Canadian Medical Association Journal

Background and ObjectivesSkilled nursing facility (SNF) hospitalization rates vary substantially across facilities serving comparable patient populations, yet the organizational factors underlying high performance remain poorly characterized. This study examines whether faith or mission-driven organizational identity is associated with lower-than-expected hospitalization rates in a national sample of Medicare-certified SNFs. DesignCross-sectional analysis of a stratified random sample of 618 Medicare-certified SNFs, drawn from a national cohort of 13,419 facilities with claims-based quality data. Facilities were classified by organizational identity (faith-affiliated, purpose-driven, or secular) using publicly available records. Performance was measured using CMS claims-based hospitalization and emergency department transfer rates adjusted for expected rates given patient case mix. Setting and ParticipantsMedicare-certified skilled nursing facilities in the United States, February 2026 CMS release. MethodsWe computed a composite performance gap as the mean of four z-scored observed-minus-expected measures (short-stay and long-stay hospitalization and ED transfer rates). We tested the association between faith affiliation and performance using Fishers exact test, logistic regression, OLS regression, propensity score matching, and causal mediation analysis. ResultsFaith-affiliated or purpose-driven facilities constituted 14.7% of significant overperformers (95% CI: 7.0-23.5%) and 0% of significant underperformers (95% CI: 0.0-4.4%), a monotonic gradient confirmed across all five performance zones. After propensity score matching on facility size, ownership type, and urbanicity (n=49 matched pairs), faith-affiliated facilities achieved 18.2% short-stay rehospitalization compared to 21.7% for matched secular facilities (3.5 percentage points fewer, p=0.019), and 1.30 long-stay hospitalizations per 1,000 resident-days compared to 1.71 (0.41 fewer per 1,000 days, p=0.019). Faith affiliation was associated with 61% more RN staffing hours per resident per day (0.96 vs. 0.60 hours, p<0.001), and formal mediation analysis confirmed that RN staffing hours substantially mediated the relationship between faith affiliation and hospitalization performance. Conclusions and ImplicationsFaith and mission-driven organizational identity is associated with superior hospitalization performance in a national SNF sample, mediated by elevated RN staffing intensity. These findings suggest that organizational culture and values are modifiable upstream determinants of nursing home quality, with implications for quality improvement, workforce policy, and value-based payment design.

Background: Health-related social needs (HRSNs), particularly housing instability, are significant drivers of poor health outcomes among Medicaid populations. New York State's Social Care Networks (SCNs) aim to systematically connect members to housing services through coordinated referral systems. However, limited systematic analysis of referral patterns hinders quality improvement efforts. We analyzed housing referral outcomes and workflows to identify barriers to successful service connections. Methods: We conducted a mixed-methods quality improvement study at Public Health Solutions' WholeYouNYC SCN Coordination Center. Quantitative analysis examined 4,258 housing referrals submitted between June 2025 and January 2026, extracted from the Unite Us platform via Power BI dashboard. We calculated acceptance rates, analyzed time metrics, and examined outcomes by receiving organization. Qualitative data were collected through structured consultations with 7 staff members (5 navigators, 2 supervisors) and review of internal workflow documentation. Process mapping identified workflow bottlenecks. Results: Of 4,258 housing referrals, only 45% (n=1,936) were accepted by receiving organizations, while 19% (n=815) were rejected and 32% (n=1,382) remained awaiting response with no recorded action. Average time to acceptance was 8 days for accepted referrals. Acceptance rates were consistent across top receiving organizations (44-46%), suggesting systemic rather than partner-specific barriers. Analysis of unresolved referrals revealed prolonged cases, with the longest pending 271 days. Three critical workflow bottlenecks were identified: CBO response delays, missing housing documentation, and challenges with client engagement. Conclusions: Low housing connection rates (45%) and prolonged unresolved referrals (up to 271 days) indicate systemic barriers requiring interventions at multiple levels. Recommendations include establishing CBO response time benchmarks, implementing automated follow-up protocols, standardizing documentation requirements, and enhancing real-time data monitoring. These findings provide an evidence-based framework for quality improvement in social care coordination programs.

Objective: Readmissions to the PICU are associated with increased morbidity and mortality. A prediction model that can identify children at risk of readmission at the time of transfer can allow providers to intervene and potentially improve patient outcomes. The objective of this study was to derive and validate machine learning models to predict PICU readmission at the time of transfer. Design: Retrospective observational cohort study Setting: Three quaternary care PICUs in the city of Chicago Patients: All children admitted to the PICU between 2012 and 2019. Measurements: The primary outcome was unplanned readmission to the PICU within 48 hours of transfer to the inpatient ward. Predictor variables included vital signs, patient characteristics, and laboratory results. We developed and externally validated four models to predict PICU readmission: logistic regression, elastic net, random forest, and XGBoost. Main Results: This study included 35,601 patients, with readmission rates ranging from 2.2-3.7% by site. The performance of models during internal validation was consistent at the three sites, with the area under the receiver operating characteristic (AUC) values between 0.70 and 0.73 and no difference across the four models. Model performance decreased significantly during external validation (AUCs of 0.60-0.69). The variables most important to the prediction differed at each site. Conclusion: Machine learning models for predicting readmissions to the PICU have limited generalizability. Locally derived models demonstrated modest performance in our study and could potentially inform provider decision-making if prospectively validated. Externally developed models are unlikely to perform well at predicting PICU readmissions.

Background Cardiovascular-kidney-metabolic (CKM) syndrome integrates adiposity, metabolic risk, kidney dysfunction, and cardiovascular disease in a prevention-oriented framework. National estimates across 1999-2023 NHANES and future burden remain limited. Methods We analyzed US adults aged 20 years from 11 NHANES cycles, 1999-2000 through August 2021-August 2023. CKM stage 0-4 was assigned using harmonized examination, laboratory, medication, and questionnaire data. Prevalence was survey-weighted and standardized to the 2010 US Census adult population. Decade trends used survey-weighted logistic regression adjusted for age, sex, and race and ethnicity. Exploratory 2040 and 2050 projections combined NHANES prevalence models with US Census projections under population-aging-only, trend-continuation, and risk-improvement scenarios. Results Among 62,890 eligible adults, 62,888 had sufficient CKM data. In 2021-2023, age-standardized prevalence was 87.9% (95% CI, 86.5%-89.4%) for CKM stage 1 and 62.0% (95% CI, 60.1%-63.8%) for stages 2-4. Stage 2 accounted for 50.1% (95% CI, 48.2%-51.9%) and stages 3-4 for 11.9% (95% CI, 11.0%-12.7%). From 1999-2000 to 2021-2023, any CKM increased by 4.6 percentage points (95% CI, 2.4 to 6.9; P<0.001), whereas stages 2-4 changed by 2.1 percentage points (95% CI, 5.1 to 0.8; P=0.156). In adjusted decade models, any CKM increased (OR, 1.28; 95% CI, 1.19-1.38; P<0.001), while stages 2-4 showed no significant linear trend (OR, 0.95; 95% CI, 0.89-1.01; P=0.084). Excess adiposity and diabetes increased, dyslipidemia declined, and hypertension, chronic kidney disease, and clinical cardiovascular disease were stable. With population aging alone, projected stages 2-4 burden rose from 164.8 million adults in 2023 to 193.7 million in 2050; under risk improvement, it was 147.7 million. Conclusions CKM syndrome remained highly prevalent among US adults. Although later stages did not increase significantly, population aging may expand the absolute care burden unless broad risk improvement occurs.

BackgroundCase-based infectious disease surveillance is subject to ascertainment bias when testing intensity varies across time and population subgroups. We previously developed a regression-based test adjustment methodology using Standardized Testing Ratios (STRs) to correct for differential testing patterns in COVID-19 surveillance data. Wastewater-based surveillance (WWS) measures viral burden in the community independently of diagnostic testing behavior, making it a valuable external validation tool for test-adjusted case estimates. MethodsWe analyzed 111 weeks of paired wastewater and case surveillance data from Ontario, Canada (July 19, 2020 to August 28, 2022). Wastewater SARS-CoV-2 signals from 107 sewersheds across 34 public health units were normalized within sewersheds and aggregated using population-weighted averages. We compared wastewater correlations with crude reported and test-adjusted case counts using Spearman rank correlations, linear regression, and negative binomial distributed lag nonlinear models (DLNM), stratified by epidemic period. ResultsTest-adjusted cases correlated substantially more strongly with wastewater signals than crude reported cases overall (Spearman {rho} = 0.849 vs. 0.679; linear R{superscript 2} = 0.609 vs. 0.191). The advantage of test adjustment was greatest during the Omicron wave, when population-level diagnostic testing contracted sharply following PCR eligibility restrictions ({rho} = 0.924 vs. 0.604; R{superscript 2} = 0.815 vs. 0.470). DLNM incorporating the wastewater signal explained substantially more variance in test-adjusted than crude reported cases (McFadden pseudo-R{superscript 2} 0.898 vs. 0.776), despite similar lag-response structure for both outcomes. ConclusionsWastewater surveillance provides compelling independent validation of a previously described test adjustment methodology for COVID-19 case surveillance. The agreement between wastewater signals and test-adjusted cases was strongest precisely when testing scarcity was most severe, supporting the use of test adjustment to recover accurate infection dynamics from case surveillance data during periods of changing testing access and policy.

Background Non-vitamin K antagonist oral anticoagulants (NOACs) are the guideline-recommended standard for stroke prevention in atrial fibrillation (AF), yet bleeding risks limit real-world adherence. Percutaneous left atrial appendage closure (LAAC) offers a mechanical alternative without definitive comparative synthesis. Objectives To evaluate percutaneous LAAC versus NOAC therapy by synthesizing all contemporary NOAC-era randomized controlled trials (RCTs). Methods Five databases and registries (PubMed, MEDLINE, Embase, Cochrane CENTRAL, ClinicalTrials.gov) were searched from inception to 8 May 2026 for RCTs comparing percutaneous LAAC against NOACs in adults with non-valvular AF. Risk of bias was assessed using Cochrane RoB 2. Ischemic stroke was pooled using a random-effects DerSimonian-Laird model; primary efficacy composite and non-procedural bleeding were evaluated via pre-specified narrative synthesis. Results Four RCTs (CHAMPION-AF, OPTION, PRAGUE-17, CLOSURE-AF) comprising 5,890 patients were included. LAAC achieved noninferiority for the primary efficacy composite in three trials and demonstrated a statistically significant 45-56% reduction in non-procedural bleeding across the three moderate-risk trials. CLOSURE-AF did not meet noninferiority but retained a directionally consistent bleeding reduction. Pooled ischemic stroke analysis (HR 1.31; 95% CI 0.96-1.80; I^2=0%) showed no statistically significant increase in stroke risk, though a consistent directional trend toward more ischemic events was observed. Conclusions LAAC significantly reduces non-procedural bleeding in moderate-risk AF patients, though this benefit attenuates in very high-risk populations. A consistent, statistically nonsignificant ischemic stroke trend and population-dependent efficacy establish LAAC as a shared decision-making alternative to NOACs rather than a universal replacement, pending 5-year CHAMPION-AF data.

BackgroundDischarge destination after acute ischemic stroke has implications for functional recovery and healthcare costs. Individuals discharged to inpatient rehabilitation facilities (IRFs) achieve better outcomes than those discharged to skilled nursing facilities (SNFs); however, many patients discharged to IRFs and SNFs have similar clinical profiles. We examined non-clinical factors associated with discharge location after acute ischemic stroke. MethodsPopulation: 236 adults hospitalized with acute ischemic stroke, living independently in the community prior to admission, and discharged to either an IRF (n=171) or SNF (n=65). Clinical variables: NIHSS, Charlson Comorbidity Index (CCI), acute care length of stay (LOS), functional status (AM-PAC "6-Clicks"), and neglect. Non-clinical variables: age, sex, race, marital status, insurance, home layout, living status, and available assistance. Associations with discharge location were evaluated using univariable and multivariable logistic regression and reported as odds ratios (OR) with 95% confidence intervals (CI). ResultsIndividuals discharged to IRFs were younger, more likely to cohabitate, and had shorter LOS than those discharged to SNFs. Functional status (AM-PAC) and comorbidity burden (CCI) did not differ significantly between groups despite differences in discharge destination. In univariable models, younger age, cohabitating marital status, living with family, available assistance, shorter LOS, private insurance, and higher NIHSS were associated with greater odds of IRF discharge. In multivariable analysis, younger age (OR 0.94, 95% CI 0.91-0.98), cohabitating marital status (OR 2.46, 95% CI 1.13-5.48), and shorter LOS (OR 0.88, 95% CI 0.82-0.93) remained independently associated with IRF discharge. ConclusionsIndividuals with comparable pre-stroke independence and similar clinical severity, discharge to IRF versus SNF was independently associated with non-clinical factors; age, marital status, and LOS, whereas stroke severity and functional status were not significant predictors. These findings underscore the importance of evidence-informed discharge criteria integrating clinical indicators and social context to support equitable access to intensive rehabilitation after stroke.

Lead is a toxic metal ubiquitous in our environment. While dramatic reductions in lead sources have paralleled equivalent decreases in lead-poisoning rates, chronic lead exposure remains a critical public health concern. Childhood lead exposure (at its lowest levels) is liked to changes in cognitive development but less is known about lead's effects on children's brain structure, especially as a result of in utero exposure. We measured prenatal and early-postnatal lead exposure in shed deciduous teeth of 448 9- and 10-year-old children (from 20 United States cities) and linked those lead levels to childhood brain structure, cognition/behavior, and neighborhood- and family-level socioeconomic characteristics. Here we show negative associations between tooth-lead levels and the thickness of the brain's cortex, particularly in regions linked to language processing. With increasing tooth-lead levels, children of lower-income (versus higher-income) families showed steeper declines in receptive vocabulary. Caregiver-reported behavioral problems exhibited similar associations. With in utero exposure linked to adverse neurodevelopmental outcomes (well before lead exposure and its risks are evaluated by healthcare professionals), prenatal screening of maternal lead levels/exposure, coupled with recommended strategies to reduce its placental transmission, may help reduce lead's effects on future generations.

Introduction. Practice coaching is increasingly used to strengthen quality improvement (QI) capacity in primary healthcare (PHC) systems in low and middle income countries (LMICs), yet the causal pathways through which it shifts provider behaviour, and the systemic conditions that enable or constrain those pathways, remain under theorised. Using a theory based qualitative evaluation, we examined how and why a practice coaching intervention influenced QI in cervical cancer screening (CCS) and antenatal care (ANC) within Honduras decentralised PHC system during the third phase of the Salud Mesoamerica Initiative (SMI). Methods. We conducted a within case explanatory case study. A programme theory was reconstructed before data collection and iteratively refined against evidence. Data comprised semi structured interviews with 11 midlevel managers, 6 PHC team medical leads, and 2 regional managers, complemented by direct observation and document review. We applied combined deductive and inductive coding, thematic analysis, and pattern matching, and reporting per COREQ. Results. We identified four causal patterns that refined the initial programme theory. Three were activated pathways: (1) novel professional identity among participating managers; (2) collective efficacy and data driven learning, sustained through verifiable progress on observable indicators, strong for CCS but null for ANC, where outcomes were less attributable to teams actions; and (3) relational coordination, psychological safety, and trust, which provided the interpersonal basis for the first two. A fourth, unanticipated pattern showed structural misalignment between coaching enabling, learning based logic and the directive, punitive logic of Honduras performance based contracting environment, confining gains to localised enabling bubbles. Conclusion. Coaching can activate meaningful QI pathways in LMIC primary care, but sustained, equitable impact requires deliberate alignment between coaching learning oriented principles and the institutional performance management architecture, and matching of coaching investment to clinical processes with observable, attributable outcomes.

Effective hypertension management depends on sustained engagement with primary care, and there is a need to understand the magnitude and determinants of follow-up loss in real-world primary care. We analyzed electronic health record (EHR) data from 26,541 patients with hypertension across primary care practices participating in the EvidenceNOW quality-improvement initiative. We characterized retention in care, longitudinal blood pressure (BP) control, and predictors of loss to follow-up using descriptive statistics, cumulative retention curves, and multivariable Cox proportional-hazards regression. At baseline, mean systolic and diastolic BP were 140.0 {+/-} 20.6 and 84.7 {+/-} 13.0 mmHg, respectively; only 10.7% (95% CI 10.4-11.1) of patients had controlled BP and 18.1% never returned for any follow-up visit. Among the 21,729 patients who had [&ge;]1 follow-up encounter, retention declined steeply over time--from 59.9% at 6 months to 16.3% at 36 months. Patients identifying as Black/African American (adjusted hazard ratio [aHR] 1.44; 95% CI 1.33-1.56), Hispanic/Latino (aHR 1.43; 1.35-1.52), or Other race/ethnicity (aHR 1.50; 1.41-1.59) had significantly higher hazards of being lost to follow-up than White patients, whereas older age, female sex, comorbid diabetes, heart failure, chronic kidney disease, stroke, and baseline BP control were each independently protective. Among patients retained for at least 12 months, BP control rose to 63.7% and remained near 64-66% through 36 months. These findings reveal a substantial and inequitable longitudinal care-engagement gap that is likely a principal driver of suboptimal hypertension control in the United States and identify actionable demographic and clinical targets for primary-care retention interventions.

ObjectiveLeukemic and hematopoietic cell transplant patients have one of the highest incidences of C. difficile infection (CDI). While CDI patients are considered the primary source of transmission, asymptomatic colonized patients (AC) can progress to CDI or contribute to in-unit transmission. We aim to quantify the roles of CDI and AC patients in C. difficile importation and transmission within oncological units. DesignProspective cohort study SettingTwo leukemia and HCT transplant units in a large tertiary care hospital in the US MethodsWe developed a stochastic, individual-based network model to simulate C. difficile acquisition and transmission. Data from cultures and nucleic acid amplification testing (NAAT) obtained at admission and weekly, and toxin enzyme immunoassay (EIA) tests used for CDI diagnosis were used to calibrate the model. Healthcare worker room assignments informed the network structure. Key parameters were estimated via particle filtering. ResultsThe model reproduced observed weekly test counts and transmission pairs. AC patients were the primary source of new colonizations: 51% were due to importation (of those, 88% were admitted as AC), and 49% were due to transmission (AC was the source in 92% of transmissions). Sensitivity analysis showed that these findings were most influenced by the colonization rate and rates of environmental contamination and cleaning. ConclusionsThese findings reinforce the role of AC, particularly via admission importation, in sustaining C. difficile transmission in high-risk hospital settings. Infection control focused on CDI effectively reduced onward transmission, as indicated by CDIs low contribution to new colonizations.

OBJECTIVE: Bladder cancer (BC) is predominantly a disease of older, comorbid adults, and radical cystectomy (RC), which is the gold standard treatment, carries considerable morbidity. We sought to determine the impact of baseline dementia and frailty on the care trajectory beyond the immediate postoperative period. We hypothesized that frail patients and those with dementia undergoing RC for BC will have poorer care trajectories. METHODS AND MATERIALS: We identified Medicare beneficiaries [&ge;] 66 years old who underwent RC for BC in 2017 with 12 months of pre- and post-RC enrollment. Frailty and dementia were characterized using validated, claims-based measures. Associations between baseline frailty and dementia with postoperative care trajectory outcomes were determined using Fine-Gray competing risk models. RESULTS: We identified 3,600 beneficiaries of whom 11.6% were frail and 3.4% met criteria for dementia. Patients with dementia were more likely to be frail, comorbid, and not receive standard-of-care neoadjuvant chemotherapy. Frailty was independently associated with [&ge;] 2 transitions in care level after index discharge from RC and skilled nursing facility (SNF) admissions within 1 year of RC, exposure to intensive post-RC interventions, including dialysis and feeding tube placement, and poorer survival. Dementia remained associated with SNF admissions regardless of frailty level. CONCLUSIONS: Among a contemporary cohort of older adults undergoing RC for BC, preoperative dementia and frailty were independently associated with poorer care trajectory beyond the immediate postoperative period after RC. Our work highlights a role for preoperative geriatric assessment in identifying and optimizing patients at greatest risk.

Background: In-laboratory polysomnography (PSG) remains the diagnostic reference standard for sleep disorders but is resource-intensive and capacity-constrained. Limited-channel home sleep apnea testing (HSAT) improves access and reduces costs compared to in-laboratory polysomnography, but underestimates disease severity due to its inability to measure true sleep time and cannot identify non-respiratory sleep disorders including periodic limb movement disorder and parasomnias.1-5 Comprehensive home polysomnography (hPSG) may preserve diagnostic fidelity while reducing system costs, improving access for patients unable to attend laboratory-based studies, and shortening time to diagnosis and therapy initiation. Objective: To estimate the short-term budget impact to a U.S. commercial health plan of substituting an appropriately selected proportion of in-laboratory PSG with comprehensive hPSG using the Onera Sleep Test System (STS). Methods: We developed a transparent budget impact model following ISPOR good practice guidelines for a hypothetical 1-million-member commercial plan. The model estimates the annual diagnostic population (top-of-funnel) using age- and sex-stratified prevalence, an undiagnosed fraction of 85%, symptom prevalence among undiagnosed individuals (30%), and an annual testing rate (12%).2-3 Baseline costs reflect current diagnostic pathways using HSAT (50% first-line) and in-laboratory PSG (50% first-line), including HSAT-to-PSG escalations (20%) and PSG repeats (4%). The intervention scenario substitutes a defined share of in-laboratory PSG and selected HSAT with Onera hPSG. Scenario and sensitivity analyses explore parameter uncertainty. Results: In the base case, approximately 4,364 individuals entered the OSA diagnostic workflow annually. Baseline diagnostic costs were estimated at $6.23 PMPM, comprising $5.45 million in PSG costs and $0.79 million in HSAT costs. Introducing Onera hPSG (30% PSG replacement, 5% HSAT replacement in Year 1) reduced per member costs to $5.66 PMPM, yielding net savings of $0.57 PMPM ($567,262 annually). In Year 3 scenarios (60% PSG, 10% HSAT replacement), savings increased to $1.64 PMPM (approximately $1.64 million annually). Sensitivity analyses demonstrated net savings ranging from $0.03 to $8.05 PMPM, depending on adoption levels. Conclusions: Partial substitution of in-laboratory PSG with Onera hPSG may yield incremental budget savings for U.S. commercial payers while maintaining access to full polysomnographic assessment. Results support further payer-specific analyses incorporating real-world utilization and downstream outcomes. Keywords: obstructive sleep apnea; polysomnography; home sleep testing; budget impact analysis; health economics

Objectives: To evaluate if direct access to a Pregnancy Early Access Center (PEACE) improves the timeliness and efficiency of pregnancy loss care. Methods: We conducted a retrospective cohort study of patients diagnosed with EPL from January 2017 to December 2022 within a single healthcare system. We included EPL patients treated with procedural or medication management who had been assessed for a related early pregnancy complaint in the thirty days prior. The exposure was direct utilization of PEACE (yes/no) between first EPL symptom visit and EPL management. The primary outcome was "care latency" defined as days from initial presentation for concerning early pregnancy symptoms to initiation of active management. Secondary outcomes included "care continuity," the number of care teams encountered, "care efficiency," the number of patient encounters, and the type of EPL management received. Results: The evaluable cohort included 2151 individuals, with 36.5% patients of Black race and 30.3% publicly insured. A total of 885 (41.1%) received any EPL care at PEACE and 246 (11.4%) initiated their care at PEACE. Patients initiating care through PEACE experienced a 5-day reduction in care latency compared to patients who did not access PEACE. Adjusting for age, race, and insurance type, patients whose index EPL visit was with PEACE initiated their treatment twice as quickly as those who never saw PEACE (aHR 2.36 [95% CI, 2.05-2.71]). Care efficiency (median 2 [1-3] encounters) and care continuity (median 4.5 [4-7] care teams) were also improved by an index visit with PEACE when compared with controls (3 [2-4] and 6 [4-8] p<0.01), respectively). Conclusions: The Pregnancy Early Access Center (PEACE) model is associated with reduced care latency and improved efficiency and continuity when compared with routine care. PEACE reduces barriers to timely, patient-centered early pregnancy care.

Objective: Alzheimer's disease (AD) is a leading cause of death and disability, and treatment options for Alzheimer's disease and related dementias (ADRD) remain limited. We applied a data-driven, mechanism-agnostic Medication-Wide Association Study Plus (MWAS+) framework to identify candidate medications associated with ADRD using longitudinal electronic health record data and explainable artificial intelligence (AI). Methods: We used Veterans Health Administration electronic health record data from January 1999 to May 2022. The initial study population comprised 8,424,715 Veterans aged 65 years or older. Cases were defined by ADRD-related diagnosis codes or ADRD-related medication prescriptions, and controls were free of ADRD diagnosis and ADRD-related medication use. After exclusions and matching on sex, race, age at first encounter, and duration of follow-up, the primary analytic cohort included 505,817 matched case-control pairs (1:1; 1,011,634 Veterans). Longitudinal features were extracted from historical data up to 1 year before the index date and aggregated into 1-year intervals. We developed an upgraded Hybrid Value-Aware Transformer (HVAT 2.0) to jointly learn from longitudinal and nonlongitudinal clinical data while incorporating numerical values associated with clinical concepts, including cumulative medication dose. To enhance interpretability, we applied a medication-specific impact score method to estimate model-derived associations between medication exposure and ADRD risk. Findings: The model demonstrated stable performance across data partitions, with area under the receiver operating characteristic curve values of 0.791 in the training set, 0.772 in the validation set, and 0.775 in the testing set. Metolazone and varenicline were identified as the top 2 candidate medications with negative impact scores, suggesting potentially protective associations with new-onset ADRD. The impact score was -0.196 per unit of cumulative dose for metolazone (1800 mg) and -0.134 per unit for varenicline (280 mg). Although individual-level impact scores varied, most exposed patients had negative scores, including 12,020 of 12,480 metolazone users (96%) and 8,341 of 8,786 varenicline users (95%). Implications: This study demonstrates the feasibility of combining a medication-wide association framework, longitudinal dose-aware modeling, and explainable AI to identify candidate medications for ADRD from real-world electronic health record data. The findings should be interpreted as signals for hypothesis generation rather than evidence of causality. This framework may support prioritization of repurposing candidates for expert review, follow-up cohort validation, and future clinical investigation.

Objective: Hispanic/Latinx populations in the U.S. experience higher rates of chronic disease linked to physical inactivity, yet digital health interventions remain largely inaccessible to more than 16 million Hispanic/Latinx adults with limited English proficiency. While large language models (LLMs) offer scalable personalization, their use in non-English behavioral coaching is unexplored. This study introduces MHC-Coach-ES, a Spanish-language LLM fine-tuned on the Transtheoretical Model (TTM) of behavior change. Materials and Methods: We fine-tuned Llama 3-70B-Instruct using a two-stage pipeline. First, the model was adapted to Spanish health and motivational language using a 2.21-million-token corpus. Second, it was instruction-tuned on 3,268 translated human written messages to align the model with the Transtheoretical Model (TTM) of Behavioral Change. We compared MHC-Coach-ES with Llama 3-70B-Instruct and translated human-expert messages using a forced-choice preference survey (N = 77) and blinded expert review (N = 2). Results: Spanish-speaking participants significantly preferred MHC-Coach-ES messages over translated human-expert messages (81% preference, P<0.001). Linguistic analysis showed that MHC-Coach-ES produced more temporally anchored messages than the base model (65% vs. 20%), while maintaining readability. In blinded evaluation, clinical experts rated MHC-Coach-ES higher for alignment with Transtheoretical Model stages than human-expert messages (4.83 vs. 4.38 out of 5). The base model also outperformed translated expert messages across preference and expert ratings. Conclusions: Generative AI can operationalize behavioral science frameworks in Spanish, offering a scalable approach to reducing health disparities. The strong performance of both MHC-Coach-ES and the base model highlights the promise of generative and personalized approaches over translation-based localization for theory-driven behavioral interventions.

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.

Background Healthcare-associated infections pose a major burden to neonatal health worldwide and remain difficult to track in low-resource hospitals because patient movement data and pathogen genomic data are rarely integrated into actionable transmission models. Existing approaches are often restricted to specific settings, highly structured electronic health records (EHRs), or analyses focused on either patient movements or pathogen characteristics alone. To address this gap, we developed PathoPath, an open-source integrative modelling platform, and evaluated its utility in a high burden paediatric hospital in Dhaka, Bangladesh. Methods PathoPath is an open-source R package that combines electronic health records with whole genome sequencing data to generate contact networks from direct and indirect contacts using minimal structured inputs. We retrospectively applied PathoPath to 373 cases of Klebsiella pneumoniae species complex (KpSC) infection identified in 2021 at the largest paediatric referral hospital in Dhaka, Bangladesh. Ward level patient movement trajectories were used to reconstruct contact networks, and genomic data from isolates from children <60 days were integrated to identify probable dissemination of bacterial clones and antimicrobial resistance plasmids. Findings PathoPath identified 750 direct contacts among 317 patients, forming 25 connected components, with the largest including 93 patients. KpSC infections were identified across 21 of 37 wards, with the neonatal intensive care unit accounting for 77.9% of all cases. Integration of genomic and network data distinguished sustained clustering of ST147 from multiple probable inter-clonal dissemination events involving IncFII plasmids carrying blaNDM-5 and/or blaOXA-181 within ST16. Four dominant sequence types accounted for 65.6% of sequenced isolates, and carbapenemase genes were detected in 95.8%. Interpretation PathoPath reconstructs hospital-wide contact networks and integrates them with pathogen genomics to map probable dissemination of pathogens and antimicrobial resistance using minimal structured clinical data. It could support more targeted infection prevention and control in hospitals where granular digital records are not available.

Background: Cardiovascular-kidney-metabolic (CKM) syndrome is a leading driver of cardiovascular morbidity and mortality. Whole-body molecular imaging is well-positioned to phenotype such syndromes, yet no imaging biomarker quantifies cumulative CKM burden. Bone scintigraphy with 99mTc-labeled bisphosphonates is widely performed and expanding with transthyretin amyloidosis assessment, under which Perugini grade 0 (absent cardiac uptake) is considered clinically benign. Objective: We hypothesized that the soft tissue-to-bone ratio (STBR) on these scans captures CKM burden and is an independent prognostic biomarker. Methods: We retrospectively analyzed 8,769 consecutive patients without cardiac uptake on 99mTc-DPD whole-body planar scintigraphy. The primary endpoint was all-cause mortality. Secondary endpoints were major adverse cardiovascular events (MACE) and heart failure hospitalization. Cox models were adjusted for ten established cardiovascular risk factors. Imaging-phenotype association (IPA) analysis mapped STBR to 1,210 clinical traits. STBR distribution across CKM stages was assessed in four prespecified analyses, including a non-cancer subgroup. Results: During a median follow-up of 5.1 years (IQR 2.5-8.2), 2,418 deaths occurred. Patients with prespecified STBR >0.5 (n=772, 8.8%) had significantly higher mortality (adjHR 1.73, 95% CI 1.54-1.94, p<0.0001) with an adjHR of up to 3.42 at higher thresholds (95% CI 2.05-5.42, p<0.0001). Hazard increased monotonically with STBR. STBR >0.5 was independently associated with MACE (adjHR 1.51, 95% CI 1.11-2.05, p=0.008) and heart failure hospitalization (adjHR 1.31, 95% CI 1.02-1.67, p=0.03). The association was robust across all prespecified subgroups and sensitivity analyses, including continuous STBR and patients without renal insufficiency. IPA analysis identified significant associations with type 2 diabetes, chronic kidney disease, chronic ischaemic heart disease, heart failure, atrial fibrillation, liver disease, amyloidosis, and hypertension among binary traits, as well as with CRP, NT-proBNP, BUN, cholesterol (inverse), and hemoglobin (inverse) among continuous parameters. STBR increased monotonically across CKM stages in all sensitivity analyses (all p<0.0001). Conclusions: STBR derived from routine 99mTc-DPD bone scintigraphy in patients without cardiac uptake is an independent prognostic imaging biomarker associated with cumulative cardiovascular-kidney-metabolic burden. As an opportunistic measure from scans already acquired at scale, STBR could refine CKM risk stratification at no additional cost, radiation, or acquisition time.

Background Antimicrobial stewardship (AMS) and infection prevention and control (IPC) are complementary strategies to improve patient safety and address antimicrobial resistance (AMR). In low- and middle-income countries (LMICs), they are often implemented separately, reducing effectiveness. Evidence on integrating AMS and IPC in routine hospital practice remains limited. Objective To evaluate the feasibility of an integrated AMS-IPC improvement approach and describe changes in implementation in Vietnamese hospitals. Methods We conducted a multisite quality improvement initiative in four hospitals within the national AMR surveillance network in Viet Nam (March-September 2025). We used US-CDC tools to guide the implementation, including the Global Antibiotic Stewardship Evaluation Tool (G-ASET) and the Infection Control Assessment and Response (ICAR) tool. Baseline assessments were followed by feedback, multidisciplinary action planning, and targeted capacity building. Follow-up occurred 2-5 months later. Changes were analysed descriptively using quantitative scores and qualitative synthesis, and reported following the SQUIRE 2.0 guidelines. Results All hospitals had established IPC programmes at baseline, while AMS maturity varied. G-ASET scores improved across all sites, with greater gains in hospitals starting from lower baselines. Key improvements included leadership and governance, education and training, stewardship actions, and monitoring and reporting. IPC practices aligned with AMS priorities also improved, particularly transmission-based precautions, environmental cleaning, and cross-team coordination. Infrastructure-dependent areas, such as water safety, showed limited short-term progress. Conclusions An integrated AMS-IPC approach using repeated assessment and feedback is feasible and associated with meaningful improvements. This model offers a scalable strategy for strengthening hospital responses to AMR in LMICs and informs national programmes.