LLM-assisted discharge summarization as a tool to reduce cognitive burden, improve documentation quality, and enhance transition-of-care communication.

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.

Introduction: Cardiovascular diseases (CVDs) are the leading cause for death and disability worldwide accounting for 75% of deaths in low- and middle-income countries (LMICs) like Nepal. Urbanization and globalization remains the major cause of rise in CVDs among urban poor population along with growth in slum settlements. This study aims to assess the knowledge, attitude and practice (KAP) of CVDs and its risk factors among women of one such urban poor community in Nepal. Methodology: This cross-sectional study (n=388) in the Sinamangal-Minbhawan slum area was conducted using semi structured questionnaire based on STEPs survey and HARDIC study among the participants selected through convenient sampling. Descriptive analysis was done using SPSS version 21 and KAP scores were further categorized based on median score to perform multivariate logistic analysis. Additionally, Anthropometric and blood pressure measurements were also recorded and analyzed. Results: The median age (Interquartile range) of participants was 33 years (17) with majority of them being Dalit by ethnicity, housewives, with up to primary level education belonging to upper lower socioeconomic class. More than half (53.3%) of the participants were obese and over 23% were hypertensive. While half of the hypertensive women were aware of their status, only 3% had their blood pressure under control.The median knowledge, attitude and practice (KAP) scores were 12, 60 and 10 respectively. The KAP scores were positively associated with socioeconomic status of the participants. Conclusion: The study revealed low knowledge with high prevalence of behavioral risk factors of CVDs along with high prevalence of other metabolic risk factors like high body mass index, high waist hip ratio and hypertension among women of slum area with a positive attitude to prevent CVDs and its risk factors.

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.

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.