Work

Distribution Shift Analysis in Generalizable Modelling: Intensive Care Time-Series Data

Year: 2026

Type: book-chapter

Abstract: In this paper, we investigate how distribution shift affects model generalizability in medical time-series from intensive care. We define clinically relevant domain adaptation scenarios for predicting hypotension and hypoxemia using the MIMIC-III Matched Waveform Database v1.0. Distribution shift is quantified via the Kolmogorov-Smirnov test (KS) applied to an interpretable, lower-dimensional data representation. Our results highlight the challenges of measuring covariate, prior probability, and semantic shifts in non-stationary multivariate time series. We observed linear correlation (0.74 and 0.99) between KS(source train, target) - KS(source train, source test) and RMSE difference when comparing in-distribution and out-of-distribution model performance. We argue that developing and benchmarking data-driven models should explicitly account for modality-specific data shift characteristics.

Source: Studies in health technology and informatics

DOI: 10.3233/shti260163

Authors: Mayra Elwes, Jonas Alfitian, Karen Hornung, Bhanu Koppolu, Oya Beyan, Ekaterina Kutafina

Institutions: University of Cologne, University Hospital Cologne

Language: English

Topic: Machine Learning in Healthcare

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: hybrid

OpenAlex ID: W7162030646

FWCI:

Cites:

Cited by:

Related to: