137. A Duality-Based Bayesian Framework for Optimizing Lactate Testing in Sports and Medicine
Invited abstract in session WB-40: Sports analytics, stream Sports and Entertainment.
Wednesday, 10:30-12:00Room: Newlyn LG.02
Authors (first author is the speaker)
| 1. | Praowpan Tansitpong
|
| NIDA Business School, National Institute of Development Administration |
Abstract
Lactate testing is a cornerstone of performance assessment and metabolic monitoring in sports and medical applications. However, frequent testing can be resource-intensive and invasive. This study introduces a novel optimization framework that combines Bayesian prediction and duality principles to improve the efficiency of lactate testing protocols. The duality problem is formulated to balance testing frequency and predictive accuracy, leveraging Bayesian methods to integrate prior data and real-time observations for precise lactate level prediction. The approach ensures optimal resource allocation by addressing the trade-off between minimizing test invasiveness and maximizing diagnostic reliability. Numerical experiments and real-world data demonstrate the efficacy of the framework in reducing testing frequency while maintaining clinical and performance decision-making accuracy. The results underscore the synergy between duality theory and Bayesian inference, offering a robust solution for adaptive, cost-effective testing protocols in diverse applications.
Keywords
- Decision Support Systems
- OR in Sports
- Programming, Linear
Status: accepted
Back to the list of papers