Interpretable Classification of Bacterial Raman Spectra with Knockoff Wavelets

Abstract

Deep neural networks and other sophisticated machine learning models are widely applied to biomedical signal data because they can detect complex patterns and compute accurate predictions. However, the difficulty of interpreting such models is a limitation, especially for applications involving high-stakes decision, including the identification of bacterial infections. In this paper, we consider fast Raman spectroscopy data and demonstrate that a logistic regression model with carefully selected features achieves accuracy comparable to that of neural networks, while being much simpler and more transparent. Our analysis leverages wavelet features with intuitive chemical interpretations, and performs controlled variable selection with knockoffs to ensure the predictors are relevant and non-redundant. Although we focus on a particular data set, the proposed approach is broadly applicable to other types of signal data for which interpretability may be important.

arXiv comment9 pages, 6 figures, 4 tables

References in corpus (9)

• Feature Selection: A Data Perspective
• Interpretable machine learning: definitions, methods, and applications
• Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning
• Consistency of random forests
• Controlling the false discovery rate via knockoffs
• Near-ideal model selection by ${\ell }_1$ minimization
• Convolutional Dictionary Learning: A Comparative Review and New Algorithms
• Deep Knockoffs
• Rejoinder: "Gene Hunting with Hidden Markov Model Knockoffs"