Explainable Surrogate Models for Decision Support at Critical Thermoregulation Thresholds: abstract

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

In operational settings thermoregulation models are used for decision support, but increasing complexity can reduce interpretability. This can limit trust and obscure which conditions drive risk. To address this gap, we introduce a workflow that converts complex physiology-based models into interpretable, threshold-focused surrogate models optimized for operational decision support, while preserving nearequivalent accuracy. This makes key risk drivers explicit and easy to communicate.