Get Started
Home
Topics
Search
Library
Research questionHow can early-stage chronic kidney disease screening remain accurate and stable with limited labeled data?Early CKD screening depends on clinical data, but obtaining enough labeled records for reliable modeling can be difficult. Screening performance may also become less stable as the number and complexity of input features increase.
AI
Health
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease ScreeningThe study evaluates large language model inference on tabular CKD features in zero-shot and few-shot in-context settings using structured prompts, without task-specific training. It compares these results with traditional machine learning, deep learning, tabular foundation models, and existing screening tools across prompt styles, feature configurations, and data settings. Reported LLM performance is model-dependent and less stable with more complex inputs, while trained models improve more consistently as training data increase.research paper · Sep 4, 2026
Related questions
How can clinical decision systems remain accurate and auditable under scarce, imbalanced data and changing features?How can demographic information improve clinical tabular prediction across diseases and populations without complicating deployment?How should tabular foundation models be adapted for censored time-to-event prediction under competing risks?How can unsupervised tabular anomaly detectors provide faithful feature-level explanations without costly post-hoc queries?