Papers

Field

Open problems in Clinical reasoning

Lack of domain-specific benchmarks for clinical reasoning2 papers raise it · 1 addresses it
General benchmarks fail to capture critical domain requirements like safety, personalization, and actionable quality, risking harm in real-world use.
- MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coachingraises · addresses
- Clinician use of language models diverges from how the models are evaluatedraises
Handling incidental information in clinical documentation1 paper raises it · 0 address it
LLMs may misattribute or use irrelevant small-talk or background noise in clinical notes, leading to errors or contamination.
- Large language models are vulnerable to incidental information in clinical documentation and reasoningraises
Temporal modeling of multimodal clinical trajectories1 paper raises it · 1 addresses it
Existing multimodal approaches often overlook irregular, time-dependent clinical events, limiting risk prediction accuracy.
- TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk Predictionraises · addresses
Privacy-preserving learning from deployment experience2 papers raise it · 2 address it
Frozen models cannot adapt to new clinical evidence or guidelines without retraining, which is often impractical or private.
- Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIraises · addresses
- Agentic discovery of blood biomarker from distilled private health recordsraises · addresses
Tool-augmented reasoning with evidence grounding1 paper raises it · 2 address it
Medical agents lack mechanisms to decide when to use auxiliary evidence and how to prevent invalid data from affecting reasoning.
- X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoningraises · addresses
- MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and Workflowsaddresses

Named by an AI from these papers' abstracts.

Activity · 12 weeks

Recent papers

All papers in Research

arXiv eess.IVOct 28
CalibCause: A Quality-Gated, Interpretable and Calibrated Deep Learning Framework for Diabetic Retinopathy Grading
Sohaib Sulman, Muhammad Atif Saeed, Akhtar Jamil, Alaa Ali Hameed, Roland Aydin
Most deep learning systems for diabetic retinopathy (DR) grading are evaluated on a single data source, with limited evidence of cross-site generalisation, uncertainty calibration, and interpretability. We propose CalibCause, a quality-gated mixture-of-experts framework that combines per-expert visual explanations, label-free image-quality conditioning, knowledge distillation, and calibrated confidence with deferral. We evaluated the framework using 51,310 fundus images from EyePACS, DDR, and APTOS 2019, with IDRiD and DeepDRiD for external testing. Evaluation included pooled testing, leave-one-environment-out experiments, paired bootstrap confidence intervals, and local grade-threshold adaptation. On the pooled test split, the label-free distilled student achieved quadratic weighted kappa (QWK) of 0.863 and accuracy of 0.865 with 27.8 million parameters, 52% fewer than its teacher. Across held-out environments, the label-free model achieved mean QWK of 0.741 compared with 0.743 for a plain ConvNeXt-Tiny baseline, while adversarial invariance did not improve cross-site grading accuracy. Refitting grade thresholds using 200 labelled images increased held-out EyePACS QWK from 0.533…
PDF arXiv
arXiv cs.LGOct 28
Latent Decision Flow Rewards for Clinical Guideline Reasoning
Gaurav Bhatt, Marinka Zitnik
Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models. Two properties of clinical reasoning make this supervision difficult to use. A decision flow consistent with a guideline does not by itself determine the correct answer for a given patient, which we call the path--answer gap, and several valid decision flows can support the same clinical decision, which we call path multiplicity. Current training approaches address parts of this problem. Answer rewards supervise the final decision, and process rewards computed against a reference flow supervise one valid decision flow per case. Supervised fine-tuning on annotated flows teaches guideline-consistent reasoning but constrains the model to one trajectory per case and can reduce answer accuracy. We introduce GUIDER, a method that jointly optimizes a decision flow controller and a reasoning policy. The controller learns to generate plausible decision flows from guideline-derived supervision, and the policy learns to generate a decision flow and a final answer for each patient case. GUIDER computes the…
PDF arXiv
arXiv cs.LGOct 28
REVBRAIN: Real-time Probabilistic EEG Forecasting Using Residual Vector Quantization
Hanna Pankka, Jaakko Lehtinen, Timo Roine
Real-time forecasting of resting-state EEG signals is required by applications like brain-state-dependent stimulation, where computer generated actions are coupled with ongoing neural oscillations. Recently, the deep learning model WaveNet was proposed for the forecasting task. It shows superior accuracy compared to the prevailing method, the linear autoregressive (AR) model, and provides a built-in uncertainty measure due to its probabilistic modeling framework. However, inference using WaveNet is too slow for real-time use due to its sample-by-sample autoregressive operation: a single forecast requires evaluating the model tens or hundreds of times depending on the length of the prediction window. In this paper, we present REVBRAIN, a probabilistic deep learning method that produces forecasts in real time by generating the forecast over the whole prediction horizon at once. This is achieved by tokenizing the output space using residual vector quantization (RVQ) and generating forecasts over the items in the tokenized space. We tested REVBRAIN for forecasting 200 ms of EEG time series in the alpha-frequency band (8-13 Hz) and compared our results against WaveNet model. We found…
PDF arXiv
arXiv cs.CVOct 28
The Power Watershed as a Differentiable Segmentation Layer
Galia Akl, Laurent Najman, Hugues Talbot
Can a Watershed transform, the classical tool of morphological segmentation, be placed at the end of a deep network and trained through? The Power Watershed (PW) is the limit of the seeded Random Walker (RW) as p grows to infinity with edge weights raised to the power p. At every finite p the RW solves a sparse positive-definite linear system and is exactly differentiable with respect to the edge weights and the unaries through one adjoint solve; its multi-label form costs one right-hand side per label, and its limit is the PW. We study this family as the last layer of a segmentation network, the watershed layer (WS layer). A conditioning study measures how the solve, the gradient and the distance to the limit evolve with p, and the implicit gradient is checked against unrolling. On synthetic data with correct edge costs the WS layer transforms a soft prediction into an exact boundary. On nuclei segmentation (PanNuke), a binary WS layer is level with a thresholded U-Net. With the instances as labels, the WS layer turns the U-Net into an instance segmenter whose number of labels is set per image by the markers rather than by the output layout, and the network is trained through…
PDF arXiv
arXiv cs.CLOct 28
Benchmarking decision models against generative large language models on medical multiple-choice questions
Oscar Freyer, Daniel Glauert, Moritz Hofmann, Max Ostermann, Stephen Gilbert +1
Medical workflows often require selecting among predefined options. We compared 13 decision models with 15 generative large language model configurations, including different reasoning settings, using 1,273 four-option MedQA questions under text-only conditions. Accuracy ranged from 67.71% to 89.08% for decision models and from 78.32% to 96.86% for generative configurations. Among the tested configurations, Mercury Decide had the lowest mean final-attempt cost (USD 0.0069 per 1,000 questions), while Clef Omni had the shortest median request duration (0.291 seconds). Decision-model probabilities distinguished correct from incorrect answers, but error rates among answers assigned probabilities of at least 0.90 ranged from 1.71% to 12.77%. Answer agreement across three runs ranged from 92.30% to 100%, while probability repeatability varied. Decision models offered resource advantages alongside lower peak accuracy; selecting models for medical workflows requires considering probability quality and repeatability together with accuracy and the resources needed to detect and correct errors.
PDF arXiv
arXiv cs.AIOct 28
DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences
Hugo Math, Maximilian Forstenhäusler, Christos Anagnostopoulos
Temporal foundation models such as Chronos and TimesFM generalize across domains through a shared numerical observation space. In contrast, discrete event sequences (DESs), including operational event logs or patient clinical-event trajectories, have domain-specific event vocabularies whose labels lack a consistent correspondence across domains. Beyond this lack of consistency, the number of distinct events in real-world settings is high enough to challenge both classical temporal point process modeling and current in-context foundation inference models such as FIM-PP. Critically, current foundation models for DESs are limited to a small, fixed number of event types, restricting their applicability to realistic, high-dimensional event streams. To address this, we propose two complementary modules: (i) DES-JEPA, a joint-embedding predictive architecture that learns a shared discrete vocabulary from synthetic stochastic processes with unaligned event vocabularies; and (ii) DES-PFN, a discrete event sequence prior-fitted network that reuses the learned vocabulary for in-context next-event prediction. Without task-specific fine-tuning, this framework achieves competitive zero-shot…
PDF arXiv

Papers

Topics in this field

clinical reasoning · clinical decision · language models278 papers43 this week
brain tumor segmentation · medical image segmentation · brain mri141 papers21 this week
slide images wsis · pathology foundation models · images wsis116 papers15 this week
radiology report generation · radiomics · radiology reports160 papers14 this week
deformable image registration · medical image segmentation · 3d medical99 papers13 this week
electroencephalography eeg · eeg foundation models · eeg based147 papers11 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv eess.IVOct 28
CalibCause: A Quality-Gated, Interpretable and Calibrated Deep Learning Framework for Diabetic Retinopathy Grading
Sohaib Sulman, Muhammad Atif Saeed, Akhtar Jamil, Alaa Ali Hameed, Roland Aydin
Most deep learning systems for diabetic retinopathy (DR) grading are evaluated on a single data source, with limited evidence of cross-site generalisation, uncertainty calibration, and interpretability. We propose CalibCause, a quality-gated mixture-of-experts framework that combines per-expert visual explanations, label-free image-quality conditioning, knowledge distillation, and calibrated confidence with deferral. We evaluated the framework using 51,310 fundus images from EyePACS, DDR, and APTOS 2019, with IDRiD and DeepDRiD for external testing. Evaluation included pooled testing, leave-one-environment-out experiments, paired bootstrap confidence intervals, and local grade-threshold adaptation. On the pooled test split, the label-free distilled student achieved quadratic weighted kappa (QWK) of 0.863 and accuracy of 0.865 with 27.8 million parameters, 52% fewer than its teacher. Across held-out environments, the label-free model achieved mean QWK of 0.741 compared with 0.743 for a plain ConvNeXt-Tiny baseline, while adversarial invariance did not improve cross-site grading accuracy. Refitting grade thresholds using 200 labelled images increased held-out EyePACS QWK from 0.533…
PDF arXiv
arXiv cs.LGOct 28
Latent Decision Flow Rewards for Clinical Guideline Reasoning
Gaurav Bhatt, Marinka Zitnik
Clinical practice guidelines encode evidence-based recommendations as conditional decision flows, which makes them a natural source of process supervision for training reasoning models. Two properties of clinical reasoning make this supervision difficult to use. A decision flow consistent with a guideline does not by itself determine the correct answer for a given patient, which we call the path--answer gap, and several valid decision flows can support the same clinical decision, which we call path multiplicity. Current training approaches address parts of this problem. Answer rewards supervise the final decision, and process rewards computed against a reference flow supervise one valid decision flow per case. Supervised fine-tuning on annotated flows teaches guideline-consistent reasoning but constrains the model to one trajectory per case and can reduce answer accuracy. We introduce GUIDER, a method that jointly optimizes a decision flow controller and a reasoning policy. The controller learns to generate plausible decision flows from guideline-derived supervision, and the policy learns to generate a decision flow and a final answer for each patient case. GUIDER computes the…
PDF arXiv
arXiv cs.LGOct 28
REVBRAIN: Real-time Probabilistic EEG Forecasting Using Residual Vector Quantization
Hanna Pankka, Jaakko Lehtinen, Timo Roine
Real-time forecasting of resting-state EEG signals is required by applications like brain-state-dependent stimulation, where computer generated actions are coupled with ongoing neural oscillations. Recently, the deep learning model WaveNet was proposed for the forecasting task. It shows superior accuracy compared to the prevailing method, the linear autoregressive (AR) model, and provides a built-in uncertainty measure due to its probabilistic modeling framework. However, inference using WaveNet is too slow for real-time use due to its sample-by-sample autoregressive operation: a single forecast requires evaluating the model tens or hundreds of times depending on the length of the prediction window. In this paper, we present REVBRAIN, a probabilistic deep learning method that produces forecasts in real time by generating the forecast over the whole prediction horizon at once. This is achieved by tokenizing the output space using residual vector quantization (RVQ) and generating forecasts over the items in the tokenized space. We tested REVBRAIN for forecasting 200 ms of EEG time series in the alpha-frequency band (8-13 Hz) and compared our results against WaveNet model. We found…
PDF arXiv
arXiv cs.CVOct 28
The Power Watershed as a Differentiable Segmentation Layer
Galia Akl, Laurent Najman, Hugues Talbot
Can a Watershed transform, the classical tool of morphological segmentation, be placed at the end of a deep network and trained through? The Power Watershed (PW) is the limit of the seeded Random Walker (RW) as p grows to infinity with edge weights raised to the power p. At every finite p the RW solves a sparse positive-definite linear system and is exactly differentiable with respect to the edge weights and the unaries through one adjoint solve; its multi-label form costs one right-hand side per label, and its limit is the PW. We study this family as the last layer of a segmentation network, the watershed layer (WS layer). A conditioning study measures how the solve, the gradient and the distance to the limit evolve with p, and the implicit gradient is checked against unrolling. On synthetic data with correct edge costs the WS layer transforms a soft prediction into an exact boundary. On nuclei segmentation (PanNuke), a binary WS layer is level with a thresholded U-Net. With the instances as labels, the WS layer turns the U-Net into an instance segmenter whose number of labels is set per image by the markers rather than by the output layout, and the network is trained through…
PDF arXiv
arXiv cs.CLOct 28
Benchmarking decision models against generative large language models on medical multiple-choice questions
Oscar Freyer, Daniel Glauert, Moritz Hofmann, Max Ostermann, Stephen Gilbert +1
Medical workflows often require selecting among predefined options. We compared 13 decision models with 15 generative large language model configurations, including different reasoning settings, using 1,273 four-option MedQA questions under text-only conditions. Accuracy ranged from 67.71% to 89.08% for decision models and from 78.32% to 96.86% for generative configurations. Among the tested configurations, Mercury Decide had the lowest mean final-attempt cost (USD 0.0069 per 1,000 questions), while Clef Omni had the shortest median request duration (0.291 seconds). Decision-model probabilities distinguished correct from incorrect answers, but error rates among answers assigned probabilities of at least 0.90 ranged from 1.71% to 12.77%. Answer agreement across three runs ranged from 92.30% to 100%, while probability repeatability varied. Decision models offered resource advantages alongside lower peak accuracy; selecting models for medical workflows requires considering probability quality and repeatability together with accuracy and the resources needed to detect and correct errors.
PDF arXiv
arXiv cs.AIOct 28
DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences
Hugo Math, Maximilian Forstenhäusler, Christos Anagnostopoulos
Temporal foundation models such as Chronos and TimesFM generalize across domains through a shared numerical observation space. In contrast, discrete event sequences (DESs), including operational event logs or patient clinical-event trajectories, have domain-specific event vocabularies whose labels lack a consistent correspondence across domains. Beyond this lack of consistency, the number of distinct events in real-world settings is high enough to challenge both classical temporal point process modeling and current in-context foundation inference models such as FIM-PP. Critically, current foundation models for DESs are limited to a small, fixed number of event types, restricting their applicability to realistic, high-dimensional event streams. To address this, we propose two complementary modules: (i) DES-JEPA, a joint-embedding predictive architecture that learns a shared discrete vocabulary from synthetic stochastic processes with unaligned event vocabularies; and (ii) DES-PFN, a discrete event sequence prior-fitted network that reuses the learned vocabulary for in-context next-event prediction. Without task-specific fine-tuning, this framework achieves competitive zero-shot…
PDF arXiv

Fields · AI · updated 43m ago

Clinical reasoning

Found by the topic model: clinical reasoning, radiology report generation, electroencephalography eeg.

157papers this week−25.6% vs last week

All papers · 1.4k With code · 8

Newest Most relevant

830 papers this month