10 papers
Attention Without Grounding: Causal Evaluation of Visual Explanations in Medical VLMs
Binesh Sadanandan, Vahid Behzadan
Attention and saliency heatmaps are widely used to explain medical Vision-Language Model (VLM) outputs on chest X-rays, yet whether they truly highlight the image evidence driving…
PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
Binesh Sadanandan, Vahid Behzadan
Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a…
Predictive Entropy as a Joint Screen for Error and Paraphrase Instability in Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Medical Vision-Language Models (VLMs) answering binary presence questions on chest radiographs can fail in two linked ways: they are confidently wrong, and they change answers when…
When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models
Binesh Sadanandan, Vahid Behzadan
Large Language Models (LLMs) are increasingly deployed in medical settings, yet their sensitivity to prompt formatting remains poorly characterized. We evaluate MedGemma (4B and 27…
Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Consistency under paraphrase, the property that semantically equivalent prompts yield identical predictions, is increasingly used as a proxy for reliability when deploying medical…
Multimodal Deep Learning for Early Prediction of Patient Deterioration in the ICU: Integrating Time-Series EHR Data with Clinical Notes
Binesh Sadanandan
Early identification of patients at risk for clinical deterioration in the intensive care unit (ICU) remains a critical challenge. Delayed recognition of impending adverse events,…