Nephrology

OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib

Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computational models on the corresponding longitudinal patient trajectories. We introduce OncoTraj, a public benchmark of 813 EGFR-mutant NSCLC patients receiving first-l...

Single-Cell Multi-Omics Dissection of Malignant Evolutionary Mechanisms and Construction of a Prognostic Model for Clear Cell Renal Cell Carcinoma

Clear cell renal cell carcinoma (ccRCC) exhibits pronounced heterogeneity across WHO histological grades, yet systematic single-cell multi-omics studies characterizing these transitions remain limited. We integrated scRNA-seq and scATAC-seq data across ccRCC WHO grades to establish a multi-omics framework encompassing tumor cells and immune populations. Using pseudotime trajectory analysis and mac...

Don't stop the heart: a performance analysis of large language models and potassium dosing

Background: Electrolyte replacement is ubiquitous in the acute care setting, but its familiarity cannot belie that even small dosing errors with potas...

Conformal Prediction and Ensemble Learning for Uncertainty-Aware ICU Mortality Stratification

Background. Conventional ICU severity scores - SOFA, qSOFA, and APACHE-II - use additive integer weightings that cannot capture non-linear organ failu...

Real-time artificial intelligence prediction of peptide characteristics and MSFragger search improves multiplexed quantification of non-canonical HLA presented peptides in clear cell renal cell carcinoma.

Non-canonical HLA-presented peptides are promising therapeutic targets, but their low abundance makes them difficult to reproducibly identify and quan...

Algorithmic Versus Expert Rankings of Large Language Models in Peritoneal Dialysis Prescription Review: A Trap-Embedded Synthetic Benchmark

Background: Clinical LLM benchmarks rarely test whether algorithmic rankings agree with expert clinical judgment. We developed a trap-embedded periton...

Boundary-Specific Failure Modes and Safety Trade-offs of Large Language Models in ChronicKidney Disease Renoprotective Therapy Review:A Stratified Synthetic Benchmark

Background.Renoprotective therapies - SGLT2 inhibitors, finerenone, and renin-angiotensin system inhibitors (RASi) - remain underutilisedin chronic ki...

Frontier Large Language Models for Comprehensive Medication Review in CKD Patients with Polypharmacy: A Trap-Embedded Synthetic Benchmark

Background: Patients with CKD and polypharmacy face high rates of drug-related problems, yet comprehensive medication review remains time-intensive an...

VesselSim: learning 3D blood vessel segmentation without expert annotations

Blood vessel segmentation is a core task in medical image analysis for the care of vascular diseases and surgical planning, yet the challenges of prov...

ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data

Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-di...

Predicting 30-Day Heart Failure Readmissions Using Machine Learning: Insights From the Kansas Health Information Network (KHIN)

Background: Heart failure (HF) is a major contributor to inpatient hospital utilization, with persistently high 30-day readmission rates. Existing pre...

DigitAb: Domain-Adaptive Cell Type Prediction Method from Light Microscopy Images

Light microscopy imaging with histological stains is central to disease diagnosis and research. It is enhanced with immunostaining to reveal cellular ...

Engineering Endogenous T Cell Receptors to Recognize Cancer Neoantigens Using a Hybrid Physics-AI Approach

T cell receptors (TCRs) are critical for immune surveillance and successful adaptive immune response against foreign antigens. TCRs drive this key arm...

FlexENN: A Graph Neural Network for Binding Energy Prediction of Globular and Intrinsically Disordered Proteins

Intrinsically disordered proteins (IDPs) drive a large fraction of cellular signaling, transcription and assembly through interfaces that lack a singl...

Cyst-type epithelial heterogeneity shapes therapeutic responsiveness in ADPKD

Autosomal dominant polycystic kidney disease (ADPKD) exhibits substantial interpatient variability in disease course and therapeutic response, but the...

Serum proteomic atlas reveals distinct molecular signatures of lupus nephritis activity, chronicity, and treatment response

Lupus nephritis (LN), a severe manifestation of systemic lupus erythematosus (SLE), features heterogeneous renal pathology and reliance on invasive bi...

Kinome profiling allows examination and prediction of kinase inhibitor cardiotoxicity

Background: Despite improved cancer outcomes with kinase inhibitors (KIs), their cardiotoxicity remains a significant clinical challenge. Current appr...

Overcoming data scarcity through multi-center federated learning for organs-at-risk segmentation in pediatric upper abdominal radiotherapy

Deep learning-based organs/structures-at-risk(OARs) auto-contouring models can improve radiotherapy workflows, but models trained on adult data often ...

Correcting heterogeneous diagnostic bias when developing clinical prediction models using causal hidden Markov models

In routine care, individuals identified a priori as high-risk are usually tested for conditions more frequently. Protected attributes, such as sex or ...

Multimorbidity increases susceptibility to myocardial injury following cardiac surgery via dysregulated macrophage activation and the development of a cardiomyopathy phenotype

Background: People with Multiple Long-Term Conditions (MLTC) experience higher rates of organ failure and death following cardiac surgery. The aim of ...