Nephrology

Single center Automated, Multi-Source deeply Phenotyped Heart Transplant Registry as a template to build tailored data infrastructure

Background: Traditional heart transplant registries often lack the granularity required for deep phenotyping and rely on labor-intensive manual abstraction. We describe the methodology and validation of a next-generation, automated, multi-source registry designed to address these limitations. Methods: Utilizing a High-Performance Computing environment, we integrated structured data from Epic data ...

Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images

Automated detection of electron dense deposits (EDD) in glomerular disease is hindered by the scarcity of high-quality labeled data. While crowdsourcing reduces annotation cost, it introduces label noise. We propose an active label cleaning method to efficiently denoise crowdsourced datasets. Our approach uses active learning to select the most valuable noisy samples for expert re-annotation, buil...

Personalised approach to hypertension treatment: Rationale and design of the HYPERMARKER randomised trial

Background and Objective: Blood pressure treatment response is variable in individual patients, and the choice of medical therapy is often dependent o...

Fast Organ-of-Origin Classification for Digital Pathology Quality Control

Digitizing large histopathology archives requires processing millions of scanned whole slide images that must be validated rapidly. Automated organ-of...

XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas

Accurate risk stratification of precancerous polyps during routine colonoscopy screenings is essential for lowering the risk of developing colorectal ...

Development and internal validation of risk scores to predict survival in the pediatric population following in-hospital cardiac arrest.

Introduction In-hospital cardiac arrest (IHCA) in the pediatric population is associated with poor survival and neurological outcomes. We aimed to dev...

Deep Learning-Enabled Screening of Chronic Kidney Disease from Echocardiography

Chronic kidney disease (CKD) affects nearly 850 million individuals globally; the prevalence of undiagnosed CKD is 60%. Taking advantage of the relati...

Improving mortality prediction in critically ill cancer patients with a multidimensional machine learning model

Background: Prognostic assessment in critically ill patients with cancer remains challenging, as conventional ICU severity scores often perform subopt...

Automated Segmentation of Kidney Nephron Structures by Deep Learning Models on Label-free Autofluorescence Microscopy for Spatial Multi-omics Data Acquisition and Mining

Automated spatial segmentation models can enrich spatio-molecular omics analyses by providing a link to relevant biological structures. We developed s...

Determinants of Digital Health Technology Acceptance Among Healthcare Caregivers: A Structural Equation Modeling Approach

Background: Digital health technologies, including artificial intelligence (AI)-powered tools and virtual reality (VR) interventions, are increasingly...

Nab-paclitaxel fused with the de novo designed receptor binder exhibits enhanced tumor targeting and therapeutic efficacy

Chemotherapy has been widely used in cancer treatment, but most of the chemotherapeutic drugs rely mainly on passive accumulation due to lack of targe...

Gene-centered representation of coding and regulatory variation enables outcome prediction

Integrating coding and regulatory variation into unified, interpretable representations remains a challenge in functional genomics. Current approaches...

Machine Learning Ensemble Reveals Distinct Molecular Pathways of Retinal Damage in Spaceflown Mice

Spaceflight-associated neuro-ocular syndrome (SANS) threatens astronaut health during long-duration missions, yet its molecular pathology remains uncl...

An Advanced Humanized Systemic Lupus Erythematosus Model Enables Parallel Profiling of B Cell-Targeted Therapies

B cell-targeted therapies represent a transformative frontier for systemic lupus erythematosus (SLE) intervention, yet clinical recommendation of spec...

C-RLM: Schema-Enforced Recursive Synthesis for Auditable, Long-Context Clinical Documentation

Clinical decision-making for multi-morbid patients requires synthesizing evidence from lengthy, fragmented records-a task that exposes the limitations...

Learning temporal embeddings from electronic health records of chronic kidney disease patients

We investigate whether temporal embedding models trained on longitudinal electronic health records can learn clinically meaningful representations wit...

Deep Learning Decodes Latent ECG Signatures of Stress Cardiomyopathy

Background Stress cardiomyopathy (SCM) shares features with acute myocardial infarction (AMI) which may lead to misdiagnosis and misaligned management...

ComPRePS: Unlocking Scalable AI Analysis for Computational Renal Pathology

Digital pathology using whole slide imaging (WSI) and artificial intelligence (AI) has the potential to transform diagnostic workflows, but adoption r...

Pharmacogenomic Determinants of Post-Liver Transplant Diabetes Mellitus: A Systematic Review and In Silico Pharmacogenomic Analysis

Introduction: Tacrolimus remains central to liver transplantation, yet its narrow therapeutic index and pharmacokinetic variability are associated wit...

High-PepBinder: A pLM-Guided Latent Diffusion Framework for Affinity-Aware Target-Specific Peptide Design

Peptides, as therapeutic molecules, offer unique advantages in targeting complex protein surfaces, yet their rational design remains limited by the va...