← Back to all news
arXiv Computation and Language

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

The study audited ten different classifiers—including linear, tree‑ensemble, neural, glass‑box, and tabular foundation models—on national health survey data to predict myocardial infarction. By systematically removing features that could cause target leakage, the authors found that all models’ AUROC scores collapsed into a narrow band, indicating that reported high accuracy in prior work was largely due to leakage rather than model sophistication. The glass‑box explainable boosting machine performed comparably to other models while being much faster, and the authors demonstrated that fairness, calibration, and uncertainty can be audited and repaired without sacrificing performance.

Related stories

arXiv Machine Learning
5d ago

Machine-Learning Assessment of the Predictive Value of Inflammatory Biomarkers for Cognitive Impairment in an Older Hispanic Adult Cohort

The study evaluates whether inflammatory biomarkers can predict cognitive impairment in older Hispanic adults using interpretable machine learning on a small clinical dataset. A leakage‑safe Bernoulli/Categorical Naive Bayes model was trained on 165 participants from the Panama Aging Research Initiative, with continuous predictors discretized via supervised chi‑square and income treated categorically. The biomarker I‑309 (CCL1) emerged as the sole reliable incremental predictor, boosting ROC‑AUC from 0.630 to 0.740 and achieving statistically significant performance across repeated cross‑validation and random partitions.

By Antony Garcia, Gabrielle Britton, Alcibiades Villarreal, Diana Oviedo, Giselle Rangel, Xinming Huang
More like this →
arXiv AI
Sep 3

The Ceiling Is in the Channel: Auditing Learner Gaps and Measurement Frontiers in Clinical Prediction

The paper introduces a framework that distinguishes two causes of saturation in clinical prediction: a learner gap, where the model fails to use available information, and a measurement‑channel ceiling, where the recorded variables limit performance. It provides theoretical characterizations, finite‑sample diagnostics, and empirical audits across three large cohorts, showing that well‑tuned models approach the frontier while deficient learners leave large gaps. A PRISMA‑guided synthesis across 104 tasks reveals consistent channel‑level patterns, suggesting that improving the learner or the measurement channel can audit and potentially lift performance.

By Sayeed Shafayet Chowdhury, Nusrat Jahan, Snehasis Mukhopadhyay, Shiaofen Fang, Vijay R. Ramakrishnan
multimodal
More like this →
arXiv AI
Jul 21

Comprehensive Evaluation of Machine Learning for Type 2 Diabetes Risk Prediction: Large-Scale External Validation and Fairness Analysis

arXiv:2607. 16253v1 Announce Type: cross Abstract: Machine learning-based Type 2 diabetes risk prediction models obtain good internal validation results but lose effectiveness in real-world applications due to deficient external testing and fairness assessment.

By Rajveer Singh Pall, Sameer Yadav, Siddharth Bhalerao, Sourabh Sahu, Ritu Ahluwalia, Bhaskar Awadhiya
safety
More like this →
arXiv Machine Learning
Jul 20

CardioMeta: Calibrated Multi-Task Prediction of Diabetes, Hypertension, and Cardiovascular Disease Across Population and EHR Data

arXiv:2607. 15721v1 Announce Type: new Abstract: Cardiometabolic diseases remain among the most persistent drivers of preventable morbidity because diabetes, hypertension, and cardiovascular disease frequently co-occur and share metabolic, vascular, demographic, and behavioral determinants.

By S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha, Jungpil Shin
fine-tuning
More like this →
arXiv Machine Learning
5d ago

Mammography Foundation Models for Opportunistic Prediction of Major Adverse Cardiovascular Events

The study evaluates whether mammography foundation models, pretrained for breast cancer tasks, can predict 5‑year major adverse cardiovascular events (MACE) in women using only screening mammograms. In a cohort of 22,497 women (500 MACE events), the models achieved AUROCs of 0.823 and 0.822, outperforming an age‑only baseline. The models also identified higher risk in patients with radiologist‑documented breast arterial calcifications, despite never being trained on that label.

By Paula Feldman, Nusrat Binta Nizam, Sunwoo Kwak, Batuhan Karaman, Katerina Dodelzon, Mert Sabuncu
More like this →
arXiv Machine Learning
5d ago

Interpretable and Calibrated Classification of Clinical Data Using Supervised Feature Binarization

The paper introduces a statistically grounded framework for interpretable, rule-based clinical classification using Bernoulli Naïve Bayes (BNB). It employs supervised chi‑square‑guided binarization to convert continuous medical variables into binary indicators, enabling BNB to handle continuous data while maintaining transparency. On three benchmark datasets—Pima Indians Diabetes, Wisconsin Breast Cancer, and Heart Failure Prediction—the method achieved AUCs of 0.800, 0.984, and 0.919, respectively, and demonstrated reliable probability calibration through cross‑validated analysis and post‑hoc beta calibration.

By Antony Garcia, Adrian Noriega, Gabrielle Britton, Xinming Huang
benchmarks
More like this →