Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.12241 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916950561521664 |
|---|---|
| author | Junior, Anisio P. Santos Sabino-Silva, Robinson Martins, Mário Machado Cunha, Thulio Marquez Carneiro, Murillo G. |
| author_facet | Junior, Anisio P. Santos Sabino-Silva, Robinson Martins, Mário Machado Cunha, Thulio Marquez Carneiro, Murillo G. |
| contents | The COVID-19 pandemic has placed unprecedented strain on healthcare systems and remains a global health concern, especially with the emergence of new variants. Although real-time polymerase chain reaction (RT-PCR) is considered the gold standard for COVID-19 detection, it is expensive, time-consuming, labor-intensive, and sensitive to issues with RNA extraction. In this context, ATR-FTIR spectroscopy analysis of biofluids offers a reagent-free, cost-effective alternative for COVID-19 detection. We propose a novel architecture that combines Convolutional Neural Networks (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) networks, referred to as CNN-BiLSTM, to process spectra generated by ATR-FTIR spectroscopy and diagnose COVID-19 from spectral samples. We compare the performance of this architecture against a standalone CNN and other state-of-the-art machine learning techniques. Experimental results demonstrate that our CNN-BiLSTM model outperforms all other models, achieving an average accuracy and F1-score of 0.80 on a challenging real-world COVID-19 dataset. The addition of the BiLSTM layer to the CNN architecture significantly enhances model performance, making CNN-BiLSTM a more accurate and reliable choice for detecting COVID-19 using ATR-FTIR spectra of non-invasive saliva samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12241 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CNN-BiLSTM for sustainable and non-invasive COVID-19 detection via salivary ATR-FTIR spectroscopy Junior, Anisio P. Santos Sabino-Silva, Robinson Martins, Mário Machado Cunha, Thulio Marquez Carneiro, Murillo G. Medical Physics Machine Learning The COVID-19 pandemic has placed unprecedented strain on healthcare systems and remains a global health concern, especially with the emergence of new variants. Although real-time polymerase chain reaction (RT-PCR) is considered the gold standard for COVID-19 detection, it is expensive, time-consuming, labor-intensive, and sensitive to issues with RNA extraction. In this context, ATR-FTIR spectroscopy analysis of biofluids offers a reagent-free, cost-effective alternative for COVID-19 detection. We propose a novel architecture that combines Convolutional Neural Networks (CNN) with Bidirectional Long Short-Term Memory (BiLSTM) networks, referred to as CNN-BiLSTM, to process spectra generated by ATR-FTIR spectroscopy and diagnose COVID-19 from spectral samples. We compare the performance of this architecture against a standalone CNN and other state-of-the-art machine learning techniques. Experimental results demonstrate that our CNN-BiLSTM model outperforms all other models, achieving an average accuracy and F1-score of 0.80 on a challenging real-world COVID-19 dataset. The addition of the BiLSTM layer to the CNN architecture significantly enhances model performance, making CNN-BiLSTM a more accurate and reliable choice for detecting COVID-19 using ATR-FTIR spectra of non-invasive saliva samples. |
| title | CNN-BiLSTM for sustainable and non-invasive COVID-19 detection via salivary ATR-FTIR spectroscopy |
| topic | Medical Physics Machine Learning |
| url | https://arxiv.org/abs/2509.12241 |