Clinical Uncertainty Impacts Machine Learning Evaluations

• URL: http://arxiv.org/abs/2509.22242v1
• Date: Fri, 26 Sep 2025 11:56:58 GMT
• Title: Clinical Uncertainty Impacts Machine Learning Evaluations
• Authors: Simone Lionetti, Fabian Gröger, Philippe Gottfrois, Alvaro Gonzalez-Jimenez, Ludovic Amruthalingam, Alexander A. Navarini, Marc Pouly,
• Abstract summary: We argue that machine-learning evaluations should explicitly account for annotation uncertainty using probabilistic metrics that directly operate on distributions.<n>We urge the community to release raw annotations for datasets and to adopt uncertainty-aware evaluation so that performance estimates may better reflect clinical data.
• Score: 40.773483049446426
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical dataset labels are rarely certain as annotators disagree and confidence is not uniform across cases. Typical aggregation procedures, such as majority voting, obscure this variability. In simple experiments on medical imaging benchmarks, accounting for the confidence in binary labels significantly impacts model rankings. We therefore argue that machine-learning evaluations should explicitly account for annotation uncertainty using probabilistic metrics that directly operate on distributions. These metrics can be applied independently of the annotations' generating process, whether modeled by simple counting, subjective confidence ratings, or probabilistic response models. They are also computationally lightweight, as closed-form expressions have linear-time implementations once examples are sorted by model score. We thus urge the community to release raw annotations for datasets and to adopt uncertainty-aware evaluation so that performance estimates may better reflect clinical data.

Related papers

• Label-free estimation of clinically relevant performance metrics under distribution shifts [3.8961057201295244]
  We introduce generalisations of existing performance prediction methods that directly estimate the full confusion matrix.<n>We benchmark their performance on chest x-ray data in real-world distribution shifts.<n>Our simulated shift scenarios exposed important failure modes of current performance estimation techniques.
  arXiv  Detail & Related papers  (2025-07-30T15:37:58Z)
• Performance Estimation in Binary Classification Using Calibrated Confidence [0.5399800035598186]
  We present CBPE, a novel method that can estimate any binary classification metric defined using the confusion matrix.<n>CBPE is shown to produce estimates that come with strong theoretical guarantees and valid confidence intervals.
  arXiv  Detail & Related papers  (2025-05-08T14:34:44Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Enhancing Uncertainty Quantification in Drug Discovery with Censored Regression Labels [1.9354018523009415]
  We adapt ensemble-based, Bayesian, and Gaussian models with tools to learn from censored labels. Our results demonstrate that despite the partial information available in censored labels, they are essential to accurately and reliably model the real pharmaceutical setting.
  arXiv  Detail & Related papers  (2024-09-06T14:38:47Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Mitigating LLM Hallucinations via Conformal Abstention [70.83870602967625]
  We develop a principled procedure for determining when a large language model should abstain from responding in a general domain. We leverage conformal prediction techniques to develop an abstention procedure that benefits from rigorous theoretical guarantees on the hallucination rate (error rate) Experimentally, our resulting conformal abstention method reliably bounds the hallucination rate on various closed-book, open-domain generative question answering datasets.
  arXiv  Detail & Related papers  (2024-04-04T11:32:03Z)
• 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)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• USE-Evaluator: Performance Metrics for Medical Image Segmentation Models with Uncertain, Small or Empty Reference Annotations [5.672489398972326]
  There is a mismatch between the distributions of cases and difficulty level of segmentation tasks in public data sets compared to clinical practice. Common metrics fail to measure the impact of this mismatch, especially for clinical data sets. We study how uncertain, small, or empty reference annotations influence the value of metrics for medical image segmentation.
  arXiv  Detail & Related papers  (2022-09-26T20:40:02Z)
• Classifier uncertainty: evidence, potential impact, and probabilistic treatment [0.0]
  We present an approach to quantify the uncertainty of classification performance metrics based on a probability model of the confusion matrix. We show that uncertainties can be surprisingly large and limit performance evaluation.
  arXiv  Detail & Related papers  (2020-06-19T12:49:19Z)
• Performance metrics for intervention-triggering prediction models do not reflect an expected reduction in outcomes from using the model [71.9860741092209]
  Clinical researchers often select among and evaluate risk prediction models. Standard metrics calculated from retrospective data are only related to model utility under certain assumptions. When predictions are delivered repeatedly throughout time, the relationship between standard metrics and utility is further complicated.
  arXiv  Detail & Related papers  (2020-06-02T16:26:49Z)

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.