When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models
Symmetry · 19.11.2026 · 18 (11) · 1936
DOI: 10.3390/sym18111936 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 19.11.2026. Verfasst von Pietro Hiram Guzzi und 6 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Predictive reliability of artificial intelligence in healthcare extends beyond discrimination, particularly when models are deployed in populations whose epidemiology changes over time. We study how predictive invariance, distributional shift, and asymmetric decision costs jointly shape the robustness of respiratory mortality risk models. A Monte Carlo experiment with known data-generating mechanisms separates prior-probability shift, covariate shift, concept drift, and joint shift, evaluating discrimination, calibration, and decision regret against a Bayes oracle. A longitudinal retrospective analysis of Brazilian SIVEP-Gripe surveillance data (2019–2025) examines temporal and geographic transportability, out-of-time recalibration, and sensitivity to case mix, outcome ascertainment, and predictor timing. In both settings, discrimination remained stable or recovered, while probability accuracy and decision utility deteriorated; covariate shift and concept drift acted differently; and simple recalibration helped in some but not all settings. Invariance, discrimination, calibration, and decision utility are distinct dimensions of robustness that reliable evaluation of clinical artificial intelligence must examine separately under explicit assumptions about distributional change and asymmetric decision consequences.
Zitieren
APA
Guzzi, P. H., Defilippo, A., Veltri, P., Ceccarelli, G., Scarpa, F., Ciccozzi, M., & Branda, F. (2026). When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models. Symmetry, 18(11), 1936. https://doi.org/10.3390/sym18111936
Vancouver
Guzzi PH, Defilippo A, Veltri P, Ceccarelli G, Scarpa F, Ciccozzi M, et al. When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models. Symmetry. 2026;18(11):1936. doi:10.3390/sym18111936
BibTeX
@article{Guzzi2026,
author = {Guzzi, Pietro Hiram and Defilippo, Annamaria and Veltri, Pierangelo and Ceccarelli, Giancarlo and Scarpa, Fabio and Ciccozzi, Massimo and Branda, Francesco},
title = {When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {11},
pages = {1936},
doi = {10.3390/sym18111936}
}
EUVIMED