6 papers · 1 filter
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
Abhishek Moturu, Babak Taati, Anna Goldenberg
Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases. This can severely undermine the reliabilit…
LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection
Abhishek Moturu, Anna Goldenberg, Babak Taati
Synthetic data is useful only when the added samples fill missing parts of the training distribution that matter for the downstream task. We introduce LiBaGS, a lightweight, genera…
Can we generate portable representations for clinical time series data using LLMs?
Zongliang Ji, Yifei Sun, Andre Amaral +2
Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we study a simple question -- can lar…
DynaSubVAE: Adaptive Subgrouping for Scalable and Robust OOD Detection
Tina Behrouzi, Sana Tonekaboni, Rahul G. Krishnan +1
Real-world observational data often contain existing or emerging heterogeneous subpopulations that deviate from global patterns. The majority of models tend to overlook these under…
ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders
Zongliang Ji, Andre Carlos Kajdacsy-Balla Amaral, Anna Goldenberg +1
Ordering a minimal subset of lab tests for patients in the intensive care unit (ICU) can be challenging. Care teams must balance between ensuring the availability of the right info…
Measurement Scheduling for ICU Patients with Offline Reinforcement Learning
Zongliang Ji, Anna Goldenberg, Rahul G. Krishnan
Scheduling laboratory tests for ICU patients presents a significant challenge. Studies show that 20-40% of lab tests ordered in the ICU are redundant and could be eliminated withou…