Urology

Human-level information extraction from clinical reports with fine-tuned language models

Extracting structured data from clinical notes remains a key bottleneck in clinical research. We hypothesized that with minimal computational and annotation resources, open-source large language models (LLMs) could create high-quality research databases. We developed Strata, a low-code library for leveraging LLMs for data extraction from clinical reports. Trained researchers labeled four datasets ...

Development and Evaluation of an AI-Assisted, Privacy-Preserving Surgical Risk Calculator

Large language models (LLMs) have shown capabilities in generating functional code, yet their utility in the development of clinical prediction tools has not been significantly explored. We evaluated GPT-4o’s capability to create a postoperative complication risk calculator similar to the existing National Surgical Quality Improvement Program (NSQIP) risk calculator. This included data preprocessi...

VADEr: Vision Transformer-Inspired Framework for Polygenic Risk Reveals Underlying Genetic Heterogeneity in Prostate Cancer

Polygenic risk scores (PRSs) serve as quantitative metrics of genetic liability for various conditions. Traditionally calculated as an effect size wei...

Radiomics-Based Early Triage of Prostate Cancer: A Multicenter Study from the CHAIMELEON Project

Prostate cancer (PCa) is the most commonly diagnosed malignancy in men worldwide. Accurate triage of patients based on tumor aggressiveness and stagin...

LiteMIL: A Computationally Efficient Transformer-Based MIL for Cancer Subtyping on Whole Slide Images

Accurate cancer subtyping is crucial for effective treatment; however, it presents challenges due to overlapping morphology and variability among path...

Transcriptomics-Driven Machine Learning Models Accurately Predict Chemotherapy Response in Muscle-invasive Bladder Cancer

Muscle-invasive bladder cancer (MIBC) is associated with poor predictability of response to cisplatin-based neoadjuvant chemotherapy (NAC). Consequent...

USING ARTIFICIAL INTELLIGENCE TO PREDICT TREATMENT OUTCOMES IN PATIENTS WITH NEUROGENIC OVERACTIVE BLADDER AND MULTIPLE SCLEROSIS

Many women with multiple sclerosis (MS) experience neurogenic overactive bladder (NOAB) characterized by urinary frequency, urinary urgency and urgenc...

Phenotypic and prognostic insights through unbiased self-supervised learning on kidney histology

Deep learning methods for image segmentation and classification in histopathology generally utilize supervised learning, relying on manually created l...

Urinary collagen peptides predict mortality

Organ fibrosis caused by the presence of excessive extracellular matrix (ECM) is strongly related to mortality. Urinary peptide signatures were report...

Identification of cellular senescence-related gene IFNG as a potential biomarker in acute rejection after kidney transplantation via weighted gene co-expression network analysis and multiple machine learning

Kidney transplantation is the best option for the treatment of end-stage kidney disease (ESKD). Acute rejection (AR) episodes are a major determinant ...

Clinically reported covert cerebrovascular disease and risk of neurological disease: a whole-population cohort of 395,273 people using natural language processing

Understanding the relevance of covert cerebrovascular disease (CCD) for later health will allow clinicians to more effectively monitor and target inte...

Clinical-grade autonomous cytopathology via whole-slide edge tomography

Cytopathology plays a central role in the early detection of cancers such as cervical, lung, and bladder cancer due to its speed, simplicity, and mini...

Rad-Path Correlation of Deep Learning Models for Prostate Cancer Detection on MRI

While Deep Learning (DL) models trained on Magnetic Resonance Imaging (MRI) have shown promise for prostate cancer detection, their lack of direct bio...

Multiple instance learning using pathology foundation models effectively predicts kidney disease diagnosis and clinical classification

Histological analysis of kidney biopsies is crucial in diagnosing kidney diseases and predicting clinical outcomes. Recently developed pathology found...

Using Large Language Models to Determine Reasons for Missed Colon Cancer Screening Follow-Up

Identifying reasons for missed preventive care, such as follow-up colonoscopy after an abnormal stool-based colon cancer screening test, is critical f...

Artificial Intelligence Enabled Phenogrouping of Heart Failure with Preserved Ejection Fraction Depicts Early and End-Stage Trajectories

Heart failure with preserved ejection fraction is challenging to diagnose, precluding the initiation of prognostic medications. A deeper understanding...

Leveraging Machine Learning for Developing and Validating a Neonatal Acute Kidney Injury Prediction Model (NEPHRO): A Comprehensive Evidence-Based Neonatal AKI Risk Stratification Tool

Acute kidney injury (AKI) is a serious and common complication among critically ill neonates. Preventing or treating AKI early requires timely predict...

Urethra contours on MRI: multidisciplinary consensus educational atlas and reference standard for artificial intelligence benchmarking

The urethra is a recommended avoidance structure for prostate cancer treatment. However, even subspecialist physicians often struggle to accurately id...

Integrating Bioinformatics and Machine Learning to Identify Mitochondria-Related Biomarkers and Their Association with Immune Infiltration in BK polyomavirus-associated nephropathy

BK polyomavirus-associated nephropathy (BKPyVAN) is a serious complication of kidney transplantation. Numerous kidney diseases such as BKPyVAN have be...

Myocardial Native T1 Mapping in the German National Cohort (NAKO): Associations with Age, Sex, and Cardiometabolic Risk Factors

In cardiovascular magnetic resonance (CMR), myocardial native T1 mapping enables quantitative, non-invasive tissue characterization and is sensitive t...