12 papers
The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging
Fabian Drexel, Bernhard Kainz, Jakob N. Kather +4
Joint-embedding predictive architectures (JEPAs) learn by predicting teacher representations of masked regions from visible context. Point prediction summarizes the conditional tar…
NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting
Tobias Susetzky, Raphael Rehms, Dmitrii Seletkov +5
The digitization of healthcare has generated vast, longitudinal, and multimodal patient records over a lifetime, yet fully exploiting these data to represent and predict patient st…
RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding
Fabian Drexel, Marlene Fritzsche, Era Stambollxhiu +15
Vision-language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a single shared embedding space, s…
ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
Alexander Selivanov, Friederike Jungmann, Jan Kehrer +3
Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardio…
A unified perspective on wavelength selection for molecular composition inference from diffuse spectroscopy
Kevin Scibilia, Marcel Rosier, Luca Giannoni +6
Optical monitoring of living tissue targeting quantification of molecular composition is an active area of research. In the case of broadband spectroscopy, one can attempt to extra…
Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance
Tianming Du, Peijie Yu, Sihan Shang +12
The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR sys…
Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure
Moritz Schlager, Friederike Jungmann, Samuel Schmidgall +12
Simulating realistic patient interactions is a key requirement to testing clinical applications of LLMs at scale without time-consuming and expensive user studies. However, existin…
DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs
Jiazhen Pan, Weixiang Shen, Jun Li +7
Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revise a differential diagnosis,…
GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
Johannes Moll, Jean-Philippe Corbeil, Jiazhen Pan +4
LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-imp…
Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus
Johannes Moll, Jannik Lübberstedt, Christoph Nuernbergk +21
Multiple myeloma is managed through sequential lines of therapy over years to decades, with each decision depending on cumulative disease history distributed across dozens to hundr…
Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve
Weixiang Shen, Bailiang Jian, Jun Li +6
Tool-augmented large language model (LLM) agents can orchestrate specialist classifiers, segmentation models, and visual question-answering modules to interpret chest X-rays. Howev…
Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data
Nikola Cenikj, Özgün Turgut, Alexander Müller +6
Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views. Although numerous deep-learning…