Search Results (885)

Large, high-quality patient datasets are essential for applications like economic modeling and patient simulation. However, real-world data is often inaccessible or incomplete. Synthetic patient data offers an alternative, and current methods often fail to preserve clinical plausibility, real-world correlations, and logical consistency. This study presents a patient cohort generator designed to produce realistic, statistically valid synthetic datasets. The generator uses predefined probability distributions and Cholesky decomposition to reflect real-world correlations. A dependency matrix handles variable relationships in the right order. Hard limits block unrealistic values, and binary variables are set using percentiles to match expected rates. Validation used two datasets, NHANES (2021–2023) and the Framingham Heart Study, evaluating cohort diversity (general, cardiac, low-dimensional), data sparsity (five correlation scenarios), and model performance (MSE, RMSE, R², SSE, correlation plots). Results demonstrated strong alignment with real-world data in central tendency, dispersion, and correlation structures. Scenario A (empirical correlations) performed best (R² = 86.8–99.6%, lowest SSE and MAE). Scenario B (physician-estimated correlations) also performed well, especially in a low-dimensions population (R² = 80.7%). Scenario E (no correlation) performed worst. Overall, the proposed model provides a scalable, customizable solution for generating synthetic patient cohorts, supporting reliable simulations and research when real-world data is limited. While deep learning approaches have been proposed for this task, they require access to large-scale real datasets and offer limited control over statistical dependencies or clinical logic. Our approach addresses this gap. Full article

Many commercial wearable sensor systems typically rely on a single continuous cardiorespiratory sensing modality, photoplethysmography (PPG), which suffers from inherent biases (i.e., differences in skin tone) and noise (e.g., motion and pressure artifacts). In this research, we present a wearable device that provides robust estimates of cardiorespiratory variables by combining three physiological signals from the upper arm: multiwavelength PPG, single-sided electrocardiography (SS-ECG), and bioimpedance plethysmography (BioZ), along with an inertial measurement unit (IMU) providing 3-axis accelerometry and gyroscope information. We evaluated the multimodal device on 16 subjects by its ability to estimate heart rate (HR) and breathing rate (BR) in the presence of various static and dynamic noise sources (e.g., skin tone and motion). We proposed a hierarchical approach that considers the subject’s skin tone and signal quality to select the optimal sensing modality for estimating HR and BR. Our results indicate that, when estimating HR, there is a trade-off between accuracy and robustness, with SS-ECG providing the highest accuracy (low mean absolute error; MAE) but low reliability (higher rates of sensor failure), and PPG/BioZ having lower accuracy but higher reliability. When estimating BR, we find that fusing estimates from multiple modalities via ensemble bagged tree regression outperforms single-modality estimates. These results indicate that multimodal approaches to cardiorespiratory monitoring can overcome the accuracy–robustness trade-off that occurs when using single-modality approaches. Full article

Cardiorespiratory fitness is a predictor of long-term health, traditionally assessed through structured exercise protocols that require maximal effort and controlled laboratory conditions. These protocols, while clinically validated, are often inaccessible, physically demanding, and unsuitable for unsupervised monitoring. This study proposes a non-invasive, unsupervised alternative—predicting the heart rate a person would reach after completing the step test, using wearable data collected during natural daily activities. Ground truth post-exercise heart rate was obtained through the Queens College Step Test, which is a submaximal protocol widely used in fitness settings. Separately, wearable sensors recorded heart rate (HR), blood oxygen saturation, and motion data during a protocol of lifestyle tasks spanning a range of intensities. Two machine learning models were developed—a Human Activity Recognition (HAR) model that classified daily activities from inertial data with 96.93% accuracy, and a regression model that estimated post step test HR using motion features, physiological trends, and demographic context. The regression model achieved an average root mean squared error (RMSE) of 5.13 beats per minute (bpm) and a mean absolute error (MAE) of 4.37 bpm. These findings demonstrate the potential of test-free methods to estimate standardized test outcomes from daily activity data, offering an accessible pathway to infer cardiorespiratory fitness. Full article

Background: Artificial intelligence (AI) and machine learning (ML) have been reshaping maternal, fetal, neonatal, and reproductive healthcare by enhancing risk prediction, diagnostic accuracy, and operational efficiency across the perinatal continuum. However, no comprehensive synthesis has yet been published. Objective: To conduct a scoping review of reviews of AI/ML applications spanning reproductive, prenatal, postpartum, neonatal, and early child-development care. Methods: We searched PubMed, Embase, the Cochrane Library, Web of Science, and Scopus through April 2025. Two reviewers independently screened records, extracted data, and assessed methodological quality using AMSTAR 2 for systematic reviews, ROBIS for bias assessment, SANRA for narrative reviews, and JBI guidance for scoping reviews. Results: Thirty-nine reviews met our inclusion criteria. In preconception and fertility treatment, convolutional neural network-based platforms can identify viable embryos and key sperm parameters with over 90 percent accuracy, and machine-learning models can personalize follicle-stimulating hormone regimens to boost mature oocyte yield while reducing overall medication use. Digital sexual-health chatbots have enhanced patient education, pre-exposure prophylaxis adherence, and safer sexual behaviors, although data-privacy safeguards and bias mitigation remain priorities. During pregnancy, advanced deep-learning models can segment fetal anatomy on ultrasound images with more than 90 percent overlap compared to expert annotations and can detect anomalies with sensitivity exceeding 93 percent. Predictive biometric tools can estimate gestational age within one week with accuracy and fetal weight within approximately 190 g. In the postpartum period, AI-driven decision-support systems and conversational agents can facilitate early screening for depression and can guide follow-up care. Wearable sensors enable remote monitoring of maternal blood pressure and heart rate to support timely clinical intervention. Within neonatal care, the Heart Rate Observation (HeRO) system has reduced mortality among very low-birth-weight infants by roughly 20 percent, and additional AI models can predict neonatal sepsis, retinopathy of prematurity, and necrotizing enterocolitis with area-under-the-curve values above 0.80. From an operational standpoint, automated ultrasound workflows deliver biometric measurements at about 14 milliseconds per frame, and dynamic scheduling in IVF laboratories lowers staff workload and per-cycle costs. Home-monitoring platforms for pregnant women are associated with 7–11 percent reductions in maternal mortality and preeclampsia incidence. Despite these advances, most evidence derives from retrospective, single-center studies with limited external validation. Low-resource settings, especially in Sub-Saharan Africa, remain under-represented, and few AI solutions are fully embedded in electronic health records. Conclusions: AI holds transformative promise for perinatal care but will require prospective multicenter validation, equity-centered design, robust governance, transparent fairness audits, and seamless electronic health record integration to translate these innovations into routine practice and improve maternal and neonatal outcomes. Full article

Background and Objectives: Heart failure (HF) and chronic kidney disease (CKD) frequently coexist and are closely interrelated, significantly affecting clinical outcomes. Among CKD-related markers, albuminuria and estimated glomerular filtration rate (eGFR) have emerged as key prognostic indicators in HF. However, their specific predictive value across different HF phenotypes—namely HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF)—remains incompletely understood. This systematic review aims to evaluate the prognostic significance of albuminuria and eGFR in patients with HF and to compare their predictive roles in HFpEF versus HFrEF populations. Materials and Methods: We conducted a systematic search of major databases to identify clinical studies evaluating the association between albuminuria, eGFR, and adverse outcomes in HF patients. Inclusion criteria encompassed studies reporting on cardiovascular events, all-cause mortality, or HF-related hospitalizations, with subgroup analyses based on ejection fraction. Data extraction and quality assessment were performed independently by two reviewers. Results: Twenty-one studies met the inclusion criteria, including diverse HF populations and various biomarker assessment methods. Both albuminuria and reduced eGFR were consistently associated with increased risk of mortality and hospitalization. In HFrEF populations, reduced eGFR demonstrated stronger prognostic associations, whereas albuminuria was predictive across both HF phenotypes. Heterogeneity in study design and outcome definitions limited comparability. Conclusions: Albuminuria and eGFR are valuable prognostic biomarkers in HF and may enhance risk stratification and clinical decision-making, particularly when integrated into clinical assessment models. Differential prognostic implications in HFpEF versus HFrEF highlight the need for phenotype-specific approaches. Further research is warranted to validate these findings and clarify their role in guiding personalized therapeutic strategies in HF populations. Limitations: The current evidence base consists primarily of observational studies with variable methodological quality and inconsistent reporting of effect estimates. Full article

Background/Objectives: Real-world evidence shows alarmingly suboptimal utilization of guideline directed medical therapy (GDMT) in heart failure with reduced ejection fraction (HFrEF). One of the barriers of GDMT implementation appears to be concerns about the potential development of drug-related adverse events (AEs), particularly in high-risk patients. This study aimed to evaluate whether advanced HFrEF (AHF) patients can be up-titrated safely and whether AHF predisposes individuals to the occurrence of putatively drug-related AEs. Methods: A total of 373 HFrEF patients with documented baseline, 2 months, and 12 months visits were analyzed for utilization and target dosages (TDs) of HF drugs. Successful up-titration and AEs were evaluated for different stages of HF reflected by N-terminal pro-B type natriuretic peptide (NT-proBNP) (<1000 pg/mL, 1000–2000 pg/mL, >2000 pg/mL). Results: A stepwise increase in HF medications was observed for all drug classes during follow-up. At 12 months, 73%, 75%, 62%, 86%, and 45% of patients received ≥90% of TDs of beta-blockers (BBs), renin–angiotensin system inhibitors (RASis), mineralocorticoid receptor antagonists (MRAs), sodium–glucose cotransporter-2 inhibitors (SGLT2 i), and triple-therapy, respectively. Predictors of successful up-titration in logistic regression were baseline HF drug TDs, estimated glomerular filtration rate (eGFR), and potassium, but not NT-proBNP or age. The development of AEs was rare, with hyperkalemia as the most common event (34% at 12 months). AEs were comparable in all stages of HF. However, the development of hyperkalemia was more frequent in patients with higher NT-proBNP and also accounted for most cases of incomplete up-titration. Conclusions: This study suggests that with dedicated protocols and frequent visits, GDMT can be successfully implemented across all stages of HFrEF, including patients with AHF. Full article

Inflammatory biomarkers, including high-sensitivity C-reactive protein (hsCRP), serum amyloid A (SAA), and interleukin-6 (IL-6), have been associated with an increased risk of future cardiovascular events. While they provide valuable prognostic information, these associations do not necessarily imply a direct causal role. The combined prognostic utility of these markers, however, remains insufficiently studied. We analysed 3300 well-characterised participants of the Ludwigshafen Risk and Cardiovascular Health (LURIC) study, all of whom underwent coronary angiography. Participants were stratified based on their serum concentrations of hsCRP, SAA, and IL-6. Associations between biomarker combinations and mortality were assessed using multivariate Cox regression and ROC analysis. Individuals with elevated hsCRP and SAA or IL-6 showed higher prevalence rates of coronary artery disease, heart failure, and adverse metabolic traits. These “both high” groups had lower estimated glomerular filtration rate, higher NT-proBNP, and increased HbA1c. Combined elevations of hsCRP and SAA were significantly associated with higher all-cause and cardiovascular mortality in partially adjusted models. However, these associations weakened after adjusting for IL-6. IL-6 alone demonstrated the highest predictive power (AUC: 0.638) and improved risk discrimination when included in multi-marker models. The co-elevation of hsCRP, SAA, and IL-6 identifies a high-risk phenotype characterised by greater cardiometabolic burden and increased mortality. IL-6 may reflect upstream inflammatory activity and could serve as a therapeutic target. Multi-marker inflammatory profiling holds promise for refining cardiovascular risk prediction and advancing personalised prevention strategies. Full article

The global prevalence of hypertension continues to rise, affecting an estimated one billion worldwide. Regular exercise is well recognized as a non-pharmacological approach for individuals with hypertension due to its blood pressure (BP)-lowering effect, largely attributed to repeated exposure to post-exercise hypotension (PEH). Recent evidence also indicates that aromatherapy can contribute to BP reduction, indicating that combining aromatherapy with exercise may enhance the overall BP-lowering effects. Therefore, this pilot study aimed to investigate the effects of aromatherapy on PEH during the recovery phase following exercise. Fourteen healthy young males (22.7 ± 0.7 yrs) participated in this randomized crossover-designed study. All participants completed two exercise sessions per week, each lasting 30 min, at a target heart rate (HR) of 60–65%. The individuals inhaled either aroma oil or water vapor at 5, 35, 65, and 95 min after exercise. The HR, BP, blood lactate level, and arterial stiffness index were measured before and after the exercise. Our findings revealed the following. (1) PEH occurred in both groups. (2) In the aroma group, PEH was augmented compared with the control group, with the maximum reduction in BP being greater in the aroma group. (3) The reduction in arterial stiffness was greater and longer in the aroma group than in the control group. (4) The changes in the lactate levels after exercise did not differ between the groups. Our findings indicate that aromatherapy can amplify PEH, suggesting that its use after exercise may help maximize the positive effects of exercise on BP reduction. Full article

Human-Robot Collaboration (HRC) is pivotal for flexible, worker-centric manufacturing in Industry 5.0, yet dynamic task allocation remains difficult because operator states—fatigue and skill—fluctuate abruptly. I address this gap with a hybrid framework that couples real-time perception and double-estimating reinforcement learning. A Convolutional Neural Network (CNN) classifies nine fatigue–skill combinations from synthetic physiological cues (heart-rate, blink rate, posture, wrist acceleration); its outputs feed a Double Deep Q-Network (DDQN) whose state vector also includes task-queue and robot-status features. The DDQN optimises a multi-objective reward balancing throughput, workload and safety and executes at 10 Hz within a closed-loop pipeline implemented in MATLAB R2025a and RoboDK v5.9. Benchmarking on a 1000-episode HRC dataset (2500 allocations·episode⁻¹) shows the hybrid CNN+DDQN controller raises throughput to 60.48 ± 0.08 tasks·min⁻¹ (+21% vs. rule-based, +12% vs. SARSA, +8% vs. Dueling DQN, +5% vs. PPO), trims operator fatigue by 7% and sustains 99.9% collision-free operation (one-way ANOVA, p < 0.05; post-hoc power 1 − β = 0.87). Visual analyses confirm responsive task reallocation as fatigue rises or skill varies. The approach outperforms strong baselines (PPO, A3C, Dueling DQN) by mitigating Q-value over-estimation through double learning, providing robust policies under stochastic human states and offering a reproducible blueprint for multi-robot, Industry 5.0 factories. Future work will validate the controller on a physical Doosan H2017 cell and incorporate fairness constraints to avoid workload bias across multiple operators. Full article

Background/Objectives: Heart failure with reduced ejection fraction (HFrEF) is associated with significant renal complications, affecting disease progression and patient outcomes. Sodium-glucose co-transporter-2 (SGLT2) inhibitors have emerged as a key therapeutic strategy, offering cardiovascular and renal benefits in these patients. However, interindividual variability in response to dapagliflozin underscores the role of pharmacogenetics in optimizing treatment efficacy. This study investigates the influence of genetic polymorphisms on renal outcomes in HFrEF patients treated with dapagliflozin, focusing on variations in genes such as SLC5A2, UMOD, KCNJ11, and ACE. Methods: This prospective, observational cohort study was conducted at the National Heart Institute, Cairo, Egypt, enrolling 200 patients with HFrEF. Genotyping of selected single nucleotide polymorphisms (SNPs) was performed using TaqMan™ assays. Renal function, including estimated glomerular filtration rate (eGFR), Kidney Injury Molecule-1 (KIM-1), and Neutrophil Gelatinase-Associated Lipocalin (NGAL) levels, was assessed at baseline and after six months of dapagliflozin therapy. Results: Significant associations were found between genetic variants and renal outcomes. Patients with AA genotype of rs3813008 (SLC5A2) exhibited the greatest improvement in eGFR (+7.2 mL ± 6.5, p = 0.004) and reductions in KIM-1 (−0.13 pg/mL ± 0.49, p < 0.0001) and NGAL (−6.1 pg/mL ± 15.4, p < 0.0001). Similarly, rs12917707 (UMOD) TT genotypes showed improved renal function. However, rs5219 (KCNJ11) showed no significant impact on renal outcomes. Conclusions: Pharmacogenetic variations influenced renal response to dapagliflozin in HFrEF patients, particularly in SLC5A2 and UMOD genes. These findings highlighted the potential of personalized medicine in optimizing therapy for HFrEF patients with renal complications. Full article

Background: Dapagliflozin, a sodium–glucose cotransporter 2 (SGLT2) inhibitor, has been shown to improve prognosis in patients with chronic heart failure (CHF), in whom a transient decline in the estimated glomerular filtration rate (eGFR), known as the “initial dip,” is often observed within the first 1–2 weeks of SGLT2 inhibitor therapy. This study aimed to investigate the factors associated with this initial dip and its impact on long-term renal function in patients with CHF initiating dapagliflozin. Methods and Results: This retrospective study included 123 consecutive CHF patients who were started on dapagliflozin at our institution. The presence of an initial dip was defined as a decrease in the eGFR of ≥5 mL/min/1.73 m² within two weeks of initiating therapy. Baseline clinical characteristics and renal function data were analyzed. Older age, hypertension, diabetes mellitus, and a higher baseline eGFR were identified as significant risk factors for the initial dip. Furthermore, both age and the presence of an initial dip were significantly associated with changes in the eGFR at 6 months and 1 year. In patients who experienced an initial dip, the eGFR showed a persistent downward trajectory from the baseline over time. Conclusions: An initial dip is more likely to occur in older patients and those with hypertension and/or diabetes mellitus. The presence of an initial dip may also influence long-term renal outcomes and could serve as an indicator of long-term renoprotective efficacy. Full article

Continuous blood pressure (BP) monitoring provides valuable insight into the body’s dynamic cardiovascular regulation across various physiological states such as physical activity, emotional stress, postural changes, and sleep. Continuous BP monitoring captures different variations in systolic and diastolic pressures, reflecting autonomic nervous system activity, vascular compliance, and circadian rhythms. This enables early identification of abnormal BP trends and allows for timely diagnosis and interventions to reduce the risk of cardiovascular diseases (CVDs) such as hypertension, stroke, heart failure, and chronic kidney disease as well as chronic stress or anxiety disorders. To facilitate continuous BP monitoring, we propose an AI-powered estimation framework. The proposed framework first uses an expert-driven feature engineering approach that systematically extracts physiological features from photoplethysmogram (PPG)-based arterial pulse waveforms (APWs). Extracted features include pulse rate, ascending/descending times, pulse width, slopes, intensity variations, and waveform areas. These features are fused with demographic data (age, gender, height, weight, BMI) to enhance model robustness and accuracy across diverse populations. The framework utilizes a Tab-Transformer to learn rich feature embeddings, which are then processed through an ensemble machine learning framework consisting of CatBoost, XGBoost, and LightGBM. Evaluated on a dataset of 1000 subjects, the model achieves Mean Absolute Errors (MAE) of 3.87 mmHg (SBP) and 2.50 mmHg (DBP), meeting British Hypertension Society (BHS) Grade A and Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed architecture advances non-invasive, AI-driven solutions for dynamic cardiovascular health monitoring. Full article

Background: In advanced heart failure patients implanted with a fully magnetically levitated HeartMate 3 (HM3) Abbott left ventricular assist device (LVAD), it is unknown how the role of the LVAD outpatient clinic may affect the long-term survival after hospital discharge. Our objective is to share our standardized protocol for outpatient care, to describe the role of the LVAD outpatient clinic in postoperative long-term care after LVAD implantation, and to report survival. Methods: We retrospectively reviewed all patients implanted with HM3 LVAD in our institute between September 2015 and January 2025. Patients who received HeartWare Ventricular Assist Device (HVAD) and HeartMate 2 LVAD devices were excluded from our study, to ensure a homogenous cohort focusing on the latest and the only currently used LVAD device generation. We included a total of 48 patients. After LVAD patients are discharged from our center, they are followed in our outpatient clinic in 3-month intervals. During visits, bloodwork, EKG, wound inspection, and echocardiography are performed in addition to LVAD analysis. The role of the outpatient clinic is to detect early signs of deterioration or problems and act accordingly to prevent serious complications. Results: Thirty-three patients (68.7%) are still alive in 2025; two patients (4.2%) had a successful heart transplantation; and thirty-one patients (64.5%) are still on LVAD support. There were 210 total patient years of support. The mean time on device is 4.4 years. During the follow-up period we noticed 15 deaths (31.3%). Notably, there was no technical device-related death. Kaplan–Meier analysis estimated an overall survival rate of 97.9%, 92.8%, 83.7%, and 51.1% at 1, 2, 4, and 8 years, respectively. Conclusion: Strict control of patients after discharge in an outpatient clinic is essential for the long-term survival of these patients. A well-structured outpatient program is of utter importance to avoid LVAD-related complications and should be a cornerstone for the treatment, especially in non-transplant centers. Full article

Background/Objectives: Haloperidol is a typical antipsychotic drug widely used for acute confusional state, psychotic disorders, agitation, delirium, and aggressive behavior. Methods: The toxicity of haloperidol was studied using zebrafish (ZF) embryos as a model organism. Dechorionated embryos were exposed to various concentrations of haloperidol (0.5–6.0 mg/L). The lethal dose concentration was estimated and was found to be 1.941 mg/L. Results: The impact of haloperidol was dose-dependent and significant from 0.25 mg/L. Haloperidol induced several deformities at sublethal doses, including abnormal somites, yolk sac edema, and skeletal deformities. Haloperidol significantly affected heart rate and blood flow and induced pericardial edema and hyperemia in a dose-dependent manner, suggesting its influence on heart development and function. Embryos exposed to haloperidol during their ontogenetic development had smaller body length and eye surface area than non-exposed ones in a dose-dependent manner. Conclusions: It was found that haloperidol significantly affects the behavior of the experimental organisms in terms of mobility, reflexes to stimuli, and adaptation to dark/light conditions. Full article

Smart glasses are promising alternatives for the continuous, unobtrusive monitoring of heart rate (HR). This study validates HR estimates obtained with the “Essilor Connected Glasses” (SmartEW) during sedentary activities. Thirty participants wore the SmartEW, equipped with an IMU sensor for HR estimation, a commercial smartwatch (Garmin Venu 3), and an ECG device (Movesense Flash). The protocol included six static tasks performed under controlled laboratory conditions. The SmartEW algorithm analyzed 22.5 s signal windows using spectral analysis to estimate HR and provide a quality index (QI). Statistical analyses assessed agreement with ECG and the impact of QI on HR accuracy. SmartEW showed high agreement with ECG, especially with QI threshold equal to 70, as a trade-off between accuracy, low error, and acceptable data coverage (80%). Correlation for QI ≥ 70 was high across all the experimental phases (r² up to 0.96), and the accuracy within ±5 bpm reached 95%. QI ≥ 70 also allowed biases to decrease (e.g., from −1.83 to −0.19 bpm while standing), with narrower limits of agreement, compared to ECG. SmartEW showed promising HR accuracy across sedentary activities, yielding high correlation and strong agreement with ECG and Garmin. SmartEW appears suitable for HR monitoring in static conditions, particularly when data quality is ensured. Full article