Search Results (292)

Background and Objectives: Contrast-associated acute kidney injury (CA-AKI) is a frequent and clinically significant complication in patients with acute myocardial infarction (AMI) undergoing coronary angiography. Early and accurate risk stratification remains challenging with conventional models that rely on linear assumptions and limited variable integration. This study aimed to evaluate and compare the predictive performance of multiple machine learning (ML) algorithms with traditional logistic regression and the Mehran risk score for CA-AKI prediction and to explore key determinants of risk using explainable artificial intelligence methods. Materials and Methods: This retrospective, single-center study included 1741 patients with AMI who underwent coronary angiography. CA-AKI was defined according to KDIGO criteria. Multiple ML models, including gradient boosting machine (GBM), random forest (RF), XGBoost, support vector machine, elastic net, and standard logistic regression were developed using routinely available clinical and laboratory variables. A weighted ensemble model combining the best-performing algorithms was constructed. Model discrimination was assessed using area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Model interpretability was evaluated using feature importance and SHapley Additive exPlanations (SHAP). Results: CA-AKI occurred in 356 patients (20.4%). In multivariable logistic regression, lower left ventricular ejection fraction, higher contrast volume, lower sodium, lower hemoglobin, and higher neutrophil-to-lymphocyte ratio (NLR) were independently associated with CA-AKI. Among ML approaches, the weighted ensemble model demonstrated the highest discriminative performance (AUC 0.721), outperforming logistic regression and the Mehran risk score (AUC 0.608). Importantly, the ensemble model achieved a consistently high NPV (0.942), enabling reliable identification of low-risk patients. Explainability analyses revealed that inflammatory markers, particularly NLR, along with sodium, uric acid, baseline renal indices, and contrast burden, were the most influential predictors across models. Conclusions: In patients with AMI undergoing coronary angiography, interpretable ML models, especially ensemble and gradient boosting-based approaches, provide superior risk stratification for CA-AKI compared with conventional methods. The high negative predictive value highlights their clinical utility in safely identifying low-risk patients and supporting individualized, risk-adapted preventive strategies. Full article

For more than a century, pathology has served as a cornerstone of modern medicine, relying primarily on static microscopic assessment of tissue morphology—such as H&E staining—which remains the “gold standard” for disease diagnosis. However, this conventional paradigm provides only a snapshot of disease states and often fails to capture their dynamic evolution and complex functional mechanisms. Moreover, animal models are constrained by marked interspecies differences, creating a persistent gap in translational research. To overcome these limitations, we propose the concept of New Pathophysiology, a research framework that transcends purely morphological descriptions and aims to resolve functional dynamics in real time. This approach integrates Organ-on-a-Chip (OOC) technology, multi-omics analyses, and artificial intelligence to reconstruct the entire course of disease initiation and to enable personalized medicine. In this review, we first outline the foundations and limitations of traditional pathology and animal models. We then systematically summarize more than one hundred existing OOC disease models across multiple organs—including the kidney, liver, and brain. Finally, we elaborate on how OOC technologies are reshaping the study of key pathological processes such as inflammation, metabolic dysregulation, and fibrosis by converting them into dynamic, mechanistic disease models, and we propose future perspectives in the field. This review adopts a relatively uncommon classification strategy based on pathological mechanisms (mechanism-based), rather than organ-based categorization, allowing readers to recognize shared principles underlying different diseases. Moreover, the focus of this work is not on emphasizing iteration or replacement of existing approaches, but on preserving past achievements from a historical perspective, with an emphasis on overcoming current limitations and enabling new advances. Full article

Optimizing immunosuppressant dosing presents significant challenges in kidney transplantation due to narrow therapeutic ranges and considerable inter-patient pharmacokinetic differences. Emerging strategies for precision dosing, encompassing Bayesian population pharmacokinetic models, pharmacogenomic integration, and artificial intelligence algorithms, aim to enhance drug monitoring by moving beyond traditional trough-based approaches. This review critically assesses available evidence for predictive dosing models targeting immunosuppressants, including calcineurin inhibitors, antimetabolites, and mTOR inhibitors in kidney transplant patients. Available observational and simulation studies demonstrate substantial methodological diversity, with Bayesian PopPK-guided strategies showing 15–35% better target exposure achievement compared to trough-based monitoring. The absence of pooled estimates precludes a precise summary effect size, and evidence from randomized controlled trials remains limited. Machine learning models, particularly for tacrolimus, frequently reduced prediction error relative to traditional regression approaches, but substantial heterogeneity in study design, outcome definitions, and external validation limits quantitative synthesis. Hybrid Bayesian–AI frameworks and explainable AI tools show conceptual promise but are largely supported by proof-of-concept studies rather than reproducible clinical implementations. Overall, Bayesian pharmacokinetic modelling represents the most mature and clinically interpretable approach for precision dosing in transplantation, whereas AI-driven and hybrid systems remain investigational. Key gaps include the need for standardized reporting, rigorous risk-of-bias assessment, prospective validation, and clearer regulatory and implementation pathways to support safe and equitable clinical adoption. Full article

Although the SARS-CoV-2 pandemic no longer poses a global emergency, the virus continues to diversify and acquire immunoevasive properties. Understanding the molecular pathways that shape SARS-CoV-2 pathogenesis has become essential. In this paper, we summarize the most recent current evidence on how the spike protein structurally evolves, on changes in key non-structural proteins, such as nsp14, and on host factors, such as TMPRSS2 and neuropilin-1. These changes, together, shape viral entry, replication fidelity and interferon antagonism. Given the emerging Omicron variants of SARS-CoV-2, recent articles in the literature, cryo-EM analyses, and artificial intelligence-assisted mutational modeling were analyzed to infer and contextualize mutation-driven mechanisms. It is through these changes that the virus adapts and evolves, such as optimizing angiotensin-converting enzyme binding, modifying antigenic surfaces, and accumulating mutations that affect CD8⁺ T-cell recognition. Multi-omics data studies further support SARS-CoV-2 pathogenesis through convergent evidence linking viral adaptation to host immune and metabolic reprogramming, as occurs in myocarditis, liver injury, and acute kidney injury. By integrating proteomic, transcriptomic, and structural findings, this work presents how the virus persists and dictates disease severity through interferon antagonism (ORF6, ORF9b, and nsp1), adaptive immune evasion, and metabolic rewiring. All these insights underscore the need for next-generation interventions that provide a multidimensional framework for understanding the evolution of SARS-CoV-2 and guiding future antiviral strategies. Full article

Chronic kidney disease (CKD) impacts more than 850 million people globally, yet existing machine learning methodologies for risk stratification encounter substantial challenges: computationally intensive hyperparameter tuning, model opacity that conflicts with clinical interpretability standards, and class imbalance leading to systematic prediction bias. We constructed an integrated architecture that combines XGBoost with Optuna-driven Bayesian optimization, evaluated against 19 competing hyperparameter tuning approaches and tested on CKD patients using dual-paradigm statistical validation. The architecture delivered 93.43% accuracy, 93.13% F1-score, and 97.59% ROC-AUC—representing gains of 6.22 percentage points beyond conventional XGBoost and 7.0–26.8 percentage points compared to 20 baseline algorithms. Tree-structured Parzen Estimator optimization necessitated merely 50 trials compared to 540 for grid search and 1069 for FLAML, whereas Boruta feature selection accomplished 54.2% dimensionality reduction with no performance compromise. Over 30 independent replications, the model exhibited remarkable stability (cross-validation standard deviation: 0.0121, generalization gap: −1.13%) alongside convergent evidence between frequentist and Bayesian paradigms (all p < 0.001, mean CI-credible interval divergence < 0.001, effect sizes d = 0.665–5.433). Four separate explainability techniques (SHAP, LIME, accumulated local effects, Eli5) consistently identified CKD stage and albumin-creatinine ratio as principal predictors, aligning with KDIGO clinical guidelines. Clinical utility evaluation demonstrated 98.4% positive case detection at 50% screening threshold alongside near-optimal calibration (mean absolute error: 0.138), while structural equation modeling revealed hyperuricemia (β = −3.19, p < 0.01) as the most potent modifiable risk factor. This dual-validated architecture demonstrates that streamlined hyperparameter optimization combined with convergent multi-method interpretability enables precise CKD risk stratification with clinical guideline alignment, supporting evidence-informed screening protocols. Full article

Heart failure (HF) and chronic kidney disease (CKD) are prevalent conditions in older adults, often coexisting and significantly increasing the risk of hospitalization, cardiovascular events, and mortality. Traditional hospital-based care, while essential for acute management, is often insufficient to ensure continuity of care and optimal long-term outcomes. Home-based care, although promising for improving quality of life and reducing hospital-acquired complications, faces challenges related to treatment adherence, monitoring, and caregiver support. Recent evidence highlights the potential of multidisciplinary, patient-centered care models integrating physicians, nurses, pharmacists, and family caregivers. Technological innovations, including telemedicine, remote monitoring, mobile health applications, and artificial intelligence, have shown efficacy in early detection of clinical deterioration, improving adherence, and reducing cardiovascular events in HF and CKD patients. Structured patient education, caregiver training, and proactive follow-up are key elements to optimize transitions from hospital to home and to improve long-term outcomes, including reduced rehospitalizations and better quality of life. Future care strategies should focus on personalized, integrated approaches that combine technology, education, and multidisciplinary collaboration to address the complex needs of HF and CKD patients, while mitigating healthcare costs and enhancing overall patient well-being. Full article

This retrospective diagnostic accuracy study compared radiologist-based qualitative assessments and radiomics-based analyses with an automated artificial intelligence (AI)–based volumetric approach for evaluating changes in kidney stone burden on follow-up CT examinations. With institutional review board approval, 157 patients (mean age, 61 ± 13 years; 99 men, 58 women) who underwent baseline and follow-up non-contrast abdomen–pelvis CT for kidney stone evaluation were included. The index test was an automated AI-based whole-kidney and stone segmentation radiomics prototype (Frontier, Siemens Healthineers), which segmented both kidneys and isolated stone volumes using a fixed threshold of 130 Hounsfield units, providing stone volume and maximum diameter per kidney. The reference standard was a threshold-defined volumetric assessment of stone burden change between baseline and follow-up CTs. The radiologist’s performance was assessed using (1) interpretations from clinical radiology reports and (2) an independent radiologist’s assessment of stone burden change (stable, increased, or decreased). Diagnostic accuracy was evaluated using multivariable logistic regression and receiver operating characteristic (ROC) analysis. Automated volumetric assessment identified stable (n = 44), increased (n = 109), and decreased (n = 108) stone burden across the evaluated kidneys. Qualitative assessments from radiology reports demonstrated weak diagnostic performance (AUC range, 0.55–0.62), similar to the independent radiologist (AUC range, 0.41–0.72) for differentiating changes in stone burden. A model incorporating higher-order radiomics features achieved an AUC of 0.71 for distinguishing increased versus decreased stone burdens compared with the baseline CT (p < 0.001), but did not outperform threshold-based volumetric assessment. The automated threshold-based volumetric quantification of kidney stone burdens provides higher diagnostic accuracy than qualitative radiologist assessments and radiomics-based analyses for identifying a stable, increased, or decreased stone burden on follow-up CT examinations. Full article

Background: Nuclear Magnetic Resonance (NMR) spectroscopy is a powerful analytical tool in metabolomics, but it is often hindered by the high cost and technical complexity of the machines, limiting its clinical and point-of-care applications. Recent advances in benchtop NMR technology have sought to overcome these barriers by providing more compact, affordable, and user-friendly instruments. This systematic review aims to assess the potential of benchtop NMR in clinical metabolomics, highlighting its practical advantages, current applications, and technological challenges relative to high-field systems. Methods: For this systematic review we searched Web of Science and PubMed databases to identify studies employing benchtop NMR spectroscopy in clinical and biomedical applications. The review focuses on works that evaluated metabolic profiling in human and animal disease contexts, compared benchtop and high-field performance, and utilized advanced data analysis methods, including multivariate and machine learning approaches. Results: Among the 74 records identified, 15 research articles were eligible, including 11 studies involving human biospecimens and 4 studies concerning animal samples. The selected works were published between 2018 and 2025. These studies demonstrated the potential clinical utility of low-field NMR in differentiating disease states such as tuberculosis, type 2 diabetes, neonatal sepsis, and chronic kidney disease, achieving diagnostic accuracies comparable to high-field instruments. Conclusions: Although limited by lower sensitivity and spectral resolution, benchtop NMR represents a significant step toward the democratization of NMR-based metabolomics. Continued hardware development, improved pulse sequences, and the integration of artificial intelligence for spectral processing and modeling are expected to enhance its analytical power and accelerate its clinical adoption. Full article

Aspartame, a widely used artificial sweetener, has been linked to various cancers, including kidney renal papillary cell carcinoma (KIRP). However, the molecular mechanisms underlying this association remain unclear. This study employed network toxicology and molecular docking to investigate potential mechanisms of aspartame-induced KIRP. Differentially expressed genes from TCGA were intersected with aspartame targets and KIRP-related genes, yielding 61 common targets. GO and KEGG analyses revealed enrichment in extracellular matrix degradation, signaling pathways, and immune microenvironment regulation. Univariate Cox regression identified 23 prognostically significant genes, from which multifactorial Cox regression with stepwise selection determined 8 core genes (APLNR, CYP2C19, EDNRA, KLK5, F2R, RAD51, AURKA, and TLR2). A risk model was constructed and validated through VIF analysis, Schoenfeld residual testing, and internal validation using a training–validation split. SHAP analysis identified EDNRA as the primary driver gene. Survival analysis demonstrated that the model effectively stratified KIRP patients, with risk score and tumor stage serving as independent prognostic factors. Molecular docking confirmed stable binding between aspartame and core target proteins. These findings provide mechanistic insights into aspartame-induced KIRP pathogenesis and establish a foundation for future experimental validation. Full article

Background and Clinical Significance: Isoechoic renal tumors, defined as masses demonstrating echogenicity similar to normal renal parenchyma, represent a significant diagnostic challenge in contemporary ultrasonographic practice. These lesions, occurring in 5–12% of all renal masses, frequently escape detection on conventional ultrasound, leading to delayed diagnosis and potentially adverse oncological outcomes. Isoechoic renal tumors encompass both benign and malignant entities, with clear cell renal cell carcinoma representing 65–70% of malignant cases. Conventional ultrasound shows limited sensitivity (48–67%) for detecting isoechoic masses, while contrast-enhanced ultrasound achieves detection rates of 94–98%. Multiparametric MRI and dual-energy CT provide superior characterization, with accuracy rates of 85–92% for differentiating benign from malignant lesions. Case Presentation: We describe the case of an 80-year-old male in whom a 2.4 cm isoechoic renal mass was incidentally detected during abdominal ultrasound performed for chronic kidney disease monitoring. Contrast-enhanced CT confirmed a solid, hypervascular lesion with wash-out characteristics. Given the patient’s age, comorbidities, and tumor characteristics, multidisciplinary evaluation led to an active surveillance strategy. At 6-month follow-up, the lesion remained stable. Conclusions: Isoechoic renal tumors require multimodal diagnostic approaches and individualized management strategies. Emerging technologies, including artificial intelligence-enhanced ultrasound systems and radiomic-based decision support tools, are undergoing clinical validation and may improve detection and characterization. Investigational approaches such as liquid biopsy and novel PET tracers targeting carbonic anhydrase IX are in early development. Translation of these technologies into clinical practice will require prospective validation, standardization of protocols, and demonstration of cost-effectiveness. Full article

Accessible health information is essential to promote patient engagement and informed participation in clinical research. Brief summaries on ClinicalTrials.gov are indented for lay people; however they are often written at a reading level that is too advanced for the public. This study evaluated the performance of a Generative Artificial Intelligence (GAI)-powered tool—Pub2Post—in producing readable and complete layperson brief summaries for urologic oncology clinical trials. Twenty actively recruiting clinical trials on prostate, bladder, kidney, and testis cancers were retrieved from ClinicalTrials.gov. For each, a GAI-generated summary was produced and compared with its publicly available counterpart. Readability indices, grade-level indicators, and text metrics were analyzed alongside content inclusion across eight structural domains. GAI-generated summaries demonstrated markedly improved readability (mean FRES 73.3 ± 3.5 vs. 17.0 ± 13.1; p < 0.0001), aligning with the recommended middle-school reading level, and achieved 100% inclusion of guideline-defined content elements. GAI summaries exhibited simpler syntax and reduced lexical complexity, supporting improved comprehension. These findings suggest that GAI tools such as Pub2Post can generate patient-facing summaries that are both accessible and comprehensive. Full article

Acute Aortic Syndromes (AAS) and Thoracic Aortic Aneurysm (TAA) remain among the most fatal cardiovascular emergencies, with mortality rising by the hour if diagnosis and treatment are delayed. Despite advances in imaging and surgical techniques, current clinical decision-making still relies heavily on population-based parameters such as maximum aortic diameter, which fail to capture the biological and biomechanical complexity underlying these conditions. In today’s data-rich era, where vast clinical, imaging, and biomarker datasets are available, artificial intelligence (AI) has emerged as a powerful tool to process this complexity and enable precision risk prediction. To date, AI has been applied across multiple aspects of aortic disease management, with mortality prediction being the most widely investigated. Machine learning (ML) and deep learning (DL) models—particularly ensemble algorithms and biomarker-integrated approaches—have frequently outperformed traditional clinical tools such as EuroSCORE II and GERAADA. These models provide superior discrimination and interpretability, identifying key drivers of adverse outcomes. However, many studies remain limited by small sample sizes, single-center design, and lack of external validation, all of which constrain their generalizability. Despite these challenges, the consistently strong results highlight AI’s growing potential to complement and enhance existing prognostic frameworks. Beyond mortality, AI has expanded the scope of analysis to the structural and biomechanical behavior of the aorta itself. Through integration of imaging, radiomic, and computational modeling data, AI now allows virtual representation of aortic mechanics—enabling prediction of aneurysm growth rate, remodeling after repair, and even rupture risk and location. Such models bridge data-driven learning with mechanistic understanding, creating an opportunity to simulate disease progression in a virtual environment. In addition to mortality and growth-related outcomes, morbidity prediction has become another area of rapid development. AI models have been used to assess a wide range of postoperative complications, including stroke, gastrointestinal bleeding, prolonged hospitalization, reintubation, and paraplegia—showing that predictive applications are limited only by clinical imagination. Among these, acute kidney injury (AKI) has received particular attention, with several robust studies demonstrating high accuracy in early identification of patients at risk for severe renal complications. To translate these promising results into real-world clinical use, future work must focus on large multicenter collaborations, external validation, and adherence to transparent reporting standards such as TRIPOD-AI. Integration of explainable AI frameworks and dynamic, patient-specific modeling—potentially through the development of digital twins—will be essential for achieving real-time clinical applicability. Ultimately, AI holds the potential not only to refine risk prediction but to fundamentally transform how we understand, monitor, and manage patients with AAS and TAA. Full article

Background/Objectives: This review paper summarizes and critically analyzes different Machine Learning (ML) and Artificial Intelligence (AI)-based predictive modeling techniques in early detection and personalized treatment for Kidney diseases, specifically diabetic kidney disease (DKD), chronic kidney disease (CKD), and end-stage renal disease (ESRD). This manuscript focuses on integrating electronic medical record (EMR) data with multi-omics biomarkers to enhance clinical decision-making. Method: A systematic database search retrieved 43 peer-reviewed articles from PubMed, Google Scholar, and ScienceDirect. These works were critically analyzed based on methodological rigor, model interpretability, and translational potential. Review: This paper examined a series of advanced AI and ML models, including but not limited to Random Forests (RF), Extreme Gradient Boosting (XGBoost), deep neural networks, and artificial neural networks, among others. Additionally, this paper explicitly explored validated approaches for fibrosis staging, dialysis prediction, and mortality risk assessment. Conclusions: The paper shows how leveraging AI models for patient-specific biomarker and EMR data presents substantial promise for facilitating preventative interventions, guiding timely nephrology referrals, and optimizing individualized treatment regimens. These state-of-the-art tools will ultimately improve long-term renal outcomes and reduce healthcare burdens. The study further addresses ethical challenges and potential adverse implications associated with the use of AI in clinical settings. Full article

Background: Atrial fibrillation (AF) and chronic kidney disease (CKD) often overlap and may amplify cardiovascular risk. Whether renal dysfunction should be incorporated into composite cardiovascular endpoints in AF remains uncertain. We aimed to quantify AF-associated risk of MACE and evaluate the incremental prognostic value of kidney measures (eGFR and albuminuria) to inform composite outcomes and clinical management. Methods: We performed a retrospective, community-based cohort study of 40,297 adults aged 65–95 years. Individuals with incident AF (n = 2574) were followed for 5 years. MACE and components were ascertained from linked health records; only events after AF diagnosis were analyzed. Cox models estimated adjusted hazard ratios (HRs). Risk was further stratified by eGFR stages and urine albumin-to-creatinine ratio (UACR) categories. Exploratory machine learning (ML) was developed to predict MACE in patients with AF and CKD, with model interpretability assessed by feature importance analysis. Results: Incident AF was associated with higher risk of MACE (HR 3.52), CKD (HR 1.97) and all-cause mortality (HR 1.14). CKD was nearly twice more frequent in AF than in non-AF (30.9% vs. 14.5%; p < 0.001). Among patients with AF, a graded eGFR–risk relationship was observed: compared with higher eGFR, MACE risk increased across G3a–G5, peaking in G5 (HR 2.08). Albuminuria showed a parallel gradient: versus UACR <30 mg/g, UACR 30–299 mg/g and ≥300 mg/g were associated with an increased risk of MACE (HR 1.51 and 1.76, respectively). Conclusions: Newly diagnosed AF confers a substantial excess risk of MACE and its components. The consistent eGFR and albuminuria in AF support considering clinically meaningful renal endpoints within composite outcomes and prioritizing integrated cardiorenal management. These findings provide actionable evidence to refine risk stratification and endpoint selection in AF research and care. Full article

Background: Tacrolimus is a cornerstone immunosuppressant in kidney transplantation, but its narrow therapeutic index and marked inter-patient variability complicate dose optimization. Conventional therapeutic drug monitoring (TDM) relies on empirical adjustments that often overlook individual pharmacokinetics. Machine learning (ML) offers a precision dosing alternative by integrating diverse clinical and biochemical variables into predictive models. Methods: We retrospectively analyzed 1351 data points from 87 kidney transplant patients at Eunpyeong St. Mary’s Hospital (April 2019–November 2023). Clinical, demographic, and laboratory information, including tacrolimus trough levels and dosing history, were extracted from electronic medical records. Four predictive models—XGBoost, CatBoost, LightGBM, and a multilayer perceptron (MLP)—were trained to forecast next-day tacrolimus concentrations, and model serum creatinine level performance was evaluated using R-squared (R²), mean absolute error (MAE), and root-mean-squared error (RMSE). An ensemble model with weighted soft voting was applied to enhance predictive accuracy, and model interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: The ensemble model achieved the best overall performance (R² = 0.6297, MAE = 1.0181, RMSE = 1.2999), outperforming all individual models, whereas the MLP model showed superior predictive power among single models, reflecting the significance of nonlinear interactions in tacrolimus pharmacokinetics. SHAP analysis highlighted prior tacrolimus levels, cumulative dose, renal function markers (eGFR level, serum creatinine level), and albumin concentration as the most influential predictors. Conclusions: We present a robust ML-based algorithm for tacrolimus dose optimization in hospitalized kidney transplant recipients. By improving predictions of tacrolimus concentrations, the model may help reduce inter-patient dose variability and lower the risk of nephrotoxicity, supporting safer and more individualized immunosuppressive management. This approach advances AI-driven precision medicine in transplant care, offering a pathway to safer and more effective immunosuppression. Full article