Detección de Personas Positivas a COVID-19 mediante el Análisis de Espectros ATR-FTIR de Muestras de Saliva empleando Machine Learning
DOI:
https://doi.org/10.17488/RMIB.43.3.5Palabras clave:
Saliva, ATR-FTIR, Machine learning, COVID-19, DiagnosisResumen
La COVID-19 es una enfermedad infecciosa ocasionada por el virus SARS-CoV-2. La propagación de este virus se produce principalmente a través de gotitas liberadas por la nariz o la boca de una persona infectada. Aunque se han desarrollado vacunas que permiten reducir efectivamente los efectos que esta infección viral provoca, el método más eficaz para contener la propagación del virus son las numerosas pruebas para detectar y aislar los posibles portadores. Sin embargo, el tiempo de respuesta, combinado con el costo de las pruebas reales, hace que esta opción sea poco práctica. Aquí, comparamos algunas metodologías de machine learning para proponer una estrategia confiable para detectar personas positivas a COVID-19 analizando espectros de saliva obtenidos por espectroscopia infrarroja transformada de Fourier (FTIR). Tras analizar 1275 espectros, con 7 estrategias comúnmente empleadas en el área de machine learning, concluimos que un modelo de regresión lineal multivariante (MLMR) resulta ser la mejor opción para identificar posibles infectados. De acuerdo con nuestros resultados, el desplazamiento observado en la región de la amida I del espectro, resulta fundamental y confiable para establecer una frontera a partir del cambio de pendiente que este provoca. Al ser más ágil y económica que la reacción en cadena de la polimerasa con transcriptasa inversa (RT-PCR), podría aplicarse confiablemente como estrategia preliminar a RT-PCR.
Descargas
Citas
World Health Organization. Coronavirus disease (COVID-19) [Internet]. 2021. Available from: https://www.who.int/health-topics/coronavirus
To KKW, Tsang OTY, Leung WS, Tam AR, et al. Temporal profiles of viral load in posterior oropharyngeal saliva samples and serum antibody responses during infection by SARS-CoV-2: an observational cohort study. Lancet Infect Dis [Internet]. 2020;20(5):565–574. Available from: https://doi.org/10.1016/S1473-3099(20)30196-1
To KKW, Tsang OTY, Yip CCY, Chan KH, et al. Consistent Detection of 2019 Novel Coronavirus in Saliva. Clin Infect Dis [Internet]. 2020;71(15):841–843. Available from: https://doi.org/10.1093/cid/ciaa149
Long C, Xu H, Shen Q, Zhang X, et al. Diagnosis of the Coronavirus disease (COVID-19): rRT-PCR or CT? Eur J Radiol [Internet]. 2020;126(1):108961. Available: https://doi.org/10.1016/j.ejrad.2020.108961
Ravi N, Cortade DL, Ng E, Wang SX. Diagnostics for SARS-CoV-2 detection: A comprehensive review of the FDA-EUA COVID-19 testing landscape. Biosens Bioelectron [Internet]. 2020;165:112454. Available from: https://doi.org/10.1016/j.bios.2020.112454
Zhang W, Du RH, Li B, Zheng XS, et al. Molecular and serological investigation of 2019-nCoV infected patients: implication of multiple shedding routes. Emerg Microbes Infect [Internet]. 2020;9(1):386–389. Available from: https://doi.org/10.1080/22221751.2020.1729071
Böger B, Fachi MM, Vilhena RO, Cobre AF, et al. Systematic review with meta-analysis of the accuracy of diagnostic tests for COVID-19. Am J Infect Control [Internet]. 2021;49(1):21–29. Available from: https://doi.org/10.1016/j.ajic.2020.07.011
Farshidfar N, Hamedani S. The Potential Role of Smartphone-Based Microfluidic Systems for Rapid Detection of COVID-19 Using Saliva Specimen. Mol Diagn Ther [Internet]. 2020;24:371–373. Available from: https://doi.org/10.1007/s40291-020-00477-4
Kucirka LM, Lauer SA, Laeyendecker O, Boon D, et al. Variation in False-Negative Rate of Reverse Transcriptase Polymerase Chain Reaction–Based SARS-CoV-2 Tests by Time Since Exposure. Ann Intern Med [Internet]. 2020;173(4):262–267. Available from: https://doi.org/10.7326/M20-1495
Luhby T. A coronavirus test could cost as little as $20 or as much as $850. CNN [Internet]. 2020. Available from: https://edition.cnn.com/2020/07/15/health/coronavirus-test-cost/index.html
Smith B. Fundamentals of Fourier Transform Infrared Spectroscopy. 2nd ed. Florida: Taylor and Francis Group; 2011. 1-17 p.
Smith BC. Infrared Spectral Interpretation: A Systematic Approach. United States of America: CRC Press; 1998. 304 p.
Bel’skaya LV, Sarf EA, Kosenok VK. Age and gender characteristics of the biochemical composition of saliva: Correlations with the composition of blood plasma. J Oral Biol Craniofacial Res [Internet]. 2020;10(2):59–65. Available from: https://doi.org/10.1016/j.jobcr.2020.02.004
Nogueira MS, Leal LB, Marcarini WD, Pimentel RL, et al. Rapid diagnosis of COVID-19 using FT-IR ATR spectroscopy and machine learning. Sci Rep [Internet]. 2021;11:15409. Available from: https://doi.org/10.1038/s41598-021-93511-2
Guleken Z, Jakubczyk P, Wiesław P, Krzysztof P, et al. Characterization of Covid-19 infected pregnant women sera using laboratory indexes, vibrational spectroscopy, and machine learning classifications. Talanta [Internet]. 2022;237:122916. Available from: https://doi.org/10.1016/j.talanta.2021.122916
Calvo-Gomez O, Calvo H, Cedillo-Barrón L, Vivanco-Cid H, et al. Potential of ATR-FTIR–Chemometrics in Covid-19: Disease Recognition. ACS Omega [Internet]. 2022;7(35):30756–30767. Available from: https://doi.org/10.1021/acsomega.2c01374
Bandeira CCS, Madureira KCM, Rossi MB, Gallo JF, et al. Micro-Fourier-transform infrared reflectance spectroscopy as tool for probing IgG glycosylation in COVID-19 patients. Sci Rep [Internet]. 2022;12:4269. Available from: https://doi.org/10.1038/s41598-022-08156-6
Kitane DL, Loukman S, Marchoudi N, Fernandez-Galiana A, et al. A simple and fast spectroscopy-based technique for Covid-19 diagnosis. Sci Rep [Internet]. 2021;11:16740 Available from: https://doi.org/10.1038/s41598-021-95568-5
Baker MJ, Trevisan J, Bassan P, Bhargava R, et al. Using Fourier transform IR spectroscopy to analyze biological materials. Nat Protoc [Internet]. 2014;9(8): 1771-1791. Available from: https://doi.org/10.1038/nprot.2014.110
Morais CLM, Lima KMG, Singh M, Martin FL. Tutorial: multivariate classification for vibrational spectroscopy in biological samples. Nat Protoc [Internet]. 2020;15:2143-2162. Available from: https://doi.org/10.1038/s41596-020-0322-8
Callery EL, Morais CLM, Paraskevaidi M, Brusic V, et al. New approach to investigate Common Variable Immunodeficiency patients using spectrochemical analysis of blood. Sci Rep [Internet]. 2019;9:7239. Available from: https://doi.org/10.1038/s41598-019-43196-5
Shi L, Liu X, Shi L, Stinson HT, et al. Mid-infrared metabolic imaging with vibrational probes. Nat. Methods [Internet]. 2020;17:844-851. Available from: https://doi.org/10.1038/s41592-020-0883-z
Yang X, Fang T, Li Y, Guo L, et al. Pre-diabetes diagnosis based on ATR-FTIR spectroscopy combined with CART and XGBoots. Optik [Internet]. 2019;180:189–198. Available from: https://doi.org/10.1016/j.ijleo.2018.11.059
Lu Y, Zhao Y, Zhu Y, Xu X, et al. In situ research and diagnosis of breast cancer by using HOF-ATR-FTIR spectroscopy. Spectrochim Acta A Mol Biomol Spectrosc [Internet]. 2020;235:118178. Available from: https://doi.org/10.1016/j.saa.2020.118178
Naseer K, Ali S, Mubarik S, Hussain I, et al. FTIR spectroscopy of freeze-dried human sera as a novel approach for dengue diagnosis. Infrared Phys Technol [Internet]. 2019;102:102998. Available from: https://doi.org/10.1016/j.infrared.2019.102998
Wang X, Wu Q, Li C, Zhou Y, et. A study of Parkinson’s disease patients’ serum using FTIR spectroscopy. Infrared Phys Technol [Internet]. 2020;106:103279. Available from: https://doi.org/10.1016/j.infrared.2020.103279
Sala A, Anderson DJ, Brennan PM, Butler HJ, et al. Biofluid diagnostics by FTIR spectroscopy: A platform technology for cancer detection. Cancer Lett [Internet]. 2020;477:122-130. Available from: https://doi.org/10.1016/j.canlet.2020.02.020
Jarvis S, Crossley SA. Approaching Language Transfer Through Text Classification: Explorations in the Detection-based Approach [Internet]. Blue Ridge Summit: Multilingual Matters; 2012. 208p. Available from: https://doi.org/10.21832/9781847696991
Stewart WJ. Probability, Markov Chains, Queues, and Simulation: The Mathematical Basis of Performance Modeling [Internet]. New Jersey, United States: Princeton University Press; 2009. 776p. Available from: https://doi.org/10.2307/j.ctvcm4gtc
Paliouras G, Karkaletsis V, Spyropoulos CD (eds.). Machine Learning and Its Applications: Advanced Lectures [Internet]. Germany: Springer; 2001. 324p. Available from: https://doi.org/10.1007/3-540-44673-7
Hodeghatta UR, Nayak U. Business Analytics Using R - A Practical Approach. United States: Apress; 2016. 297p.
Vidgen R, Kirshner S, Tan F. Business Analytics: A Management Approach. United Kingdom: Bloomsbury Academic; 2019. 430p.
Géron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. Canada: O’Reilly Media, Inc.; 2019. 851p.
Rajaguru H, Prabhakar SK. KNN Classifier and K-Means Clustering for Robust Classification of Epilepsy from EEG Signals. A Detailed Analysis. Germany: Anchor Academic Publishing; 2017. 54p.
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2022 Revista mexicana de ingeniería biomédica.
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
Una vez que el artículo es aceptado para su publicación en la RMIB, se les solicitará al autor principal o de correspondencia que revisen y firman las cartas de cesión de derechos correspondientes para llevar a cabo la autorización para la publicación del artículo. En dicho documento se autoriza a la RMIB a publicar, en cualquier medio sin limitaciones y sin ningún costo. Los autores pueden reutilizar partes del artículo en otros documentos y reproducir parte o la totalidad para su uso personal siempre que se haga referencia bibliográfica al RMIB. No obstante, todo tipo de publicación fuera de las publicaciones académicas del autor correspondiente o para otro tipo de trabajos derivados y publicados necesitaran de un permiso escrito de la RMIB.
