Diagnostics

Background: Low-dose computed tomography (LDCT) screening reduces lung cancer mortality but is limited by low uptake and associated with high rates of false-positives and indeterminate-nodules. Breath volatile organic compound (VOC) analysis is a non-invasive candidate biomarker approach that could complement LDCT, but prior work has relied on laboratory-based high-resolution mass spectrometry (HRMS), limiting point-of-care deployment. Methods: In this pilot study, breath samples were collected from 40 patients with treatment-naive, pathologically confirmed non-small cell lung cancer (NSCLC) and 25 lung-cancer-screening-eligible healthy controls. Paired samples were analyzed via a compact point-of-care GC-MS platform (CLARION) and a laboratory HRMS reference. Diagnostic classification models were built independently for each platform using elastic net logistic regression with leave-one-out cross-validation, and performance was evaluated by area under the receiver operating characteristic curve (AUC). Results: CLARION identified 103 VOCs across breath specimens, compared to over 900 identified by HRMS. Despite this difference in panel size, CLARION achieved diagnostic performance nearly identical to HRMS for distinguishing NSCLC cases from controls (AUC 0.864 vs. 0.863). Compared to controls, performance statistics were similar for early-stage NSCLC (AUC 0.854 vs. 0.841) and adenocarcinoma (AUC 0.770 vs. 0.787). VOCs of interest include p-cymene, phenol, propylbenzene, tetradecane, {beta}-ocimene, 2,3-dihydro-indole, and 1-methylthio-(Z)-1-propene. Conclusion: A compact, point-of-care breath GC-MS platform achieved diagnostic performance for NSCLC detection comparable to a laboratory HRMS reference despite a substantially smaller detected VOC panel. These findings support continued development of point-of-care breath VOC testing as a non-invasive, field-deployable complement to LDCT-based lung cancer screening.

Background. In Europe, first-trimester combined screening with the Fetal Medicine Foundation (FMF) algorithm identifies women at increased risk of preeclampsia who may benefit from personalized aspirin prophylaxis. However, a substantial proportion of early-onset preeclampsia (EOPE) remains undetected at clinically acceptable specificity. Objective. To evaluate the first-trimester performance of MaiRa for early-onset preeclampsia (EOPE) risk stratification by benchmarking it against FMF screening in the same women, characterizing discordant patient-level classification profiles and exploring potential implementation strategies. Study Design. This secondary case-control analysis was nested within the prospective, multicentre PREMOM cohort [NCT04990141], which enrolled women with singleton pregnancies across 14 tertiary hospitals in Spain. First-trimester MaiRa and FMF risk estimates were evaluated in the same 126 pregnant women, comprising 99 uncomplicated controls and 27 EOPE cases, defined by disease onset before 34 weeks. Discrimination was compared using a stratified paired bootstrap analysis of the areas under the receiver-operating-characteristic curves. Performance was assessed at prespecified clinical thresholds, and detection rates were evaluated at fixed false-positive rates. Universal and contingent MaiRa implementation strategies were also evaluated. Results. MaiRa showed greater first-trimester discrimination for EOPE than FMF combined screening (AUC, 0.974 vs 0.900; P=.040) and consistently achieved higher detection rates across fixed false-positive rates. At false-positive rates of 5% and 10%, MaiRa detected 85.2% and 92.6% of EOPE cases, compared with 44.4% and 70.4% for FMF, respectively. Patient-level analysis demonstrated that MaiRa identified 12 of 27 EOPE cases (44.4%) classified as low risk by FMF; these pregnancies generally exhibited less abnormal conventional first-trimester profiles, including fewer maternal risk factors, lower mean arterial pressure and lower uterine artery pulsatility index, yet 8 of 12 (66.7%) subsequently developed severe EOPE. Exploratory implementation analyses showed that universal MaiRa screening achieved the highest EOPE detection, whereas a contingent strategy using FMF for triage and reflex MaiRa testing reduced molecular testing to 35.7% of pregnancies while maintaining 77.8% sensitivity and 97.0% specificity. Conclusion. MaiRa provided greater first-trimester discrimination for EOPE than conventional combined screening and detected additional pregnancies that later developed severe disease despite less abnormal conventional screening profiles. The findings suggest that maternal plasma cfRNA profiling captures biological alterations not fully reflected by combined first-trimester screening and support further prospective evaluation in an independent, unselected obstetric population. Key words: early-onset preeclampsia; first-trimester screening; cell-free RNA; liquid biopsy; Fetal Medicine Foundation algorithm; combined screening; risk stratification; aspirin prophylaxis.

Background: High-sensitivity cardiac troponin (hs-cTn) assays enable safe early discharge of patients at very low risk for myocardial infarction. We previously developed a single-sample rule-out pathway using the ARCHITECT hs-cTnI assay to risk stratify patients with suspected acute coronary syndrome. In a secondary analysis of the POC-ET (Point of Care Evaluation of High-sensitivity Cardiac Troponin) study, we evaluated performance of risk stratification with the Alinity hs-cTnI assay. Methods: Patients presenting with possible myocardial infarction in the POC-ET (NCT05665127) study were included. The primary outcome was type 1, 4b or 4c myocardial infarction or cardiac death at 30 days. Cardiac troponin I (cTnI) was measured in stored materials using the ARCHITECT and Alinity hs-cTnI assays. The sex-specific 99th percentile upper reference limit (URL) are 34 ng/L in men and 16 ng/L in women for both assays. Agreement was assessed with Bland-and-Altman limit of agreement method, Passing Bablok regression, and Pearson's correlation coefficient. Distributions of presentation measurements were compared with Kolmogorov-Smirnov test. Performance was evaluated in the overall population and prespecified subgroups. The negative predictive value (NPV) and sensitivity were determined and proportion of patients identified as low, intermediate, and high risk were calculated and modelled using ordinal logistic regression. Results: In 986 patients (60 [51-70] years, 38% female), 78 (7.9%) had a primary outcome. Strong agreement was found in the raw cTnI measurements (99% samples within the Bland-Altman limit of agreement; correlation coefficient r: 0.967 (95% CI 0.964-0.969, P<0.001); Passing Bablok regression: slope 1.12 [1.11-1.13], intercept -0.16 [-0.18 to -0.13]). At presentation, distributions of cTnI measurements by the two assays were similar (P=0.810). Both assays showed comparable diagnostic performance using a risk stratification threshold of <5 ng/L and the sex-specific diagnostic threshold, with the same NPV (Alinity 100 [99.7-100]% versus ARCHITECT 100 [99.7-100]%) and sensitivity (Alinity 100 [97.3-100]% versus ARCHITECT 100 [97.3-100]%). Similar proportions of patients stratified as low- (Alinity 67% versus ARCHITECT 67%), intermediate-risk (23% versus 24%) and high-risk (10% versus 9%) at presentation with minor reclassification. Similar efficacy was observed across subgroups stratified by sex, age, history of myocardial infarction, renal function, and symptom duration. Conclusions: The Alinity hs-cTnI and the ARCHITECT hs-cTnI assays can be used interchangeably in the assessment of suspected myocardial infarction with comparable safety and efficacy.

In primary healthcare centers lacking advanced imaging, community-based active tuberculosis (TB) case finding often relies on basic symptom screening. This approach often misses cases and leads to the inefficient allocation of rapid molecular testing (RMT). We aimed to develop and internally validate a simple clinical triage scorecard to improve TB detection and guide RMT use in resource-constrained settings. We conducted a retrospective cross-sectional study of 15,137 adults ([&ge;]18 years) evaluated within the Zero TB Yogyakarta program (2020-2025). Participants with complete clinical assessments and confirmatory GeneXpert results were included. Using multivariable logistic regression, we identified independent clinical predictors, which were subsequently transformed into an integer-based point scorecard. Model performance was evaluated via discrimination and calibration, utilizing bootstrap resampling (1,000 iterations) for internal validation. Among the 15,137 participants, 251 (1.7%) were GeneXpert-positive. The final multivariable model identified eight independent predictors: age, male sex, body mass index, prolonged cough, hemoptysis, unexplained weight loss, TB contact history, and diabetes mellitus. The model demonstrated strong predictive accuracy, with an optimism-adjusted AUROC of 0.836 and good calibration. When translated to the integer scorecard and compared directly to standard national symptom screening, the scorecard performed (AUROC 0.81 vs. 0.73; p<0.001). At a high sensitivity cut off score of [&ge;] 0, the tool achieved 93.63% sensitivity and 41.33% specificity. This point-of-care clinical scorecard provides higher diagnostic accuracy than standard symptom screening algorithms. By offering flexible operational thresholds, it empowers local health programs to dynamically balance the urgency of case detection with available diagnostic capacity, optimizing GeneXpert allocation where advanced radiological imaging is unavailable.

Background: Plasma phosphorylated tau at threonine 217 (p-Tau217) is a leading blood-based biomarker for Alzheimer's disease (AD). Robust analytical characterization on high-throughput platforms is essential for research use and clinical translation. Objective: To evaluate the analytical performance of an automated plasma p-Tau217 immunoassay and characterize its discrimination of PET-defined amyloid status. Methods: We performed analytical validation of the Access Research Use Only (RUO) plasma p-Tau217 immunoassay on the Beckman Coulter DxI 9000 Access Immunoassay Analyzer and evaluated biomarker discrimination of PET-defined amyloid pathology in a subset of the Bio-Hermes-001 cohort spanning the symptomatic cognitive continuum (mild cognitive impairment or mild AD dementia; cognitively unimpaired participants excluded; n = 449). Analytical precision, sensitivity, linearity, specificity, interference, and sample stability were assessed per Clinical and Laboratory Standards Institute guidelines. Discrimination of PET-defined amyloid status was evaluated using receiver operating characteristic curve and indeterminate zone analyses. Results: The assay demonstrated high precision (within-laboratory CV </=7.1%), excellent sensitivity (limit of detection 0.018-0.021 pg/mL), linearity across the analytical measuring range (R-squared > 0.99), strong epitope specificity (</=1.0% cross-reactivity with other tau phosphoisoforms), and minimal interference from over 60 endogenous and exogenous substances. In 449 research participants plasma p-Tau217 showed strong discrimination between amyloid-positive and amyloid-negative groups (AUC 0.881; 95% CI 0.846-0.915). Application of indeterminate zones systematically improved classification metrics at the cost of fewer definitive classifications. Conclusions: These findings support the Access p-Tau217 (RUO) assay as a robust, high-throughput assay for plasma biomarker-based discrimination of PET-defined amyloid pathology in AD applications.

Objectives To validate two computational fluid dynamics (CFD) models derived from computed tomography angiography (CTA) for estimating trans-stenotic pressure gradients, using invasive intra-arterial pressure measurements as the reference standard in patients with renal artery stenosis (RAS). Background We assessed whether non-invasive assessment of the pressure gradient using CFD could be a reliable alternative to intra-arterial measurements for identifying hemodynamically significant RAS. Methods We performed intra-arterial measurements at rest and during dopamine-induced hyperemia to assess the trans-stenotic pressure gradient in 28 patients with RAS. A pre-intervention CTA scan was used to simulate the pressure gradient with a CFD model using a strategy based on Murray's law (CFD-Mu) and cortical volume (CFD-C). The agreement between the simulated and measured pressure gradients was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis and diagnostic agreement on the presence of a hemodynamically significant stenosis. Results In 20 patients, successful measurements and simulations were obtained. The ICC between measured pressure gradient and the CFD pressure gradient was 0.78 and 0.94 during baseline and 0.86 and 0.72 during hyperemia, for CFD-Mu and CFD-C, respectively. The sensitivity of CFD-Mu and CFD-C was 70% for both models at rest and 100% compared to the hyperemic measurements, whereas the specificity was 90% and 70% at rest and 79% and 72% during hyperemia, respectively. Conclusions The results support the use of individualized CFD simulations for hemodynamic assessment of RAS using CTA as input. The CFD models demonstrated high accuracy for the identification of a hemodynamically significant stenosis.

Background. Videolaryngoscopy still requires adjuncts or hyperangulated rescue in a clinically important minority, and bedside screening discriminates modestly. Point-of-care ultrasound (POCUS) of the anterior airway is a promising alternative, but existing prediction models are opaque or assume a pre-specified functional form. We developed and internally validated a parsimonious, fully disclosed POCUS risk equation whose form is recovered from data and whose structural properties are machine-checked by formal proof - to our knowledge the first formally verified clinical risk predictor - following TRIPOD+AI 2024. Methods. In a prospective single-centre, single-operator cohort of 259 adults undergoing elective videolaryngoscopy (no-Easy airway 68/259, 26.3%), Sequentially Thresholded Least Squares with bootstrap stability selection (B=300) screened a 71-term library of nine POCUS features and retained a seven-term logistic equation; a two-term bootstrap-stable model was pre-specified as robustness analysis. Internal validation used 5x10 repeated cross-validation plus temporal and device hold-outs, with pre-specified overfitting and optimism assessments. Five behavioural properties of the deployed equation were machine-checked in Lean 4. Results. Two interactions met the |c|/sigma_c>2 stability criterion: skin-to-epiglottis x skin-to-hyoid-bone distance and tongue volume x sagittal tongue area. The seven-term equation reached a 5x10 cross-validated C-statistic of 0.966 (optimism-corrected 0.968) and held across temporal and device hold-outs (0.94-0.97). Calibration-in-the-large matched prevalence, with cross-validated slope 0.90 attenuating to 0.625 out-of-time; standard recalibration restored 0.92 without loss of discrimination. The pre-specified two-term robustness model reproduced this performance (C-statistic 0.964-0.968; events-per-parameter 34; shrinkage 0.99), confirming the result is not an artefact of the screening stage. Net benefit over a clinical baseline was positive across 10-50% thresholds. All five Lean 4 theorems compiled without sorry. Conclusions. A sparse, formally verified POCUS equation predicts difficult videolaryngoscopy with high internally validated discrimination and quantified, modest overfitting. Because the equation was developed in a single-operator cohort and its inputs are operator-dependent, external validation requires prior harmonisation of the measurement protocol and operator credentialing.

Background. Urine-based testing offers a promising non-sputum approach for diagnosing paediatric tuberculosis. However, the currently available lipoarabinomannan (LAM) assay shows limited sensitivity in children and is primarily indicated for those living with HIV. Co-detection of LAM with Mycobacterium tuberculosis (Mtb) proteins in urine could provide complementary pathogen-derived biomarkers that improve diagnostic performance. Methods. We developed an ultrasensitive multiplex electrochemiluminescence (ECL) immunoassay to measure Ag85B, CFP-10, ESAT-6, MPT32, and MPT64 in urine. We determined the analytical limits of detection and evaluated the diagnostic performance of individual proteins and LAM using urine samples from children with Confirmed, Unconfirmed, and Unlikely pulmonary tuberculosis enrolled across five high-burden countries (The Gambia, India, Peru, South Africa, and Uganda). Performance was assessed overall, by HIV and nutritional status, and across biomarker combinations. Findings. Urine samples from 630 children were analysed (median age was 4 years [IQR 2-8]; 44% female, 15% living with HIV, 19% underweight, 24% with Confirmed tuberculosis). The ECL assay achieved femtomolar limits of detection (1.5 to 4.0 fM). The sensitivity and specificity of individual Mtb proteins were 12-33% and 98-100%, respectively. Ag85B had the highest sensitivity (33%, 95% CI 26-41) for Confirmed tuberculosis and was similar to LAM. A four-antigen signature (Ag85B, MPT64, MPT32, LAM) was 50% sensitive (95% CI 42-58) and 94% specific (95% CI 90-96), and was significantly more sensitive than LAM alone, in particular among those without HIV. An additional sixteen (10%) of children with Unconfirmed TB had at least one Mtb protein or LAM detected. Interpretation. Multiple Mtb proteins are detectable in paediatric urine with high specificity, and multi-antigen signatures can augment sensitivity versus LAM alone. These findings demonstrate the potential of multi-antigen urine detection for childhood TB and define analytical targets for the development of future point-of-care diagnostics. Funding. National Institutes of Health.

Acute kidney injury (AKI) is a frequent complication within intensive care units, with its sudden onset often missed. This is especially important because a timely window for intervention is required as delayed detection leads to progressively worse outcomes. Existing machine learning and deep learning models have contributed to closing this gap, but their complexity, requiring hundreds to thousands of features, and lack of generalisation pose a limitation that prevents them from being integrated into clinical workflows across different electronic health-record ecosystems. This study presents a 37-feature XGBoost model trained on the MIMIC-IV dataset with 5.4% positive cases, with hyperparameters optimised via Optuna and probabilities calibrated using isotonic regression, designed for transportability across clinical settings. Validation was conducted internally using a temporal patient-level split simulating prospective deployment, training on 2008-2016 data and testing on 2017-2022 data"External validation was performed on the eICU Collaborative Research Database, a multi-centre dataset spanning 208 US hospitals, using the trained model without retraining. SHAP TreeExplainer was used to provide feature-level explainability for individual predictions. Internal testing yielded an AUROC score of 0.794 for predicting AKI onset within a 12-24 hour window. External validation produced a 0.750 AUROC without retraining. Equitable discrimination was observed across gender, age, chronic kidney disease presence, race, and AKI stages on both datasets, with a 95% internal CI of 0.789-0.799 confirming the model's estimate stability. These results suggest that clinically useful prediction systems are achievable with substantially fewer features than current models require.

BACKGROUND: Subarachnoid hemorrhage (SAH) induces inflammatory responses and subsequent immune cell activation, which may contribute in cerebral vasospasm, microcirculatory impairment and poor neurological outcomes. Although cerebral vasospasm has traditionally been considered a major cause of delayed cerebral ischemia after SAH, therapies targeting angiographic vasospasm have not consistently improved functional outcomes. Early inflammatory responses may contribute to microcirculatory impairment, cerebral vasospasm, and subsequent neurological injury. Herein, we investigated whether interleukin-10 (IL-10), an anti-inflammatory cytokine, improves these outcomes in an experimental SAH model. METHODS: Mice received intramuscular injections of either an adeno-associated virus encoding IL-10 (AAV/IL-10) vector or an AAV expressing green fluorescent protein (AAV/GFP) vector (control). India ink angiography was performed to assess the diameter of the sphenoidal segment of the middle cerebral artery (MCA), the total length of the visible cortical arteries, and cortical staining intensity, as indices of cerebral vasospasm, microcirculatory impairment, and cerebral perfusion, respectively. Perivascular inflammatory cell infiltration and cytokine levels were assessed using immunohistochemistry and ELISA. We also evaluated the therapeutic efficacy of the AAV/IL-10 vector when administered immediately after SAH induction. RESULTS: IL-10 overexpression significantly improved neurological outcomes after SAH and was associated with attenuated cerebral vasospasm and microcirculatory impairment, as well as preservation of cerebral perfusion. It also significantly reduced neutrophil and macrophage infiltration around the internal carotid artery and attenuated SAH-induced elevations in IL-6 and matrix metalloproteinase-3 levels. Mice treated with the AAV/IL-10 vector immediately after SAH induction showed significant improvements in neurological scores and cerebral perfusion. CONCLUSIONS: AAV-mediated IL-10 overexpression improves neurological outcomes after SAH, likely by attenuating inflammatory responses, cerebral vasospasm, and microcirculatory impairment. These findings suggest that IL-10-based anti-inflammatory therapy is a promising therapeutic strategy for SAH.

Background: Pulmonary arterial hypertension (PAH) is a serious disease with poor prognosis, especially in infants or preterm babies and there is still no optimal treatment for this disease. Noradrenalin (NE) is a vasoactive mediator which is released by sympathetic ganglion. According to previous studies, NE/1-adrenoreceptors is not only in regulating normal physiologic responses, but also in the pathogenesis of PAH. However, the mechanisms of NE in PAH are not fully understood. Methods: Human PASMC (PASMC) was used in this study. Cell viability assay and Wound healing assay were used to evaluate the proliferation and migration of PASMC. Immunoprecipitation and western blots analysis were used to investigate the mechanisms which involved in NE-induced PASMC proliferation. Results: We investigated that NE could induce human PASMC proliferation and migration. Furthermore, we first find that endothelin 1 (ET-1) signaling pathway plays an important role in NE-induced PASMC proliferation. ET1 is a critical molecular which is known for regulating cell growth and migration. We investigated that NE could increase NE-1 secretion, further enhancing ET-1 bind to its receptors. For further clarifying the downstream signals in NE/ET-1 induced PASMC proliferation, we detected the phosphorylation and expression levels of ERK and JNK. Conclusions: By combining the results from ours and previous studies, we believed that JNK/c-jun pathway may play an important role in NE-induced PASMC proliferation. Key Words: Noradrenaline; Pulmonary Arterial Hypertension; Pulmonary Artery Smooth Muscle Cells; Endothelin-1; JNK/c-Jun Signaling.

Stroke remains a leading cause of mortality and long-term disability worldwide, yet rapid diagnosis is often limited by the shortage of trained radiologists, particularly in resource-constrained settings. Automated analysis of CT imaging offers a potential solution, but existing methods often struggle to achieve clinically generalisable performance while jointly addressing multiple diagnostic tasks. Here we present the Intelligent Integrated Stroke Diagnosis System IISDS, an end-to-end deep learning framework built upon StrokeGNN, a graph-based architecture that integrates 3D contextual feature extraction with U-Net-based 2D lesion segmentation to enable comprehensive stroke analysis from non-contrast CT scans. IISDS performs stroke subtype classification, lesion segmentation and lesion volume estimation within a unified pipeline. To develop and validate the system, we collected and curated BGD-ISD through a collaboration between AI researchers, neurologists, radiologists and clinicians, resulting in a large multi-centre dataset comprising 1,507 CT scans from 597 stroke cases acquired across six hospitals and medical centres in Bangladesh. Across BGD-ISD and multiple publicly available datasets, IISDS achieves state-of-the-art performance on all tasks, improving segmentation accuracy by [&ge;]0.011 Dice score, reducing lesion volume estimation error by [&ge;]0.3 average symmetric surface distance (ASSD), and increasing classification performance by [&ge;]0.018 area under the receiver operating characteristic curve (AUC) compared with existing approaches. These results demonstrate the potential of graph-based deep learning to enable clinically generalisable, automated and scalable stroke diagnosis from CT imaging, supporting rapid clinical decision-making, particularly in healthcare environments with limited access to expert radiological interpretation.

In this work, we demonstrate the unprecedented value of NIH's "All of Us Research Program" (AoURP) dataset in studying maternal morbidity and building predictive machine learning (ML) models across heterogeneous populations in the United States. We developed robust and data-driven preprocessing pipelines to curate a longitudinal, multi-site, multimodal, and demographically diverse pregnancy dataset (20,253 subjects; 27,525 pregnancy episodes) from AoURP data, using electronic health records (EHR) (Conditions, Labs, Measurements) and survey responses (Social Determinant of Health (SDoH)), focusing on 7 crucial maternal health adverse outcomes. After characterizing data quality, missingness, and heterogeneity, we performed statistical correlation analysis to identify risk factors. We subsequently developed XGBoost and sequential LSTM models to predict the adverse outcomes, reaching state-of-the-art performance for multiple outcomes. We conducted model interpretability post-hoc analysis to understand success points and fairness analysis to evaluate implications for socio-economic disparities. Four practicing physicians reviewed the set of statistically significant and ML model identified features to assess their clinical validity and novelty. Most features identified through either statistical correlations or ML feature importance analysis aligned with known clinical risk factors. Several features were identified that the ML models used but that are not currently used in clinical practice and may merit further clinical investigation. Fairness analysis revealed certain associations with SDoH and age highlight areas that warrant continued monitoring. Overall, we demonstrate that meaningful populational level patterns can be extracted, and high-performing machine learning models can be trained on this longitudinal, diverse, multi-site dataset. Important risk features, particularly novel ones identified, if validated, could inform new strategies for maternal care or enable development and validation of outcome-specific, clinically deployable ML models.

Early identification of Alzheimer's disease and related dementias (ADRD) remains challenging despite its importance for timely intervention, management of modifiable risk factors, and care planning. We developed and evaluated ADRD onset prediction models using longitudinal electronic health records (EHRs) from the All of Us Research Program at clinically meaningful lead times of 6, 12, 24, and 36 months before diagnosis, benchmarking interpretable count-based representations against four publicly available pretrained clinical foundation models (CLMBR-T, GPT-style, LLaMA-style, and Mamba) across multiple ADRD phenotype definitions. Count-based models consistently achieved the highest discrimination and calibration across all cohorts and prediction horizons. Predictive performance declined with increasing lead time for all approaches; however, the performance gap between count-based and pretrained representations progressively narrowed, with foundation models achieving comparable AUROC of 0.719 (compared to the AUROC of 0.738 of count-based model) at the 36-month horizon while providing higher sensitivity and F1 scores under a fixed operating threshold. External validation with zero-shot evaluation on UChicago EHRs exhibited limited generalizability for count-based and pretrained clinical foundation model based representations. These findings demonstrate that transparent count-based EHR representations remain the strongest overall approach for ADRD onset prediction, while pretrained clinical foundation models provide complementary advantages for long-term risk identification and establish a benchmark for evaluating transferable clinical representations in temporal ADRD risk prediction.

Background: The Boston Criteria v2.0 represent the gold standard for diagnosing Cerebral Amyloid Angiopathy (CAA), but their application is currently precluded in mixed small vessel disease (SVD), where deep and lobar hemorrhages coexist. The aims of this study are: (i) to determine which cerebrospinal fluid (CSF) biomarker (A{beta}42, A{beta}40, A{beta}42/40 ratio) is the best candidate to support the CAA diagnosis; (ii) to define a data-driven cut-off, and (iii) to explore if a biomarker-integrated classification significantly improves the phenotypical concordance with the suspected predominant SVD (CAA vs. arteriosclerosis). Methods: We analyzed data from a retrospective multicenter cohort of patients with suspected CAA, defined as probable CAA (Boston criteria v2.0) but allowing deep hemorrhagic lesions, and with available CSF biomarkers. We visually quantified MRI-visible SVD markers (e.g., cerebral microbleeds [CMB], cortical superficial siderosis [cSS], lacunes) and their association with MRI-visible SVD features. We employed a Gaussian Mixture Model (GMM) to identify a data-driven threshold for amyloid positivity (A+). Then, we compared the prevalence of MRI-visible manifestations of SVD between subgroups applying different frameworks, namely the current MRI-based classification (probable CAA vs. mixed SVD) and a CSF biomarker-integrated classification (A+ vs. A-). Results: We enrolled 121 patients (age: 72 [66-77] years; 60% probable CAA, 40% mixed SVD with suspected CAA). The CSF A{beta}42/40 ratio showed a bimodal distribution and consistent associations with all CAA-specific radiological features. The CSF biomarker-integrated reclassification, particularly using the GMM cut-off, significantly improved the distinction between subgroups regarding CAA- and arteriosclerosis-related MRI features (e.g., cSS presence: probable CAA vs. mixed SVD: aOR=2.84 [95%CI 1.27-6.39], p=0.011; A+ vs. A-: aOR=12.68 [95%CI 4.31-37.32], p<0.001; deep lacunes presence: probable CAA vs. mixed SVD: aOR=0.20 [95%CI 0.08-0.50], p<0.001; A+ vs. A-: aOR=0.04 [95%CI 0.01-0.11], p<0.001). Notably, patients classified as A+ never demonstrated more than four deep CMBs. Discussion: A CSF biomarker-integrated classification may improve the classification of CAA compared with the current MRI-based framework. These findings are cohort-specific and would benefit from further validation, especially with a neuropathological reference. Still, these results support a future transition toward an integrated biological-radiological framework, which may refine in vivo CAA diagnosis, particularly in mixed SVD.

Background. Whether predictors of intraoperative hypotension (IOH) add information beyond the mean arterial pressure (MAP) already displayed on the monitor is contested: selection bias in common evaluation designs inflates apparent performance, and the field has called for comparisons against simple MAP-based references under bias-resistant protocols. Existing predictors also depend on proprietary waveform analysis or pulse-contour monitors, restricting both deployment and external validation. Methods. Using 807 non-cardiac surgery patients from the open VitalDB database, we derived an additive gradient boosting model (one split per tree: a learned shape function per variable, no interactions) from three variables computable from an arterial line alone: current MAP, its drift from the patient's own 20-minute baseline, and the growth of its rolling variance (critical slowing down). Evaluation used patient-level 5-fold cross-validation under a strict protocol - exclusion of the 65-75 mmHg grey zone and of all samples already hypotensive at prediction time - with MAP alone (same learner class) as comparator. The frozen model was then validated, without any refitting, on an independent cohort from another continent (MOVER, University of California Irvine) following a pre-registered plan sealed before external data access. Results. In development the pressure-only model reached AUROC 0.907 vs. 0.884 for MAP alone (Delta AUROC +0.023, 95% CI +0.017 to +0.029) at 5 min, with +0.031 and +0.032 at 10 and 15 min, and good calibration (Brier skill +0.418 vs. prevalence). In external validation on 3,069 patients (442,194 samples, 1-minute charting, event prevalence 5.8%), the advantage not only transferred but was larger than in development: AUROC 0.696 vs. 0.638, Delta AUROC +0.058 (95% CI +0.051 to +0.064), meeting both pre-registered gates. Discrimination transferred; calibration did not (external Brier skill -0.014), requiring local recalibration. In the unrestricted scenario, where samples already at threshold are retained, the advantage collapsed (+0.007), reproducing the selection effect this paper documents. A secondary model adding pulse-contour cardiac output and stroke volume variation improved development discrimination further (Delta AUROC +0.035) but could be externally validated in only 39 patients, because those signals are rarely recorded. Conclusions. The dynamics of arterial pressure itself - drift from a patient-specific baseline and variance growth - carry predictive information beyond its current value, in a fully interpretable additive model that requires only an arterial line, no waveform access and no proprietary hardware. The advantage is confirmed in a pre-registered frozen-model external validation of over three thousand patients, and is largest at coarse recording cadence, where instantaneous pressure is least informative.

Background: Evidence regarding delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH) remains sparse. We aimed to identify its predictors and occurrence and evaluate its role in ischemic stroke and functional outcome under treatment with interventional rescue therapy (IRT). Methods: This retrospective single-center study included 628 adults with aSAH from 2014?2023. The primary endpoint was occurrence of refractory DCI (= refractory despite induced hypertension) treated with at least one IRT. Multivariable models evaluated refractory DCI, new ischemic stroke, and poor functional outcome (mRS 3?6) at 6?12 months. Results: Among 628 included patients, 61 who died within 3 days were excluded from DCI analysis; 166/567 (29%) developed refractory DCI. Younger age (OR = 0.98; P<0.001), female sex (OR = 0.57; P=0.007), and higher WFNS grade (OR = 1.18; P=0.011) were independently associated with refractory DCI. Earlier first IRT was associated with longer DCI duration (IRR = 0.88; P<0.001) and more required IRTs (IRR = 0.91; P<0.001). IRT was performed later than day 14 in 29/166 patients (17.5%); none was older than 70 years. Refractory DCI was associated with new ischemic stroke (OR = 4.68; P<0.001) and poor functional outcome (OR = 2.37; P<0.001); earlier first IRT was associated with poor outcome within the refractory DCI subgroup (OR = 0.86; P=0.03). Outcomes after 1?2 IRTs did not differ from those without refractory DCI (P=0.4), whereas ?3 IRTs were associated with poor outcome (P=0.04). Conclusions: Refractory DCI affected 29% of aSAH patients, predominantly younger women and patients with poorer initial neurological status, and extended beyond day 14 in nearly 20% of affected patients, none of whom was older than 70 years. Refractory DCI and earlier onset were associated with poorer radiological and functional outcomes. The absence of a detected outcome difference after 1?2 IRTs suggests that favorable outcomes may remain achievable despite refractory DCI.

Background: Pressure ulcers often develop complex three-dimensional morphologies that extend beyond the visible wound surface. Subsurface extensions such as tunneling and undermining create hidden cavities that complicate clinical assessment and wound management. Despite their clinical relevance, the prevalence and spatial characteristics of these subsurface wound morphologies have not been well characterized at scale. Methods: We performed a registry-based analysis using data from the LIFT-OFF Pressure Ulcer Registry, which captures longitudinal clinical documentation of pressure ulcers treated in routine care. The registry included approximately 18,000 patients with 32,000 documented pressure ulcers. Spatial characteristics of tunneling and undermining were analyzed using measurements recorded during routine wound assessments, including tract length, direction, and circumferential extent. Directional and circumferential distributions of subsurface defects were examined to characterize wound geometry. Results: Tunneling was present in 764 of 14,700 full-thickness pressure ulcers (5.2%), whereas undermining occurred in 2,293 wounds (15.6%). Tunneling tracts were typically short and exhibited directional clustering relative to the wound bed. In contrast, undermining demonstrated broader circumferential distributions and frequently involved larger subsurface separations beneath the wound margin. Both morphologies demonstrated distinct spatial patterns across anatomical locations and wound stages. Conclusion: Tunneling and undermining are common subsurface features of pressure ulcers and exhibit distinct spatial geometries. Whereas tunneling manifests as directional tract-like extensions, undermining more frequently produces circumferential tissue separation beneath wound margins. Improved characterization of subsurface wound architecture may enhance assessment of wound complexity and provide information not captured by surface measurements alone. Future studies should evaluate whether these features contribute to wound severity assessment, prognosis, and risk stratification.

Abstract Background: Vaginal steaming has gained popularity among women for reasons known best to them. However, the effects of vaginal steaming on vaginal lactobacilli levels remain poorly understood and understudied. This study investigated the prevalence, assessed differences in the presence of bacterial vaginosis (BV) among women who practiced vaginal steaming and those who do not and determined the factors associated with vaginal steaming among women attending Mulago Sexually Transmitted Infections (STI) clinic in Uganda. Methods: This study utilized a cross-sectional design to enroll 181 women aged 18 to 49 years who were systematically sampled at Mulago STI clinic. Interviews were conducted to obtain the demographic characteristics of the participants. Vaginal swabbing and Gram staining were done to attain lactobacilli counts by microscopy which were categorized using the Nugent score. Data were analyzed using Stata. The potential confounding effects of other variables on the relation between vaginal steaming and the presence of bacterial vaginosis as well as factors associated with vaginal steaming were assessed using modified Poisson regression. Results: Prevalence of vaginal steaming was 40.3%, (95% confidence interval (CI) 33.0% - 48.0%). There were 41.1% women who practiced vaginal steaming occasionally, 53.4% who used hot water having herbs and 78.1% who practiced vaginal steaming for medical reasons. There was no difference in the presence of bacterial vaginosis when women who practiced vaginal steaming were compared to those who did not (p-value = 0.286). Factors that were significantly associated with vaginal steaming included having experienced vaginal issues (aPR = 0.07, 95% CI 0.01 - 0.12, p value = < 0.001) and contraceptive use (aPR= 0.52, 95% CI 0.37 - 0.72, p value = 0.001). Conclusions: About 2 in every 5 women at Mulago STI clinic reported to have indulged in vaginal steaming. There was no difference in the presence of bacterial vaginosis when women who practiced vaginal steaming were compared to those who did not. Having experienced vaginal issues and contraceptive use were significantly associated with vaginal steaming among women at Mulago STI clinic, Uganda. The Ministry of Health of Uganda should establish targeted screening and treatment for bacterial vaginosis alongside other sexually transmitted infections.

Background: Unstructured biomedical data, such as echocardiography reports, are rich in information but time consuming to analyze at scale. Rule-based, regular expression-driven terminology mapping can only extract individual variables while large language models (LLMs) offer scalable and clinically meaningful interpretations of heterogeneous disease processes. Right ventricular dysfunction (RVD) is an example of a multifactorial disease state in which key structural and physiologic features are captured both narratively and in structured fields, making it an ideal test case for evaluating whether LLMs can recover complex phenotypes that rules based methods routinely miss. Purpose: To compare an LLM-based extraction method to a conventional rules-based schema for identifying and phenotyping echocardiographic features associated with RVD in a large TTE dataset. Methods: MIMIC-III NOTE2NUM echocardiography reports (n = 45,794) were analyzed using GPT-4o-based LLM extraction deployed within a secure health system enclave and were benchmarked against echocardiographic measurements defined in the MIMIC-III dictionary schema. In MIMIC-III, PH was recorded qualitatively (mild/moderate/severe) based on tricuspid regurgitant (TR) jet velocity and then re-coded as present vs. absent. LLM based extraction defined RVD as (1) RV structural abnormality (>= 1 of hypertrophy, dilation, or wall hypo-/akinesis) or (2) RV pressure/volume overload (>= 2 of the following: estimated right atrial pressure > 8 mmHg, TR jet velocity > 2.8 m/s, fractional area change < 35%, tricuspid annular planar systolic excursion < 17 mm, S' < 9.5 cm/s, or E/e' > 14), with PH defined as estimated pulmonary artery systolic pressure > 35 mmHg or qualitative documentation of PH. Results: LLM extraction identified PH in 15,394 (33.6%), RV pressure/volume overload in 14,449 (31.6%), and RV structural abnormalities in 11,955 (26.1%). Co-occurrence was common: overload + structural changes in 9,380 (20.5%), overload + PH in 9,756 (21.3%), structural changes + PH in 6,183 (13.5%), and all three in 5,620 (12.3%). Using the MIMIC-III dictionary schema, PH prevalence was similar (15,371; 33.6%), but RV overload fields were captured less often (pressure overload 1,357 [3.0%], volume overload 1,128 [2.5%], pressure + volume overload 1,093 [2.4%]; any overload field 3,578 [7.8%]), and RV pressure/volume overload with PH was identified in only 731 (1.6%). Conclusions: LLM-based extraction outperforms rules-based schemas for identifying complex disease states not defined by any single variable. By synthesizing multifactorial signals, LLMs can phenotype RVD with higher fidelity and support population-level assessment. Further validation using multimodality imaging, invasive hemodynamics, and clinical outcome data is needed.