Healthcare

Background: System One Model is designed for structured decision-making and can provide probabilistic outputs, but their performance in domain-specific physical therapy tasks has not been established. Objective: To evaluate the performance and potential utility of Jev, a System One Model, for professional knowledge-based selection tasks in physical therapy by comparing it with GPT-4o. Methods: A total of 380 multiple-choice questions from the 2024 and 2025 Korean Physical Therapist Licensing Examinations were independently submitted to Jev and GPT-4o. The outcomes included answer accuracy, subgroup performance, output validity, API response latency, token usage, estimated API cost, and Jev's prediction uncertainty. A retrospective probability-based model-cascading simulation was also performed. Results: Jev correctly answered 282 questions (74.2%), whereas GPT-4o answered 326 (85.8%), a difference of -11.6 percentage points. Jev produced valid structured responses for all questions, whereas GPT-4o produced three invalid responses. Jev's selected-answer probabilities discriminated correct from incorrect answers (AUROC = 0.866), and accuracy reached 99.3% when probabilities were greater than or equal to 0.90. The median API response latency was 0.94 s for Jev and 1.06 s for GPT-4o, with estimated costs of US$0.008 and US$0.161, respectively. At a retrospective cascading threshold of 0.70, accuracy was 86.6% with 175 simulated GPT-4o calls. Conclusion: Jev showed lower overall accuracy than GPT-4o but provided reliable structured outputs, informative prediction probabilities, lower latency, and lower estimated cost. Its probabilistic outputs warrant further prospective evaluation for selective model escalation and decision-support workflows in physical therapy.

Cardiovascular diseases (CVD) are the leading cause of global mortality, responsible for 17.8 million deaths and 423 million prevalent cases annually. While the etiology of CVD is multifactorial, evidence confirms that multicomponent behavioral interventions regarding diet and lifestyle can substantially reduce risk. This study aimed to evaluate the effectiveness of a 12-month mHealth intervention, i.e., public health practice supported by mobile devices in reducing the 10-year CVD risk among overweight and obese adults aged 35 to 64 in an urban Sri Lankan population. A two-group parallel-arm randomized control trial (RCT) was conducted with 1,200 participants from the Colombo district, assigned either to an intervention arm (n=600) or a usual care control arm (n=600). The intervention group received automated text and voice messages in their native language at a frequency of two of each per week over 12 months. The primary outcome, 10-year CVD risk, was assessed using the WHO CVD risk prediction score. The intervention significantly reduced the proportion of participants with a 10-year CVD risk from 10.0% to 6.2% (p=0.003), whereas no significant change was observed in the control group (11.0% to 9.7%). Participants in the mHealth arm demonstrated substantial behavioral improvements, including increasing daily fruit and vegetable servings from 3.6 to 5.5 and reducing daily salt intake from 7.64g to 5.62g. Physical activity levels also improved, with 89.6% meeting minimum daily requirements compared to 77.4% at baseline. These findings suggest a potentially beneficial effect on predicted cardiovascular risk. The study concludes that an automated mHealth intervention is an effective, feasible, and acceptable approach to reducing cardiovascular risk in an urban South Asian setting. The findings provide a robust evidence base for integrating digital health strategies into national non-communicable disease (NCD) prevention policies. While the 12-month results are promising, further longitudinal research is required to evaluate the long-term sustainability of these behavioral changes and their ultimate impact on mortality rates.

Aim. To evaluate the accuracy, run-to-run consistency, and agreement of large language models on the Ukrainian Integrated Licensing Examination Krok 2 for the Specialty of Physical Therapy. Materials and Methods. Five cloud-based LLMs (ChatGPT-5.5, Claude 5 Sonnet, Gemini 3.5 Flash, Grok 4, DeepSeek-V3) were evaluated using 150 Ukrainian-language multiple-choice questions from the official Krok 2 database. Each model completed two independent runs with identical inputs. Accuracy (with 95% confidence intervals, Wilson method), run-to-run consistency, and agreement were assessed. Statistical analysis included Cohen's {kappa}, Cochran's Q and pairwise McNemar tests with Holm-Bonferroni correction. Results. All models achieved >80% accuracy in both runs, exceeding the passing threshold of [≥]64%. In the first run, accuracy ranged from 80.00% (DeepSeek-V3) to 93.33% (Gemini 3.5 Flash); in the second run, from 82.67% (Claude 5 Sonnet) to 88.67% (Gemini 3.5 Flash). In the first run significant differences were observed between Gemini 3.5 Flash and Grok 4 (93.33% vs 84.00%; p=0.0022) and DeepSeek-V3 (93.33% vs 80.00%; p=0.0001). There were no statistically significant differences between models in the second run. R2R consistency exceeded 90% for all models with the highest in ChatGPT-5.5 (98.67%) and lowest in DeepSeek-V3 (90.00%). Cohen's {kappa} ranged from 0.64 to 0.94, indicating substantial to almost perfect agreement. The stability of LLMs' response correctness across two runs ranged from 77.33% (DeepSeek-V3) to 88.00% (Gemini 3.5 Flash). Conclusions. All LLMs demonstrated high performance on Ukrainian-language Krok 2 examination tasks. Gemini 3.5 Flash showed the highest accuracy in both runs and response correctness stability while ChatGPT-5.5 exhibited the greatest response consistency and agreement. Although the accuracy and stability of LLM responses may be interrelated, they represent distinct aspects of model performance. This highlights the need for a comprehensive approach to evaluating LLMs. The findings indicate the potential of LLMs as an auxiliary tool in the professional practice of physical therapy specialists.

Abstract Background Community-based exercise may support physical and cognitive recovery after stroke, but the preferences of stakeholders involved in receiving, supporting and delivering these programmes are poorly understood. This study piloted a discrete choice experiment (DCE) that aimed to evaluate stroke survivors, carers, clinicians, and fitness instructors preferences for community-based exercise programmes for stroke survivors. The pilot aimed to assess the feasibility of conducting and analysing data for a larger-scale study and inform the sample size for a definitive DCE. Methods A DCE design was developed using literature reviews, stakeholder consultations, and evaluations of current services. Six attributes were included in the design: location, price, session frequency, individualisation, carer involvement, and recovery. Sixteen Bayesian D-optimal choice sets were developed, then blocked into two sets of eight to reduce cognitive burden. Main-effects were analysed using a mixed logit model, and stakeholder differences were explored using a conditional logit interaction model. Willingness to pay was also calculated. Results Overall, 161 respondents started the survey and 106 (66%) fully completed it. Stakeholders significantly preferred programmes that were delivered at a leisure centre, lower priced, individualised, had carer-specific sessions and offered greater chances of recovery. The largest willingness-to-pay estimates were {pound}49.41/ month for 80% chance of meaningful recovery vs 20%, and {pound}18.61/ month for leisure centre delivery vs online. Significant preference heterogeneity was identified in the main-effects model. Exploratory stakeholder interactions suggested clinicians were more price sensitive and placed greater importance on recovery and carer-specific sessions than stroke survivors, while fitness instructors placed greater importance on programme location and recovery. Carer interaction estimates were unstable due to the small subgroup sample. Conclusions The pilot supported the feasibility of the DCE design and analytical approach but identified limitations in the recruitment methods and survey completion. Addition of face-to-face recruitment methods are recommended for a larger-scale study. A larger sample size is required to investigate differences in preferences between stakeholder groups.

Background: Data from National Health and Nutrition Examination Survey (NHANES) cycles 1988-1994 and 1999-2004 show a declining trend in the adherence to Dietary Approaches to Stop Hypertension (DASH) among adults. Since then, DASH evidence, dietary guidelines, and public-facing dietary resources have advanced, but whether national DASH adherence has improved is uncertain. Methods: We extended the Mellen et al. NHANES analysis among 14,163 adults with self-reported hypertension (N=6,914, 2003-2010, N=7,249, 2011-2018). DASH score included 9 nutrient components: total fat, saturated fat, protein, cholesterol, fiber, calcium, magnesium, potassium, and sodium, with adherence defined as a score 4.5. Survey-weighted multivariable models compared DASH score, adherence, and nutrient-threshold attainment across periods. Results: In 2011-2018, U.S. adults with self-reported hypertension represented 76.2 million individuals (33.8%). Multivariable-adjusted DASH adherence declined from 22.1% in 2003-2010 to 18.6% in 2011-2018 (p=0.003), and mean DASH score declined from 2.98 to 2.85 (p=0.007). Adjusted odds of adherence were lower in 2011-2018 compared with 2003-2010 (OR, 0.78; 95% CI, 0.67-0.91; p=0.002). Adherence was lower among non-Hispanic Black adults (OR, 0.70; 95% CI, 0.59-0.84), adults with BMI 30 kg/m2 (OR, 0.61; 95% CI, 0.51-0.73), and adults with prior stroke (OR, 0.71; 95% CI, 0.56-0.89). Total fat and sodium threshold attainment declined from 20.9% to 18.7% and 13.8% to 11.8%, respectively. Conclusions: DASH adherence among U.S. adults with self-reported hypertension declined from 2003-2011 to 2011-2018. Implementation strategies should identify barriers to adoption and address the full DASH dietary pattern.

Importance: Dyslipidemia, hypertension, and diabetes are highly prevalent conditions for which medical nutrition therapy (MNT) is guideline-recommended, yet access remains limited, and real-world evidence on technology-enabled MNT models at scale is sparse. Objective: To characterize lipid, blood pressure, and glycemic outcomes among adults receiving virtual MNT (vMNT) across three cardiometabolic conditions. Design: Retrospective cohort study of adults with a first Nourish appointment before November 2025, followed for 6 months. Setting: National vMNT platform. Participants: Adults meeting enrollment criteria for dyslipidemia, hypertension, or diabetes and remaining engaged in care with [&ge;]1 follow-up measurement at 3 or 6 months. Final cohorts: dyslipidemia (n=6,501), hypertension (n=13,704), diabetes (n=2,444); 18,965 unique patients overall. Exposure: vMNT delivered by a registered dietitian via telehealth visits, with technology-enabled support between visits. Main Outcomes and Measures: Outcomes were LDL cholesterol, total cholesterol, HDL cholesterol, and triglycerides (dyslipidemia); systolic and diastolic blood pressure (SBP, DBP) (hypertension); and HbA1c (diabetes), assessed at enrollment, 3, and 6 months. Weight was a secondary outcome. The proportion achieving guideline-recommended targets (HbA1c <7.0%, SBP <130 mmHg) was also assessed. Results: Among 18,965 patients (mean [SD] age, 42.9 [11.6] years; 15,770 [83.2%] female), significant changes from baseline to 6 months included: LDL cholesterol (-14.0 mg/dL [SE, 0.56]); total cholesterol (-19.4 mg/dL [SE, 0.61]); HDL cholesterol (-0.5 mg/dL [SE, 0.15]); triglycerides (-28.6 mg/dL [SE, 1.06]); SBP (-5.5 mmHg [SE, 0.16]); DBP (-4.5 mmHg [SE, 0.11]); and HbA1c (-1.37 percentage points [SE, 0.04]) (all P<.001). Among those with elevated SBP, 57.3% achieved <130 mmHg by 6 months; among those with elevated HbA1c, 54.7% achieved <7.0%. Outcomes among patients with stable medication regimens were similar to the full cohort. Conclusions and Relevance: In this study of 18,965 patients, vMNT delivered through a technology-enabled care model was associated with clinically meaningful improvement across three prevalent cardiometabolic conditions. These findings support technology-enabled virtual care as a scalable approach to delivering effective MNT.

Background: Hypertension (HTN) and Type 2 diabetes mellitus (T2DM) are leading drivers of the global cardiometabolic disease burden and major contributors to preventable morbidity and mortality. In Hong Kong, where population ageing and lifestyle-related risk factors are increasingly prevalent, both conditions and their complications pose substantial challenges to the healthcare system. Although territory-wide prevalence figures are available, small area district-level evidence on the burden of these diseases and their associated complications remains limited. Disparities are likely due to heterogeneity in demographic composition, socioeconomic status, and primary care accessibility across Hong Kong's eighteen administrative districts. There is also a lack of accessible, age-adjusted, district-level disease visualization in Hong Kong. Objectives: This study estimates the age-standardized prevalence rates (ASPR) of HTN, T2DM, and their associated complications across the eighteen districts of Hong Kong, formally evaluate the statistical significance of inter-district disparities, and rank the districts according to disease burden to inform place-based health planning. Methods: This study analyzed the prevalence of chronic diseases from 2014 to 2023 in 18 districts among an adult cohort aged equal or above 35 years using data collected from the Hong Kong Hospital Authority (HA) electronic health records, using the International Classification of Diseases, Ninth Revision (ICD-9) diagnostic codes, the International Classification of Primary Care (ICPC) codes, and the disease flags to identify diseases. Sample weights are used to reflect the total population. HTN, T2DM, and their major complications were identified according to standardized diagnostic criteria. ASPR were calculated for each district with the WHO World Standard Population as the standard. Inter-district disparities in disease prevalence were assessed using Cochran's Q test, with statistical significance set at P <0.05. The slope index of inequality (SII) was also used to analyze the socioeconomic inequality between districts. Districts were subsequently ranked according to their ASPR for each condition to identify high-burden and low-burden areas. Results: 1,756,521 patients (52.71% females) contribute 9,906,729 patient-years from 2014 to 2023. Substantial inter-district variation and increasing trend were observed in the ASPR of HTN, T2DM, and their complications. The weighted ASPR of HTN varied by 27.3% from 46,701 (95% CI: 45,691-47,711) per 100,000 population in Tsuen Wan district to 59,445 (95% CI: 58,759-60,130) per 100,000 population in Yuen Long district, and the weighted ASPR of T2DM ranged from 20,464 (Tsuen Wan, 95% CI: 19,803-21,124) per 100,000 population to 28,275 (Yuen Long, 95% CI: 27,792-28,758) per 100,000 population across the districts in 2023. All diseases showed district disparities (all P <0.05). Cochran's Q test demonstrated statistically significant disparities across districts and showed no convergence through the period. The SII test also showed the most serious inequality exists in HTN, with the lower socioeconomic position districts have more burden. Conclusion: Significant geographic disparities exist in the prevalence of HTN, T2DM, and their complications across Hong Kong's eighteen districts. These findings highlight the need for district-specific public health strategies, equitable allocation of primary care resources, and targeted chronic disease prevention and management programs in high-burden areas.

Background and objective. The WHO growth reference judges a child's height against the population at one age, without using the child's own earlier growth. This study built and validated a quantile regression based conditional growth reference predicting a child's future height for age distribution from early growth status. Methods. Using deidentified longitudinal annual school children health check data from three major cities in Vietnam, this study linked a baseline height and BMI for age Z score near age 6 to outcome visits near age 12 or 15 in 4,857 children. A linear quantile regression and a pooled quantile generalized additive model, fit by sex, were compared against a linear benchmark and a naive persistence model on a held out test set, using pinball loss, interval coverage, and width against the WHO 90% band. This study also tested adding growth phenotype and checked generalization across the three cities. Results. The pooled model outperformed the discrete quantile regression in every group. Every individualized 90% interval was narrower than the WHO band, by 34.6 to 54.5%. Growth phenotype improved accuracy in most groups. The model generalized well to a held out Hanoi or Haiphong but poorly to a held out Ho Chi Minh City, where coverage fell to between 0.35 and 0.52, though the all-city model stayed well calibrated for Ho Chi Minh City itself. Conclusion. Conditional quantile modeling gives individualized growth predictions markedly narrower than a fixed population reference and gains further from growth phenotype, but needs local validation before use at an unrepresented site.

Background: Artificial intelligence (AI) is increasingly used in healthcare, but data on its real-world use and perceptions among obstetricians and gynecologists remain limited. Objectives: To assess familiarity, use, perceptions, and expectations regarding AI among physicians practicing obstetrics and gynecology in France. Study Design: We conducted a cross-sectional survey between June 2 and July 30, 2025, mainly distributed through professional organizations or associations and social media. Participation was voluntary and self-selected. AI use was defined as any use of an AI tool in routine clinical practice, regardless of type or frequency. Comparisons were made between AI users and non-users and between junior and senior physicians. Results: Among 469 respondents, representing approximately 5% of the target population, 199 of 466 (42.7%) reported AI use in practice; three respondents were excluded from this analysis because of discordant questionnaire responses. AI use was associated with male gender and professional status, with residents more represented among users. Junior physicians reported greater AI use than senior physicians and expressed greater concern regarding medical confidentiality. Current applications primarily involved administrative tasks, medical writing, literature retrieval, and translation; anticipated future uses centered on clinical decision support and medical data interpretation. Perceptions of several AI applications differed between groups. Conclusions: AI was reported to be used by a substantial proportion of respondents, primarily for supportive and informational tasks. These findings support further evaluation of training, validation, governance, and safe implementation of AI in obstetrics and gynecology.

Background: Knowledge translation (KT) is essential for ensuring that research evidence informs policy and practice. However, little is known about researchers' intentions to engage in KT activities or their relationship with conventional bibliometric indicators. This study aimed to (1) assess researchers intentions to engage in KT activities using a questionnaire informed by the Theory of Planned Behavior (TPB), and (2) examine the association between these intentions and individual bibliometric indicators. Methods: A cross-sectional survey was conducted among faculty members at Tehran University of Medical Sciences. A questionnaire informed by selected constructs of the TPB was developed to assess researchers intentions to engage in activities across the seven components the action cycle of Knowledge-to-Action (KTA) framework. The instrument was validated through several rounds of expert review and then with a sample of potential participants. Bibliometric indicators (H-index, Number of Publications, Number of Citations, First-Author Publications, Corresponding Authorship, International Publications and Self-Citations) were extracted from the national academic registry. To assess representativeness, bibliometric characteristics of respondents were compared with those of a random sample of non-respondents drawn from the same registry. Confirmatory Factor Analysis (CFA) validated the intention construct, and Structural Equation Modeling examined associations with demographic and bibliometric variables. Results: A total of 143 researchers participated. Intention scores were highest for adapting knowledge to local contexts and identifying barriers and facilitators, and lowest for monitoring and sustaining knowledge use. CFA supported a unidimensional intention construct with favorable model-fit indicators. No bibliometric indicator was significantly associated with KT intention. Age was the only significant predictor. Respondents had stronger bibliometric profiles than non-respondents, indicating potential non-response bias. Conclusions: Researchers reported relatively strong intentions to engage in KT, but these intentions were not associated with conventional bibliometric indicators. Age was the only significant predictor. Overall, findings suggest that traditional academic metrics may not reflect KT intentions and highlight the need to strengthen institutional incentives for KT.

Despite the numerous benefits associated with higher dietary quality, many older Veterans do not meet national dietary recommendations. Existing programs are not typically tailored for older Veterans who may experience physical and environmental limitations that hinder their ability to access and prepare healthy foods. This project piloted the incorporation of age-friendly, tailored, virtual nutrition education into an existing health promotion program for older Veterans. Programming followed an iterative design process over two years. Year 1 included 14 weeks of virtual nutrition education on healthy aging paired with weekly produce bags and recipe suggestions. In Year 2, virtual nutrition education shifted to more hands-on learning emphasizing basic meal preparation and adaptive cooking strategies for mobility limitations. Produce distribution in Year 2 shifted to a farmer's market model, based on feedback from year 1, allowing participants to self-select items. Primary outcomes included program satisfaction, dietary intake assessed via 24-hour recall to calculate the Healthy Eating Index (HEI-2015), and health-related quality of life (PROMIS Global Health). Findings demonstrate the feasibility and acceptability of a virtual nutrition program incorporating age-friendly cooking instruction and adaptive strategies to improve dietary quality among older Veterans.

Preeclampsia is a multisystem hypertensive disorder of pregnancy that emerges after 20 weeks of gestation, and remains a leading cause of maternal and perinatal morbidity and mortality globally, yet evidence on its predictors and outcomes in Kenya remains limited. This prospective cohort study compared pregnant women with and without preeclampsia who attended selected hospitals in Kiambu County, to determine the predictors of preeclampsia and its associated maternal and neonatal outcomes. The results indicated a very strong statistical association between preeclampsia and the following i.e parity, time taken to reach the hospital, hypertension and diabetes mellitus (p-value <0.001) and religion (p-value <0.013). Women with preeclampsia had nearly twice the risk and six times the odds of delivering low-birth-weight infants compared with women without preeclampsia (RR = 1.97; OR = 6.25). A strong statistically significant association was observed between multiparity and prematurity (RR = 5.3, OR = 8.4, p < 0.001). Multiparous women with preeclampsia had approximately 5.3 times the risk and 8.4 times the odds of experiencing a premature birth compared with women without preeclampsia. In conclusion preeclampsia significantly increased adverse maternal and neonatal outcomes, highlighting the need for early high-risk pregnancies identification and strengthened antenatal care to improve both maternal and neonatal outcomes.

Youth are increasingly engaging with generative AI beyond its use as a productivity tool, with a growing share turning to AI for social interaction and emotional support. This leads to unknown risks for their well-being and development. Online community discussions reveal that youth already perceive risks that caregivers have not recognized.

Abstract Background The SYNTAX score (SS) quantifies the severity and complexity of coronary artery lesions and serves as an independent predictor of major adverse cardiovascular events and mortality in patients with acute coronary syndrome (ACS). However, few studies have examined the association between SS and in-hospital cardiac arrest (IHCA) in this population. Therefore, this study aims to elucidate the relationship between SS and the incidence of IHCA in patients with ACS. Methods This study consecutively enrolled 3,224 patients undergoing percutaneous coronary intervention (PCI). Logistic regression and restricted cubic spline (RCS) analyses were employed to examine the association between SS and the incidence of IHCA. Participants were stratified into three groups based on SS: Group T1 (SS ? 10, N = 1,097), Group T2 (10 < SS ? 18, N = 1,089), and Group T3 (SS > 18, N = 1,038). The primary endpoint was the incidence of IHCA. Results The overall incidence of IHCA was 4% (N=147). After adjusting for covariates, SS was significantly associated with the incidence of IHCA in ACS patients treated with PCI (OR = 1.0400; 95% confidence interval (CI) = 1.0200?1.0700; p < 0.001). Compared with the T1 group, the T3 group exhibited an increased risk of IHCA (OR = 2.1800; 95% CI = 1.2900?3.6900; p = 0.0040). Subgroup analyses revealed that, after covariate adjustment, patients with ST-segment elevation myocardial infarction (STEMI) had an increased risk of IHCA (OR = 1.0700; 95% CI = 1.0300?1.1100; p < 0.001). Similarly, both patients with diabetes mellitus (DM) (OR = 1.0400; 95% CI = 1.000?1.0700; p = 0.0270) and those without DM (OR = 1.0600; 95% CI = 1.0200?1.1000; p = 0.0020) showed an increased risk. Furthermore, elderly patients (?60 years) (OR = 1.0300; 95% CI = 1.0100?1.0700; p = 0.0210) and non-elderly patients (<60 years) (OR = 1.0500; 95% CI = 1.000?1.1000; p = 0.0470) had an increased risk, as did male patients (OR = 1.0500; 95% CI = 1.0200?1.0700; p = 0.0020). RCS analysis indicated a dose-response relationship between IHCA incidence and SS (nonlinear p-value = 0.906), with the risk of IHCA increasing when SS exceeded 23.975. Incorporating SS into the baseline risk model improved the predictive value for IHCA incidence in ACS patients undergoing PCI (Net reclassification improvement [NRI]: 0.3537 [0.1906?0.5167], p < 0.001; Integrated discriminant improvement [IDI]: 0.0104 [0.0025?0.0183], p = 0.0097). Conclusions Among patients with ACS undergoing PCI, SS is significantly associated with the incidence of IHCA. Consequently, SS may serve as an effective predictor of IHCA in this population.

Background: Genetic conditions are common in congenital heart disease (CHD) and affect care, but are often missed or diagnosed late. We asked whether routine clinical data can shortlist the most likely genetic conditions. Methods: Retrospective single-center cohort of children with CHD and an echocardiogram who had either a confirmed genetic diagnosis or negative cytogenetic testing and CHD gene sequencing. Echocardiogram images and serial medical record data were added as model inputs in the order they become clinically available. Class balanced logistic regression (LR) and a multimodal deep learning fusion network were fitted to the same inputs at each step. The primary metric was balanced top-3 accuracy (correct diagnosis among the top three, averaged across conditions), with bootstrap intervals. Results: The cohort included 1,720 children (988 with common CHD-associated genetic conditions, 231 rare diagnoses, 501 negative testing). Using only inputs generated at the echocardiogram visit, LR reached a balanced top-3 accuracy 0.758 (chance 0.429). Serial records, radiology notes and ICD-10 codes, raised this to 0.809. Multimodal fusion performed similarly at each stage. With a genetic condition withheld from training, the fusion embedding placed affected children nearest to others sharing a gene group in 0.37 of cases versus 0.10 without the embedding (+0.268 [95% CI +0.242, +0.295]). Conclusions: Routine clinical data available at first echocardiogram can help identify likely genetic diagnoses, and later coded inputs ceiling. Multimodal fusion added no accuracy over LR, but places children sharing a genetic cause near one another, making nearest-neighbor retrieval informative for undiagnosed children.

Background & Aims Personalized nutrition has the potential to improve nutritional intake and clinical outcomes in hospitalized patients by adapting to individual dietary needs and preferences. Despite its promise, no personalized nutrition product (PNP) for hospitalized patients is currently available. This study aimed to assess the acceptability of PNPs among hospitalized patients and hospital staff. Methods A prospective, ten-days, proof-of-concept study was conducted among in-hospital adult patients ([&ge;]18y). Study patients received a freshly 3D printed PNP, customized to match individual taste preferences and health profiles. Patients could reorder the product daily if they remained hospitalized >24h after consumption. Consumption was assessed by weighing the PNP before and after consumption. Acceptability, sensory feedback, and overall experience were evaluated using questionnaires. Hospital staff also evaluated sensory feedback and acceptability. Factors influencing consumption and liking among patients were evaluated by testing within-group differences. Correlations between consumption rates, liking and patient characteristics were assessed. Results Eighty-seven patients received 137 PNPs during the study period. The average overall liking score was 5.7 ({+/-}2.1) on a 1-9 scale, and median consumption rate was 51% [Interquartile Range 19-100]. Consumption rates positively correlated with overall liking (R2 = 0.50, p < 0.001). Patients' willingness to reorder was 3.5 ({+/-}2.3) on a 1-7 scale, and reorder rate 63%. The perceived value of a PNP service in a hospital setting (scale 1-7) was scored 5.3 ({+/-}1.7) by patients and 4.5 ({+/-}1.1) by staff. Conclusions PNPs were evaluated as moderately positive in terms of acceptability and value by both patients and staff. However, further optimization of the product is needed before evaluating clinical efficacy.

PurposeRural Alaska relies on air ambulances ("medevacs") to connect remote villages off the road system to higher-level care. Yet medevac decision-making is complicated by limited guidelines, high costs, and delayed transport. We aimed to quantify variability in physician medevac decisions and identify contributing factors. MethodsWe conducted a cross-sectional survey of physicians (n=20) within the Alaska Tribal Health System using 20 clinical vignettes representing varying levels of transport complexity. Participants selected transport modality (medevac, commercial, or remain in village) and rated confidence. Interrater agreement was assessed using Gwets AC1. A generalized linear mixed model evaluated predictors of medevac use. FindingsAgreement was "almost perfect" for clearly critical cases ("always medevac," AC1=0.97) but declined substantially for intermediate scenarios ("possible medevac" AC1=0.39; "never medevac" AC1=0.26; "special considerations" AC1=0.12). Confidence strongly correlated with agreement (r=0.83, p<0.001), forming distinct clusters of high-, medium-, and low-certainty decisions. Vignette type was the dominant driver of medevac use (OR 455.5 for "always medevac"), but decisions did not change with experience (OR=0.99, 0.94-1.04). Between-physician variability persisted after adjustment (ICC 3.8%; MOR 1.67), consistent with differences in risk tolerance. ConclusionsMedevac decision-making is highly consistent in certain clinical cases but interrater agreement is limited for intermediate cases. Without a shared gold standard of "correct" medevac decisions, future clinical decision support cannot rely on automated medevac decision making. Efforts to improve care should focus on deconstructing decisions, enhancing outcome feedback, and developing targeted decision support rather than prescriptive decision models.

Purpose Autistic adults have diverse communication characteristics that are not well captured by standard demographic measures. Communication affects self-determination, relationships, access to healthcare, and services. Characterizing communication differences may improve research and intervention targeting for meaningful subgroups of autistic adults. Methods The Academic Autism Spectrum Partnership in Research and Education (AASPIRE) Outcomes Project team used a community based participatory research (CBPR) approach to develop a self- or caregiver-report module to characterize communication among autistic adults. The 10-item module asks about receptive and expressive communication, literacy, speech reliability, usage of digital communication, use of alternatives to speech, and communication fluency. It can be completed directly, with or without support, or via a caregiver. We used baseline survey data from 844 autistic adults to evaluate the module and derived a five-level variable, Communication Profile, from selected module items to stratify participants. We examined completion feasibility, response consistency, and construct validity. We also assessed test-retest reliability in a 15% random subsample who completed a 2-week retest following the 6-month survey, with oversampling of caregiver-report respondents. Results The Communication Characteristics module demonstrated high completion feasibility, minimal systematic error, and strong construct validity. The Communication Profile variable stratified participants into five meaningful communication profiles and demonstrated strong construct validity and substantial test-retest reliability ({kappa} = .69). Conclusion The Communication Characteristics module and Communication Profile variable provide a valid approach for characterizing communication diversity among autistic adults for research, clinical, and service settings. The full AASPIRE Measurement Toolkit is available at https://aaspire.org/measurement. Lay Summary Autistic people communicate in many different ways, and their communication may change in different situations. We developed and tested a set of survey questions to describe an individuals communication. We also used the results to describe 5 groups of autistic people based on how they communicate, without treating these groups as different types of autism.

Background Owing to a growing body of evidence, clinical guidelines now recommend exercise for stroke survivors. However, many stroke survivors are physically inactive and may need more support to engage with exercise in the community. There are between 600-800 exercise referral schemes in the United Kingdom, but engagement from stroke survivors is very low. This study aimed to evaluate the accessibility of exercise referral schemes in England to stroke survivors. Methods A cross-sectional, online survey was conducted throughout England. All 317 local authorities in England were invited to participate. Geospatial mapping was used to visualise the accessibility of exercise referral schemes across England. Data on scheme design and delivery parameters were analysed descriptively. Results Data were collected from 147 local authorities. Exercise referral schemes were offered in 134 local authorities, of which, stroke survivors were able to access 128. However, stroke-specific schemes were available in only 17 local authorities. Significant variations in exercise referral scheme design and delivery were identified across the country. Only two consistencies were found between schemes: the involvement of fitness instructors, and the lack of transport provision. The capacity of exercise referral schemes did not correlate with the general population, stroke population, or stroke prevalence within a local authority. Conclusions Exercise referral schemes are widely available across England, and the majority are open to stroke survivors. However, stroke-specific services are very limited and there is substantial variation in scheme eligibility, capacity, costs, and referral pathways. These inconsistencies, paired with the lack of transport provision, may explain the low uptake of exercise referral schemes within the stroke population.

Background: Social vulnerability is associated with adverse health outcomes, but existing social vulnerability indices often rely on cohort-based and self-reported data, potentially limiting their population-level applicability. Therefore, this study aimed to develop an SVI from routinely collected electronic health records (EHRs) using natural language processing (NLP) and examine its association with mortality and healthcare utilization. Method: EHR data from 193,629 individuals aged 35 to102 from the Wellbeing Services County of Central Finland between years 2010 and 2023 were used in this study. A 6 item SVI (total score 0 to 6) was developed from free-text clinical notes using deep-learning-based NLP. SVI scores were calculated at baseline and annually for individuals. Associations between baseline SVI and all cause mortality and healthcare utilization were assessed over 12-year follow-up using Cox and count models. Results: The mean baseline SVI among all participants was 0.35 (range 0 to 6). Women had higher SVI (0.39) than men (0.32, p<0.001). SVI increased with age. One unit increase in SVI was associated with a higher risk of mortality (Hazard Ratio (HR) 1.23; 95% Confidence Interval (CI) (1.21 to 1.24), a higher odds of using healthcare services (Odds Ratio (OR) = 1.20; 95% CI): 1.19 to 1.21) and a greater healthcare service use (Incidence Rate Ratio (IRR) = 1.07; 95% CI: 1.06 to 1.07). Discussion: An index capturing multiple domains of social vulnerability can be derived from EHRs using NLP. Higher SVI was associated with increased mortality and healthcare utilization. These findings support the potential of EHR data for assessing social vulnerability and related health risks.