Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling

• URL: http://arxiv.org/abs/2604.01898v1
• Date: Thu, 02 Apr 2026 11:01:31 GMT
• Title: Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling
• Abstract summary: unpredictability of AI errors poses a significant challenge, particularly in healthcare contexts.<n>We propose a novel approach that leverages disagreement in expert responses to generate targets for training machine learning models.<n>Our experiments demonstrate that incorporating expert knowledge can enhance uncertainty estimation quality by $9%$ to $50%$ depending on the task.
• Score: 35.159273667448176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Artificial intelligence (AI) systems accelerate medical workflows and improve diagnostic accuracy in healthcare, serving as second-opinion systems. However, the unpredictability of AI errors poses a significant challenge, particularly in healthcare contexts, where mistakes can have severe consequences. A widely adopted safeguard is to pair predictions with uncertainty estimation, enabling human experts to focus on high-risk cases while streamlining routine verification. Current uncertainty estimation methods, however, remain limited, particularly in quantifying aleatoric uncertainty, which arises from data ambiguity and noise. To address this, we propose a novel approach that leverages disagreement in expert responses to generate targets for training machine learning models. These targets are used in conjunction with standard data labels to estimate two components of uncertainty separately, as given by the law of total variance, via a two-ensemble approach, as well as its lightweight variant. We validate our method on binary image classification, binary and multi-class image segmentation, and multiple-choice question answering. Our experiments demonstrate that incorporating expert knowledge can enhance uncertainty estimation quality by $9\%$ to $50\%$ depending on the task, making this source of information invaluable for the construction of risk-aware AI systems in healthcare applications.

Related papers

• Agentic Uncertainty Quantification [76.94013626702183]
  We propose a unified Dual-Process Agentic UQ (AUQ) framework that transforms verbalized uncertainty into active, bi-directional control signals.<n>Our architecture comprises two complementary mechanisms: System 1 (Uncertainty-Aware Memory, UAM), which implicitly propagates verbalized confidence and semantic explanations to prevent blind decision-making; and System 2 (Uncertainty-Aware Reflection, UAR), which utilizes these explanations as rational cues to trigger targeted inference-time resolution only when necessary.
  arXiv  Detail & Related papers  (2026-01-22T07:16:26Z)
• Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification [11.21639536740362]
  We evaluate 13 uncertainty quantification methods for convolutional (ResNet) and transformer-based (Vision Transformer) architectures.<n>We extend Evidential Deep Learning, HetClass NNs, and Deep Deterministic Uncertainty to the multi-label setting.
  arXiv  Detail & Related papers  (2025-08-06T13:58:17Z)
• 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)
• Explaining Uncertainty in Multiple Sclerosis Lesion Segmentation Beyond Prediction Errors [30.086986374579414]
  This study introduces a novel framework to explain the potential sources of predictive uncertainty.<n>The proposed analysis shifts the focus from the uncertainty-error relationship towards relevant medical and engineering factors.<n>Our findings reveal that instance-wise uncertainty is strongly related to lesion size, shape, and cortical involvement.
  arXiv  Detail & Related papers  (2025-04-07T08:09:27Z)
• Uncertainty-aware abstention in medical diagnosis based on medical texts [87.88110503208016]
  This study addresses the critical issue of reliability for AI-assisted medical diagnosis.<n>We focus on the selection prediction approach that allows the diagnosis system to abstain from providing the decision if it is not confident in the diagnosis.<n>We introduce HUQ-2, a new state-of-the-art method for enhancing reliability in selective prediction tasks.
  arXiv  Detail & Related papers  (2025-02-25T10:15:21Z)
• Know Where You're Uncertain When Planning with Multimodal Foundation Models: A Formal Framework [54.40508478482667]
  We present a comprehensive framework to disentangle, quantify, and mitigate uncertainty in perception and plan generation.<n>We propose methods tailored to the unique properties of perception and decision-making.<n>We show that our uncertainty disentanglement framework reduces variability by up to 40% and enhances task success rates by 5% compared to baselines.
  arXiv  Detail & Related papers  (2024-11-03T17:32:00Z)
• Expert-aware uncertainty estimation for quality control of neural-based blood typing [0.0]
  In medical diagnostics, accurate uncertainty estimation for neural-based models is essential for complementing second-opinion systems. A major difficulty here is the lack of labels on the hardness of examples, making the uncertainty estimation problem almost unsupervised. Our novel approach integrates expert assessments of case complexity into the neural network's learning process, utilizing both definitive target labels and supplementary complexity ratings. Experiments demonstrate enhancement of our approach in uncertainty prediction, achieving a 2.5-fold improvement with expert labels and a 35% increase in performance with estimates of neural-based expert consensus.
  arXiv  Detail & Related papers  (2024-07-15T19:07:02Z)
• Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness [106.52630978891054]
  We present a taxonomy of uncertainty specific to vision-language AI systems. We also introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error.
  arXiv  Detail & Related papers  (2024-07-02T04:23:54Z)
• Evaluating AI systems under uncertain ground truth: a case study in dermatology [43.8328264420381]
  We show that ignoring uncertainty leads to overly optimistic estimates of model performance.<n>In skin condition classification, we find that a large portion of the dataset exhibits significant ground truth uncertainty.
  arXiv  Detail & Related papers  (2023-07-05T10:33:45Z)
• Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection [78.24964622317634]
  In this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty. To evaluate the quality of uncertainty, we consider the task of classifying anomalies with the additional option of rejecting predictions of high uncertainty. Our experiments demonstrate the effectiveness of the BAE and total anomaly uncertainty on a set of benchmark datasets and two real datasets for manufacturing.
  arXiv  Detail & Related papers  (2022-02-25T12:20:04Z)
• Enabling risk-aware Reinforcement Learning for medical interventions through uncertainty decomposition [9.208828373290487]
  Reinforcement Learning (RL) is emerging as tool for tackling complex control and decision-making problems. It is often challenging to bridge the gap between an apparently optimal policy learnt by an agent and its real-world deployment. Here we propose how a distributional approach (UA-DQN) can be recast to render uncertainties by decomposing the net effects of each uncertainty.
  arXiv  Detail & Related papers  (2021-09-16T09:36:53Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)

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.