Citations

Abstract Objective: This study aimed to develop a machine learning model for the diagnosis of chronic renal failure (CRF) with spleen–kidney qi deficiency (SKQD) syndrome by investigating facial chromatic biomarkers based on traditional Chinese medicine (TCM) theory. Materials and Methods: This cross-sectional study analyzed TCM-defined facial regions in 303 patients with CRF (166 SKQD and 137 non-SKQD) and 25 healthy controls using active appearance models and RGB/Lab color spaces. Key chromatic features were selected using Chi-square automatic interaction detection (CHAID) decision trees to construct a multibranch deep convolutional neural network (CNN), nomogram, and hybrid model. The model performances were compared using the DeLong test. Results: The SKQD group showed a higher glomerular filtration rate, albumin level, and facial R-value with a lower serum creatinine level (all P < 0.05), accompanied by a higher prevalence of shortness of breath with reluctance to speak, and cold extremities ( P < 0.05) compared with the non-SKQD group. Chromatic analysis revealed elevated R/a values in the kidney region using the natural facial color region method ( P < 0.05), and distinctively higher R -values in the bladder-uterus region and a -values in the right small intestine region using the Mingtang facial color region method ( P < 0.05). The CHAID algorithm selected four diagnostic determinants, including the overall facial R -values. The CNN achieved superior discriminative performance (test area under the receiver operating characteristic curve = 0.74 vs. nomogram 0.68, DeLong test P < 0.001) with no added benefit from model integration ( P > 0.05). Conclusions: Facial chromatic biomarkers effectively differentiated SKQD in patients with CRF when analyzed using TCM-defined regions. The superior performance of the CNN validates AI-driven TCM diagnostics as a clinically actionable tool for precise syndrome classification.

ABSTRACT Background Factor XI/XIa inhibitors are emerging anticoagulants with potential to reduce bleeding complications in atrial fibrillation (AF) patients. This meta‐analysis evaluated their efficacy and safety compared to direct oral anticoagulants (DOACs) and explored dose optimization. Methods A systematic search of PubMed, Cochrane, and Embase was conducted through March 2025 following PRISMA guidelines. Randomized controlled trials (RCTs) comparing Factor XI/XIa inhibitors with DOACs in AF patients were included. Outcomes assessed were major bleeding, stroke, systemic embolism, all‐cause and cardiovascular mortality and serious adverse events. Risk ratios (RR) with 95% confidence intervals (CI) were pooled using a Mantel‐Haenszel random‐effects model. Heterogeneity was evaluated with the I² statistic, and evidence certainty assessed by the GRADE approach. Trial Sequential Analysis (TSA) was performed. Results Three RCTs including 16,772 patients (mean age 73 years, CHA₂DS₂‐VASc 3.9–5) were analyzed. Factor XI/XIa inhibitors significantly reduced major bleeding (RR: 0.41, 95% CI: 0.36–0.46, I² = 0%) compared to DOACs. However, stroke risk was increased (RR: 3.42, 95% CI: 2.62–4.46), particularly with asundexian 50 mg (RR: 4.02). No significant differences were observed in all‐cause mortality (RR: 0.82) or cardiovascular death (RR: 1.05). Systemic embolism risk was higher (RR: 4.26), while serious adverse events were comparable (RR: 0.95). TSA indicated encouraging safety outcomes but highlighted the need for further large‐scale studies. Conclusion Factor XI/XIa inhibitors lower major bleeding risk in AF patients but increase stroke and systemic embolism rates without impacting mortality.

Abstract INTRODUCTION The Centiloid scale is the standard for amyloid (Aβ) PET quantification in research and clinical settings. However, variability between tracers and scanners remains a challenge. METHODS This study introduces DeepSUVR, a deep learning method to correct Centiloid quantification, by penalizing implausible longitudinal trajectories during training. The model was trained using data from 2,129 participants (7,149 Aβ positron emission tomography [PET] scans) in the Australian Imaging, Biomarkers and Lifestyle Study of ageing (AIBL)/Alzheimer's Disease Neuroimaging Initiative (ADNI) and validated using 15,807 Aβ PET scans from 10,543 participants across 10 external datasets. RESULTS DeepSUVR increased correlation between tracers, and reduced variability in the Aß‐negatives. It showed significantly stronger association with cognition, visual reads, neuropathology, and increased longitudinal consistency between studies. DeepSUVR also increased the effect size for detecting small treatment related slowing of amyloid accumulation in the A4 study. DISCUSSION DeepSUVR substantially advances Aβ PET quantification, outperforming all standard approaches, which is particularly important for clinical decision making and to detect subtle or early changes in Aβ. Highlights Novel artificial intelligence (AI)‐method that penalizes biologically implausible longitudinal trajectories, enabling the model to learn standardized uptake value ratios (SUVR) correction factors without requiring longitudinal data at inference time. Improves Centiloid consistency across tracers and studies, significantly enhancing cross‐sectional and longitudinal amyloid positron emission tomography (PET) quantification. DeepSUVR‐derived Centiloids show stronger associations with cognition, visual reads, and neuropathology. Longitudinal variability is reduced three‐ to five‐fold, enabling more reliable tracking of amyloid accumulation and better detection of treatment effects. Novel reference and target masks derived from DeepSUVR replicate most of the model's performance, offering a practical alternative for integration into existing pipelines.

Abstract Background Renal denervation (RDN) has emerged as a promising therapeutic adjunct for the management of hypertension, yet its efficacy in the long term, particularly in patients with hypertension and concurrent renal insufficiency, remains to be fully elucidated. This study was designed to evaluate the sustained impact of RDN on blood pressure control, renal function, and cardiovascular outcomes in hypertensive patients with pre-existing renal impairment over an extended follow-up period. Methods We conducted a single-center, single-arm, real-world retrospective study involving patients with hypertension and chronic kidney disease (CKD) stages 3-4 who underwent RDN at a hospital between 2011 and 2016. Comprehensive baseline data, including demographic information, comorbidities, and medication history, were meticulously recorded. Long-term follow-up assessments were performed at 1, 5, and 11.5 years post-RDN to monitor changes in office and home blood pressure, 24-hour ambulatory blood pressure results, renal function, and the incidence of cardiovascular events and mortality. Results A total of 20 participants completed the long-term follow-up, with a mean age of 51.7 ± 14.5 years (35% female), and a median follow-up duration of 11.5 years. At baseline, the cohort presented with an average office systolic blood pressure of 183.8 ± 18.6 mmHg and a diastolic blood pressure of 104.7 ± 17.0 mmHg. Following RDN, participants experienced a significant reduction in blood pressure, with an average decrease of -37.94/-20.38 mmHg (P &lt; 0.001) compared to baseline. Additionally, ambulatory systolic and diastolic blood pressures were reduced by 16.87 ± 9 mmHg (P &lt; 0.001) and 9.88 ± 4.05 mmHg (P &lt; 0.001) 11.5 years after the procedure, respectively. The study also revealed a substantial reduction in the need for antihypertensive medications (P &lt; 0.001) and a decrease in average heart rate (P = 0.046) following renal denervation. Assessments of renal function, as measured by estimated glomerular filtration rate and creatinine levels, were consistent with expected age-related decline. Importantly, no significant adverse events associated with RDN were observed in the long-term follow-up. Over the 11.5-year period, the cardiovascular mortality rate and overall mortality were 10% and 20%, respectively. Conclusion This long-term follow-up study demonstrates that RDN is a safe and effective intervention for managing hypertension in patients with renal impairment.

Immunotherapy has been effective in many cancer types but has failed in multiple clinical trials in prostate cancers, with the underlying mechanisms remaining largely unclear. Here, we demonstrate that androgen receptor pathway inhibitor (ARPI) plus irradiation (IR) triggered robust anticancer immunity in prostate cancers in both patients and mice. We show that androgen-activated AR suppressed innate immune signaling by inducing inhibitor of nuclear factor kappa-B kinase subunit epsilon ( IKBKE ) gene repression through HDAC2 interaction with an IKBKE enhancer RNA ( IKBKE eRNA, or IKBKE-e ). ARPI treatment caused IKBKE derepression and enhanced an IR-induced innate immune response via action of RIG-I and MDA5 dsRNA sensors. IKBKE-e ablation largely enhanced innate immunity in prostate cancer cells in culture and anticancer immunity in mice. Our results revealed AR, HDAC2, and IKBKE eRNA as critical intrinsic immune suppressors in prostate cancer cells, suggesting that rejuvenating inhibitor of nuclear factor kappa-B kinase subunit epsilon (IKKε) signaling by targeting IKBKE-e is an actionable strategy to elicit synthetic anticancer immunity in immunologically “cold” cancers such as prostate cancer.

Abstract Background Neurofibromatosis type 1 (NF1) is a multisystem genetic condition. Up to 50% of individuals with NF1 develop plexiform neurofibromas (PN) that can cause pain and significant morbidity, impairing quality of life. As of December 2025, only a limited number of countries have an approved medical treatment for adults with NF1-PN. A systematic literature review (PROSPERO CRD42023463980) was conducted to better understand disease burden and unmet need in this population. Methods An evidence prioritization strategy identified studies reporting on NF1-PN populations with ≥50% adults from database searches conducted between 1988 and July 20, 2023. Studies published in the last 15 years were extracted. Results Of 3242 identified sources, 57 publications (53 unique studies) were included. The proportion of adults with NF1 who had PN ranged from 11.8% to 84.9% (n = 9 studies). Annual median change in untreated PN volume was −3.7% to +8.3% (n = 5 articles). Pain was the most common PN-related manifestation (32.0%–38.4% of patients; n = 12 articles). Malignant PN transformation occurred in 2.0%–4.1% of patients (n = 5 cohorts); 3 shorter-term studies reported no transformation. Surgery was performed in 69.5% of patients (n = 7 cohorts); post-operative complications occurred in 13.0%–30.0% (n = 3 articles). Analgesia was the most reported pharmacological treatment (37.9% of patients; n = 7 articles). Limited data indicated that PN monitoring and surgery cause substantial resource use. No studies reported on caregiver burden, healthcare costs, or transition from pediatric to adult care. Conclusions Adults with NF1-PN experience high disease burden. Data gaps exist for epidemiology, transition of care, caregiver burden, healthcare cost, and resource use.

Abstract Background The mechanisms of left ventricular outflow tract obstruction (LVOTO) in hypertrophic cardiomyopathy (HCM) with moderate septal hypertrophy (≤ 18 mm) remain uncertain with therapeutic implications. This study investigated the role of three-dimensional echocardiography (3DE)-derived myocardial mechanics in LVOTO. Methods We retrospectively analyzed 216 HCM patients with moderate septal hypertrophy, stratified into nonobstructive (n = 38), provokable LVOTO (n = 63), and resting LVOTO (n = 115). Transthoracic echocardiography assessed LV geometry, LVOT diameter, anterior mitral leaflet length, and papillary muscle abnormalities (via a composite SubMV score). 3DE-derived strain parameters, including global longitudinal (GLS), circumferential, radial, area (GAS) strain, twist, and torsion, were quantified. Determinants of LVOTO were evaluated using multivariate regression, restricted cubic splines (RCS), and receiver operating characteristic (ROC) analysis. Results Both LVOTO subgroups showed significantly augmented strain mechanics versus nonobstructive patients, greatest in resting LVOTO (p < 0.05); twist and torsion were the strongest discriminators (p < 0.001). Multivariate regression showed that, beyond LVOT diameter and SubMV score, torsion (B = 9.47), twist (B = 1.92), and GAS (B = 1.29) independently predicted provoked LVOT gradients (all p < 0.05); RCS demonstrated nonlinear twist/torsion–LVOTO relationships, with obstruction risk rising sharply above twist = 15° and torsion = 3°/cm, especially under provocation. Torsion discriminated provokable LVOTO achieving 81% specificity (cutoff 2.4°/cm, AUC = 0.72), outperforming all structural parameters. Integrating 3DE-derived mechanics with structural metrics improved diagnostic accuracy, especially in provokable LVOTO (AUC 0.84 vs. 0.76, DeLong p = 0.003). Conclusions In moderate-hypertrophy HCM, 3DE-derived strain mechanics, especially twist and torsion, independently determine LVOTO beyond structural narrowing, particularly under provocation, strengthening mechanistic insight and clinical applicability.

The success of living donor liver transplantation (LDLT) has bridged the growing gap between organ demand and availability in patients with liver failure or liver cancer. Safety of the living liver donor (LLD) is paramount, and astute intraoperative management plays a critical role in ensuring optimal outcomes for them. Given that intraoperative surgical and anesthesia practices vary widely across centers, the International Liver Transplantation Society (ILTS) and the International Living Donor Liver Transplantation Group (iLDLT Group) convened a global consensus conference in Toronto in March 2025 to develop guidelines for intraoperative management of the LLD. This manuscript details the recommendations on intraoperative considerations for the safety of LLD developed by Working Group II of the Consensus Scientific Committee, using the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) system for assessment of recommendations, and the Danish model of consensus. Working Group II focused on intraoperative monitoring, fluid and ventilation strategies, surgical techniques for vascular and biliary division, surgeon and center-specific experience, and intraoperative crises planning. These guidelines aim to support both established and emerging LDLT teams to ensure high-quality and safe intraoperative care for the LLD.

Background: Adequate medication dosing in the intensive care unit (ICU) remains challenging due to rapid physiological variability, narrow therapeutic windows, and evolving standards of care. Artificial intelligence (AI) offers promise for personalized dosing, but its accuracy and clinical utility remain uncertain. Methods: We conducted a systematic scoping review (2011-2025) of PubMed, Embase, and Cochrane, following the Joanna Briggs Institute (JBI) and preferred reporting Items for systematic reviews and meta-analyses extension for scoping reviews (PRISMA-ScR) guidelines (open science framework [OSF]-registered). Eligible studies applied AI methods ( e.g. , machine learning [ML], deep learning [DL], reinforcement learning [RL], and natural language processing [NLP]) to ICU medication dosing or monitoring. Results: Data extraction included study design, drug class, model inputs and outputs, algorithms, validation approach, and reported outcomes. Forty-seven studies met the inclusion criteria, which were mostly retrospective and focused on adult ICU populations over the past five years. Antibiotics and anticoagulants were the most studied classes, with vancomycin being the most common. Models primarily used labs, vitals, and demographics, with limited incorporation of time series, pharmacokinetic data, or clinical notes. Outputs spanned dose prediction, serum concentration, risk stratification, adverse events, and decision support. Algorithms evolved from classical ML and ensembles to RL and long short-term memory (LSTM)-based models, although a few advanced beyond retrospective validation. Discussion: AI systems showed strong predictive performance and some clinical benefits ( e.g. , heparin target attainment, sedative reduction, and adverse event detection), but the field remains fragmented and clinically immature. Newer architectures and systematic explainability are lacking, and generalizability is uncertain. AI-enabled dosing holds promise for precision pharmacotherapy in critical illness but requires prospective multicenter validation, inclusion of population pharmacokinetic (PK) parameters, diverse cohorts, explainable design, and clinical integration.