When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models

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.

Authors

Institutions

Publication Details

Journal
Symmetry
Published
2026-11-19
DOI
https://doi.org/10.3390/sym18111936
Primary Topic
Machine Learning in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models

Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi, Giancarlo Ceccarelli et al.
Symmetry
Machine Learning in Healthcare
article

When Symmetry Breaks: A Monte Carlo and Longitudinal Study of Predictive Invariance, Dataset Shift, and Asymmetric Decision Costs in Respiratory Mortality Risk Models

Fabio Scarpa, Pierangelo Veltri, Pietro Hiram Guzzi, Giancarlo Ceccarelli, Francesco Branda, Massimo Ciccozzi, Annamaria Defilippo
article en

Abstract

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.

SymmetryVol. 18(11)
Università Campus Bio-Medico (IT), University of Sassari (IT), Policlinico Umberto I (IT), Magna Graecia University (IT), University of Calabria (IT), Sapienza University of Rome (IT)
Machine Learning in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon