Yuanbiao Wang | Searcharxiv

arXiv2025

An AI-driven Assessment of Bone Density as a Biomarker Leading to the Aging Law

As global population aging intensifies, there is growing interest in the study of biological age. Bones have long been used to evaluate biological age, and the decline in bone density with age is a well-recognized phenomenon in adults. However, the pattern of this decline remains controversial, making it difficult to serve as a reliable indicator of the aging process. Here we present a novel AI-driven statistical method to assess the bone density, and a discovery that the bone mass distribution in trabecular bone of vertebrae follows a non-Gaussian, unimodal, and skewed distribution in CT images. The statistical mode of the distribution is defined as the measure of bone mass, which is a groundbreaking assessment of bone density, named Trabecular Bone Density (TBD). The dataset of CT images are collected from 1,719 patients who underwent PET/CT scans in three hospitals, in which a subset of the dataset is used for AI model training and generalization. Based upon the cases, we demonstrate that the pattern of bone density declining with aging exhibits a consistent trend of exponential decline across sexes and age groups using TBD assessment. The developed AI-driven statistical method blazes a trail in the field of AI for reliable quantitative computation and AI for medicine. The findings suggest that human aging is a gradual process, with the rate of decline slowing progressively over time, which will provide a valuable basis for scientific prediction of life expectancy.

physics.med-ph↗

arXiv2025

MonoM: Enhancing Monotonicity in Learned Cardinality Estimators

Cardinality estimation is a key component of database query optimization. Recent studies have demonstrated that learned cardinality estimation techniques can surpass traditional methods in accuracy. However, a significant barrier to their adoption in production systems is their tendency to violate fundamental logical principles such as monotonicity. In this paper, we explore how learned models specifically MSCN, a query driven deep learning algorithm can breach monotonicity constraints. To address this, we propose a metric called MonoM, which quantitatively measures how well a cardinality estimator adheres to monotonicity across a given query workload. We also propose a monotonic training framework which includes a workload generator that produces directly comparable queries (one query's predicates are strictly more relaxed than another's, enabling monotonicity inference without actual execution) and a novel regularization term added to the loss function. Experimental results show that our monotonic training algorithm not only enhances monotonicity adherence but also improves cardinality estimation accuracy. This improvement is attributed to the regularization term, which reduces overfitting and improves model generalization.

cs.DB↗