Machine learning-based investigation of the relationship between plasma emission spectra and biological responses
Abstract
Cold atmospheric plasma (CAP) has shown promising potential across biomedical applications. However, translating these effects into predictable and reproducible outcomes remains challenging due to device variability and the complex and unknown interplay of reactive species. This study evaluates the potential of machine learning (ML) to reliably predict CAP biological results including 24 h MTT and 48 h MTT from optical emission spectroscopy (OES) data. Data-driven models correlate plasma characteristics with cell viability and metabolic activity outcomes in human dermal fibroblasts. Diverse ML models were employed for their differing capabilities in feature extraction from OES data, essential for assessing the predictive capability of ML models for the biological effects of CAP from OES data. To evaluate cross plasma-device transferability without information leakage, models were tested on two distinct CAP jet systems. While the models achieved high accuracy for the primary jet used in training, their performance degraded considerably when applied to data from the secondary jet. To assess whether the loss of cross-device predictability could in principle be restored through minimal domain calibration, we conducted a controlled fine-tuning ablation on the pre-trained models. Results show that while spectra cannot serve as a device-independent predictor for the acute (24 h MTT) outcome, they retain partial transferability for the delayed (48 h MTT) response when minimal calibration is performed and sufficiently expressive models are employed to extract the underlying transferable structure. Moreover, the analysis identified the plasma source frequency as the most influential operational predictor, followed by voltage and treatment time. In identifying the gas-phase free radicals with the highest impact on biological outcomes, spectral fingerprints show the most influential species contributed in cell viability.
Related
- Investigation of human defence responses in a virtual reality environment: an EEG study
- Novel 5-Phenylmorphans as Opioid Receptor Antagonists: Synthesis, Structure-Activity Relationship, Biological Evaluation and Computational Modeling
- Sensing forces: How plants convert mechanical cues into biological responses
- Purified Dietary Aflatoxin B₁ Does Not Impair Broiler Growth Across a Broad Exposure Range but Elicits Subclinical Biological and Tissue Responses.
- Computational investigation of circuit mechanisms underlying short-latency responses to cortical stimulation
BibTeX
@article{emadi2026machine,
title = {{Machine learning-based investigation of the relationship between plasma emission spectra and biological responses}},
author = {Sara Emadi and Kamal Hajisharifi and Ali Fahami and Hassan Mehdian and Jamshid Shanbezadeh and Fatemeh Momeni-Azimi and Augusto Stancampiano and Ali Mesbah and Eric Robert},
journal = {Journal of Physics D: Applied Physics},
year = {2026},
month = sep,
doi = {10.1088/1361-6463/ae3293},
url = {https://hal.science/hal-05759008v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning-based investigation of the relationship between plasma emission spectra and biological responses
AU - Sara Emadi
AU - Kamal Hajisharifi
AU - Ali Fahami
AU - Hassan Mehdian
AU - Jamshid Shanbezadeh
AU - Fatemeh Momeni-Azimi
AU - Augusto Stancampiano
AU - Ali Mesbah
AU - Eric Robert
PY - 2026
DA - 2026/09/22
JO - Journal of Physics D: Applied Physics
DO - 10.1088/1361-6463/ae3293
UR - https://hal.science/hal-05759008v1
AB - Cold atmospheric plasma (CAP) has shown promising potential across biomedical applications. However, translating these effects into predictable and reproducible outcomes remains challenging due to device variability and the complex and unknown interplay of reactive species. This study evaluates the potential of machine learning (ML) to reliably predict CAP biological results including 24 h MTT and 48 h MTT from optical emission spectroscopy (OES) data. Data-driven models correlate plasma characteristics with cell viability and metabolic activity outcomes in human dermal fibroblasts. Diverse ML models were employed for their differing capabilities in feature extraction from OES data, essential for assessing the predictive capability of ML models for the biological effects of CAP from OES data. To evaluate cross plasma-device transferability without information leakage, models were tested on two distinct CAP jet systems. While the models achieved high accuracy for the primary jet used in training, their performance degraded considerably when applied to data from the secondary jet. To assess whether the loss of cross-device predictability could in principle be restored through minimal domain calibration, we conducted a controlled fine-tuning ablation on the pre-trained models. Results show that while spectra cannot serve as a device-independent predictor for the acute (24 h MTT) outcome, they retain partial transferability for the delayed (48 h MTT) response when minimal calibration is performed and sufficiently expressive models are employed to extract the underlying transferable structure. Moreover, the analysis identified the plasma source frequency as the most influential operational predictor, followed by voltage and treatment time. In identifying the gas-phase free radicals with the highest impact on biological outcomes, spectral fingerprints show the most influential species contributed in cell viability.
SN - 0022-3727
SN - 1361-6463
ER -