Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks

• URL: http://arxiv.org/abs/2509.22258v1
• Date: Fri, 26 Sep 2025 12:20:01 GMT
• Title: Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks
• Authors: Miao Jing, Mengting Jia, Junling Lin, Zhongxia Shen, Lijun Wang, Yuanyuan Peng, Huan Gao, Mingkun Xu, Shangyang Li,
• Abstract summary: Recent advances in vision-language models (VLMs) have achieved remarkable performance on standard medical benchmarks, yet their true clinical reasoning ability remains unclear.<n>We introduce Neural-MedBench, a compact yet reasoning-intensive benchmark designed to probe the limits of multimodal clinical reasoning in neurology.
• Score: 21.203358914772465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in vision-language models (VLMs) have achieved remarkable performance on standard medical benchmarks, yet their true clinical reasoning ability remains unclear. Existing datasets predominantly emphasize classification accuracy, creating an evaluation illusion in which models appear proficient while still failing at high-stakes diagnostic reasoning. We introduce Neural-MedBench, a compact yet reasoning-intensive benchmark specifically designed to probe the limits of multimodal clinical reasoning in neurology. Neural-MedBench integrates multi-sequence MRI scans, structured electronic health records, and clinical notes, and encompasses three core task families: differential diagnosis, lesion recognition, and rationale generation. To ensure reliable evaluation, we develop a hybrid scoring pipeline that combines LLM-based graders, clinician validation, and semantic similarity metrics. Through systematic evaluation of state-of-the-art VLMs, including GPT-4o, Claude-4, and MedGemma, we observe a sharp performance drop compared to conventional datasets. Error analysis shows that reasoning failures, rather than perceptual errors, dominate model shortcomings. Our findings highlight the necessity of a Two-Axis Evaluation Framework: breadth-oriented large datasets for statistical generalization, and depth-oriented, compact benchmarks such as Neural-MedBench for reasoning fidelity. We release Neural-MedBench at https://neuromedbench.github.io/ as an open and extensible diagnostic testbed, which guides the expansion of future benchmarks and enables rigorous yet cost-effective assessment of clinically trustworthy AI.

Related papers

• AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning [73.50200033931148]
  We introduce AgentsEval, a multi-agent stream reasoning framework that emulates the collaborative diagnostic workflow of radiologists.<n>By dividing the evaluation process into interpretable steps including criteria definition, evidence extraction, alignment, and consistency scoring, AgentsEval provides explicit reasoning traces and structured clinical feedback.<n> Experimental results demonstrate that AgentsEval delivers clinically aligned, semantically faithful, and interpretable evaluations that remain robust under paraphrastic, semantic, and stylistic perturbations.
  arXiv  Detail & Related papers  (2026-01-23T11:59:13Z)
• Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation [97.36081721024728]
  We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations.<n>Our benchmark unifies three types of medical data for open-ended diagnostic generation.<n>We present MedConf, an evidence-grounded linguistic self-assessment framework.
  arXiv  Detail & Related papers  (2026-01-22T04:51:39Z)
• CutisAI: Deep Learning Framework for Automated Dermatology and Cancer Screening [0.0]
  We present the Conformal Bayesian Dermatological (CBDC) framework that combines Statistical Learning Theory, Topological Data Analysis, and Bayesian Conformal Inference.<n>CBDC attains classification accuracy and generates calibrated predictions that are interpretable from a clinical perspective.<n>This research constitutes a theoretical and practical leap for deep dermatological diagnostics, thereby opening the machine learning theory clinical applicability interface.
  arXiv  Detail & Related papers  (2026-01-05T21:29:08Z)
• NEURO-GUARD: Neuro-Symbolic Generalization and Unbiased Adaptive Routing for Diagnostics -- Explainable Medical AI [0.6345042809319409]
  We present NEURO-GUARD, a knowledge-guided vision framework that integrates Vision Transformers (ViTs) with language-driven reasoning to improve performance.<n> NEURO-GUARD employs a retrieval-augmented generation (RAG) mechanism for self-verification, in which a large language model (LLM) iteratively generates, evaluates, and refines feature-extraction code for medical images.<n>Experiments on diabetic retinopathy classification across four benchmark datasets demonstrate that NEURO-GUARD improves accuracy by 6.2% over a ViT-only baseline and achieves a 5% gain in domain generalization.
  arXiv  Detail & Related papers  (2025-12-20T02:32:15Z)
• Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models [15.530083855947987]
  We propose the first Multimodal Medical Reasoning-with-Retrieval framework, Med-RwR.<n>Med-RwR actively retrieves external knowledge by querying observed symptoms or domain-specific medical concepts during reasoning.<n> Evaluation on various public medical benchmarks demonstrates Med-RwR's significant improvements over baseline models.
  arXiv  Detail & Related papers  (2025-10-21T05:18:18Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis [56.373297358647655]
  Retrieval-Augmented Diagnosis (RAD) is a novel framework that injects external knowledge into multimodal models directly on downstream tasks.<n>RAD operates through three key mechanisms: retrieval and refinement of disease-centered knowledge from multiple medical sources, a guideline-enhanced contrastive loss transformer, and a dual decoder.
  arXiv  Detail & Related papers  (2025-09-24T10:36:14Z)
• Challenges in Deep Learning-Based Small Organ Segmentation: A Benchmarking Perspective for Medical Research with Limited Datasets [1.2648105980808475]
  This study investigates a systematic evaluation of state-of-the-art deep learning segmentation models.<n>Our findings reveal that model performance is highly sensitive to data splits, with minor differences driven more by statistical noise than by true algorithmic superiority.
  arXiv  Detail & Related papers  (2025-09-07T01:54:20Z)
• Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models [57.73472878679636]
  We introduce Med-RewardBench, the first benchmark specifically designed to evaluate medical reward models and judges.<n>Med-RewardBench features a multimodal dataset spanning 13 organ systems and 8 clinical departments, with 1,026 expert-annotated cases.<n>A rigorous three-step process ensures high-quality evaluation data across six clinically critical dimensions.
  arXiv  Detail & Related papers  (2025-08-29T08:58:39Z)
• Benchmarking and Explaining Deep Learning Cortical Lesion MRI Segmentation in Multiple Sclerosis [28.192924379673862]
  Cortical lesions (CLs) have emerged as valuable biomarkers in multiple sclerosis (MS)<n>We propose a comprehensive benchmark of CL detection and segmentation in MRI.<n>We rely on the self-configuring nnU-Net framework, designed for medical imaging segmentation, and propose adaptations tailored to the improved CL detection.
  arXiv  Detail & Related papers  (2025-07-16T09:56:11Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• NeuroMoE: A Transformer-Based Mixture-of-Experts Framework for Multi-Modal Neurological Disorder Classification [3.5313393560458826]
  Deep Learning has recently emerged as a powerful tool for extracting meaningful patterns from medical data to aid in diagnosis.<n>We propose a novel transformer-based Mixture-of-Experts (MoE) framework for classifying neurological disorders.<n>Our framework achieves a validation accuracy of 82.47%, outperforming baseline methods by over 10%.
  arXiv  Detail & Related papers  (2025-06-17T20:40:06Z)
• REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis [6.446611581074913]
  We introduce REMEMBER -- Retrieval-based Explainable Multimodalively-guided Modeling for Brain Evaluation and Reasoning.<n>REMEMBER is a new machine learning framework that facilitates zero- and few-shot Alzheimer's diagnosis using brain MRI scans.<n> Experimental results demonstrate that REMEMBER achieves robust zero- and few-shot performance.
  arXiv  Detail & Related papers  (2025-04-12T22:06:15Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.<n>Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy [45.2233252981348]
  Large Language Models (LLMs) have been shown to encode clinical knowledge.<n>We present SemioLLM, an evaluation framework that benchmarks 6 state-of-the-art models.<n>We show that most LLMs are able to accurately and confidently generate probabilistic predictions of seizure onset zones in the brain.
  arXiv  Detail & Related papers  (2024-07-03T11:02:12Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.