SHAPCA: consistent and interpretable explanations for machine learning models on spectroscopy data
Loading...
Files
Accepted Version
Date
03/07/2026
Authors
Zhang, Mingxing
Rossberg, Nicola
Innocente, Simone
Komolibus, Katarzyna
Gautam, Rekha
O'Sullivan, Barry
Longo, Luca
Visentin, Andrea
Journal Title
Journal ISSN
Volume Title
Publisher
Springer
Published Version
Abstract
In recent years, machine learning models have been increasingly applied to spectroscopic datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safetycritical settings, professionals and researchers must be able to understand and trust the reasoning behind model predictions. However, the inherently high dimensionality and strong collinearity of spectroscopy data pose a fundamental challenge to model explainability. These properties not only complicate model training but also undermine the stability and consistency of explanations, leading to fluctuations in feature importance across repeated training runs. Feature extraction techniques have been used to reduce the input dimensionality; these new features hinder the connection between the prediction and the original signal. This study proposes SHAPCA, an explainable machine learning pipeline that combines Principal Component Analysis (for dimensionality reduction) and Shapely Additive exPlanations (for post hoc explanation) to provide explanations in the original input space, which a practitioner can interpret and link back to the biological components. The proposed framework enables analysis from both global and local perspectives, revealing the spectral bands that drive overall model behaviour as well as the instancespecific features that influence individual predictions. Numerical analysis demonstrated the interpretability of the results and greater consistency across different runs.
Description
Keywords
SHAP , Spectroscopy , Medical diagnosis , PCA
Citation
Zhang, M., Rossberg, N., Innocente, S., Komolibus, K., Gautam, R., O'Sullivan, B., Longo, L. and Visentin, A. (2026) 'SHAPCA: consistent and interpretable explanations for machine learning models on spectroscopy data', 4th World Conference on eXplainable Artificial Intelligence, Fortaleza, Brazil, 1-3 July 2026, pp. 1-25.