Saved in:
| Main Authors: | , , |
|---|---|
| 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 |