Saved in:
Bibliographic Details
Main Authors: Wei, Longfei, Sheng, Fang, Zhang, Jianfei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12755
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914112777224192
author Wei, Longfei
Sheng, Fang
Zhang, Jianfei
author_facet Wei, Longfei
Sheng, Fang
Zhang, Jianfei
contents Artificial intelligence (AI) has significantly improved medical screening accuracy, particularly in cancer detection and risk assessment. However, traditional classification metrics often fail to account for imbalanced data, varying performance across cohorts, and patient-level inconsistencies, leading to biased evaluations. We propose the Cohort-Attention Evaluation Metrics (CAT) framework to address these challenges. CAT introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity. Key metrics like CATSensitivity (CATSen), CATSpecificity (CATSpe), and CATMean ensure balanced and fair evaluation across diverse populations. This approach enhances predictive reliability, fairness, and interpretability, providing a robust evaluation method for AI-driven medical screening models.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cohort-attention Evaluation Metric against Tied Data: Studying Performance of Classification Models in Cancer Detection
Wei, Longfei
Sheng, Fang
Zhang, Jianfei
Machine Learning
Computational Engineering, Finance, and Science
Artificial intelligence (AI) has significantly improved medical screening accuracy, particularly in cancer detection and risk assessment. However, traditional classification metrics often fail to account for imbalanced data, varying performance across cohorts, and patient-level inconsistencies, leading to biased evaluations. We propose the Cohort-Attention Evaluation Metrics (CAT) framework to address these challenges. CAT introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity. Key metrics like CATSensitivity (CATSen), CATSpecificity (CATSpe), and CATMean ensure balanced and fair evaluation across diverse populations. This approach enhances predictive reliability, fairness, and interpretability, providing a robust evaluation method for AI-driven medical screening models.
title Cohort-attention Evaluation Metric against Tied Data: Studying Performance of Classification Models in Cancer Detection
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2503.12755