Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
Abstract
Antimicrobial resistance is expected to claim 10 million lives per year by 2050, and resource-limited regions are most affected. Raman spectroscopy is a novel pathogen diagnostic approach promising rapid and portable antibiotic resistance testing within a few hours, compared to days when using gold standard methods. However, current algorithms for Raman spectra analysis 1) are unable to generalize well on limited datasets across diverse patient populations and 2) require increased complexity due to the necessity of non-trivial pre-processing steps, such as feature extraction, which are essential to mitigate the low-quality nature of Raman spectral data. In this work, we address these limitations using Sharpness-Aware Minimization (SAM) to enhance model generalization across a diverse array of hyperparameters in clinical bacterial isolate classification tasks. We demonstrate that SAM achieves accuracy improvements of up to 10.5% on a single split, and an increase in average accuracy of 2.7% across all splits in spectral classification tasks over the traditional optimizer, Adam. These results display the capability of SAM to advance the clinical application of AI-powered Raman spectroscopy tools.
Related
- Bacterial competence and genetic diversity: Implications for the design of diagnostics and vaccines.
- Bacterial toxin sensing induces transient inflammasome-dependent innate immune memory that improves survival during sepsis
- Perturbation-based propagation of bacterial composition uncertainty improves robustness and reproducibility of microbiome differential abundance analysis.
- Dietary licorice improves carcass yield, hepatocellular protection, gut health, oxidative status, and cecal bacterial balance in broiler chickens.
- When Raman Spectral Fidelity and Bacterial Classification Accuracy Diverge
BibTeX
@misc{zareno2026sharpnessaware,
title = {{Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics}},
author = {Kaitlin Zareno and Jarett Dewbury and Siamak K. Sorooshyari and Hossein Mobahi and Loza F. Tadesse},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.19453},
eprint = {2609.19453},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.19453},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
AU - Kaitlin Zareno
AU - Jarett Dewbury
AU - Siamak K. Sorooshyari
AU - Hossein Mobahi
AU - Loza F. Tadesse
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.19453
UR - https://arxiv.org/abs/2609.19453
AB - Antimicrobial resistance is expected to claim 10 million lives per year by 2050, and resource-limited regions are most affected. Raman spectroscopy is a novel pathogen diagnostic approach promising rapid and portable antibiotic resistance testing within a few hours, compared to days when using gold standard methods. However, current algorithms for Raman spectra analysis 1) are unable to generalize well on limited datasets across diverse patient populations and 2) require increased complexity due to the necessity of non-trivial pre-processing steps, such as feature extraction, which are essential to mitigate the low-quality nature of Raman spectral data. In this work, we address these limitations using Sharpness-Aware Minimization (SAM) to enhance model generalization across a diverse array of hyperparameters in clinical bacterial isolate classification tasks. We demonstrate that SAM achieves accuracy improvements of up to 10.5% on a single split, and an increase in average accuracy of 2.7% across all splits in spectral classification tasks over the traditional optimizer, Adam. These results display the capability of SAM to advance the clinical application of AI-powered Raman spectroscopy tools.
ER -