Evolutionary Neural Architecture Search for Type 2 Diabetes Mellitus Diagnosis from Salivary ATR-FTIR Spectroscopy

• Lucas Mendonça Andrade UFU
• Robinson Sabino-Silva UFU
• Murillo Guimarães Carneiro UFU

DOI: https://doi.org/10.5753/sbcas.2024.2675

Resumo

The blood diagnosis of diabetes mellitus (DM) is accurate, but invasive. Attenuated Total Reflectance by Fourier Transform Infrared Spectroscopy (ATR-FTIR) is a green technology adopted in the detection of several diseases resulting in a non-invasive and accurate diagnosis. The analysis of ATR-FTIR data using deep learning techniques like Convolutional Neural Network (CNN) is promising. However, the challenges to find optimized architectures are barely explored in the ATR-FTIR literature. In this paper, we propose an Evolutionary Neural Architecture Search technique able to find optimized CNN architectures for salivary ATR-FTIR spectra for type 2 DM diagnosis using Genetic Algorithm as optimization approach.

Referências

Azhar, A., Gillani, S.W., Mohiuddin, G. and Majeed, R.A. (2020) “A Systematic Review on Clinical Implication of Continous Glucose Monitoring in Diabetes Management”, Journal of Pharmacy and Biollied Sciences p. 102–111.

Cho, N.H., Shaw, J.E., Karuranga, S., Huang, Y., Fernandes, J.D.R., Ohlrogge, A.W. and Malanda, B. (2018) “IDF Diabetes Atlas: Global estimates of diabetes prevalence for 2017 and projections for 2045”, Diabetes Res. Clin. Pract. 18.

Care, D. and Suppl, S.S. (2021) “Classification and diagnosis of diabetes: Standards of medical care in diabetes-2021”, Diabetes Care 44 S15–S33.

Contreras-Rozo, J.A., Mata-Miranda, M.M., Vazquez-Zapien, G.J. and Delgado-Macuil, R.J. (2023) “Infrared spectroscopy technique: An alternative technology for diabetes diagnosis”, Biomedical Signal Processing and Control, Volume 86, Part B.

Nogueira, M., Barreto, A., Furukawa, M., Rovai, E., Bastos, A., Bertoncello, G. and Carvalho, L. (2022) “FTIR spectroscopy as a point of care diagnostic tool for diabetes and periodontitis: A saliva analysis approach”, Photodiagnosis and Photodynamic Therapy, Volume 40.

Zhang, X., Yang, F., Xiao, J., Qu, H., Jocelin, N.F., Ren, L. and Guo, Y. (2024) “Analysis and comparison of machine learning methods for species identification utilizing ATR-FTIR spectroscopy”, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, Volume 308.

Souza, N.M., Machado, B., Padoin, L., Prá, D., Fay, A., Tomaz, M., Cobellini, V.A. and Rieger, A. (2023) “Discrimination of molecular subtypes of breast cancer with ATR-FTIR spectroscopy in blood plasma coupled with partial least square-artificial neural network discriminant analysis (PLS-ANNDA)”, Chemometrics and Intelligent Laboratory Systems, Volume 237.

Yang, X., Fang, T., Li, Y., Guo, L., Li, F., Huang, F. and Li, L. (2019) “Pre-diabetes diagnosis based on ATR-FTIR spectroscopy combined with CART and XGBoosts”, Optik, Volume 180.

Caixeta, D., Carneiro, M., Rodrigues, R., Alves, D., Goulart, L., Cunha, T., Espindola, F., Vitorino, R. and Sabino-Silva, R. (2023) “Salivary ATR-FTIR Spectroscopy Coupled with Support Vector Machine Classification for Screening of Type 2 Diabetes Mellitus”, Diagnostics.

Caixeta, D., Aguiar, E., Cardoso-Sousa, L., Coelho, L., Oliveira, S., Espindola, F., Raniero, L., Crosara, K., Baker, M., Siqueira, W. and Sabino-Silva, R. (2020) “Salivary mocelular spectroscopy: A sustainable, rapid and non-invasive monitoring tool for diabetes mellitus during inslin treatment”, PLOS ONE 15.

Sánches-Brito, M., Luna-Rosas, F., Mendoza-González, R., Mata-Miranda, M., Martínez-Romo, J., and Vázquez-Zapién, G. (2021) “A machine-learning strategy to evaluate the use of FTIR spectra of saliva for a good control of type 2 diabetes”, Talanta, Volume 221.

Guo, S., Xiu, J., Chen, W., Ji, T., Wang, F. and Liu, H. (2023) “Precise diagnosis of lung cancer enabled by improved FTIR-based machine learning”, Infrared Physics & Technology, Volume 132.

Dou, J., Dawuti, W., Li, J., Zhao, H., Zhou, R., Zhou, J., Lin, R. and Lü, G. (2023) “Rapid detection of serological biomarkers in gallbladder carcinoma using fourier transform infrared spectroscopy combined with machine learning”, Talanta, Volume 259.

Nogueira, M., Leal, L., Marcarini, W., Pimentel, R., Muller, M., Vassallo, P., Campos, L., Santos, L., Luiz, W., Mill, J., Barauna, V. and Carvalho, L. (2021) “Rapid diagnosis of COVID-19 using FT-IR ATR spectroscopy and machine learning”, Scientific Reports 11, 15409.

Jiang, S., Xu, Z., Kamran, M., Zinchik, S., Paheding, S., McDonald, A., Bar-Ziv, E. and Zavala, V. (2021) “Using ATR-FTIR spectra and convolutional neural networks for characterizing mixed plastic waste”, Computers & Chemical Engineering, Volume 155.

Zeng, G., Ma, Y., Du, M., Chen, T., Lin, L., Dai, M., Luo, H., Hu, L., Zhou, Q. and Pan, X. (2024) “Deep convolutional neural networks for aged microplastics identification by Fourier transform infrared spectra classification”, Science of the Total Environment, Volume 913.

Santos, A.P., Filho, A.C.M., Sabino-Silva, R. and Carneiro, M. (2023) “Convolutional Neural Networks for the Molecular Detection of COVID-19”, Intelligent Systems, Volume 14196.

Sanchez-Brito, M., Luna-Rosas, F., Mendoza-Gonzalez, R., Vazquez-Zapien, G., Martinez-Romo, J. and Mata-Miranda, M. (2021) “Type 2 diabetes diagnosis assisted by machine learning techniques through the analysis of FTIR spectra of saliva”, Biomedical Signal Processing and Control, Volume 69.

Sánchez-Brito, M., Luna-Rosas, F., Mendoza-González, R., Mata-Miranda, M., Martínez-Romo, J. and Vázquez-Zapién, G. (2021) “A machine-learning strategy to evaluate the use of FTIR spectra of saliva for a good control of type 2 diabetes”, Talanta, Volume 221.

Asghari, A., Khorrami, M. e Garmarudi, A. (2020) “Comparison between partial least square and support vector regression with a genetic algorithm wavelength selection method fot the simultaneous determination of some oxygenate compounds in gasoline by FTIR spectroscopy”, Infrared Physics & Technology, Volume 105.

Mohammadi, M., Khorrami, M., Vatani, A., Ghasemzadeh, H., Vatanparast, H., Bahramian, A. e Fallah, A. (2021) “Genetic algorithm based support vector machine regression for prediction of SARA analysis in crude oil samples using ATR-FTIR spectroscopy”, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 245.

Zandbaaf, S., Khorrami, M. e Afshar, M. (2022) “Genetic algorithm based artificial neural network and partial least squares regression methods to predict of breakdown voltage for transformer oils samples in power industry using ATR-FTIR spectroscopy”, Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, vol. 273.

Elsken, T., Metzen, J.H. and Hutter, F. (2019) “Neural architecture search: A survey”, J. Mach. Learn. Res., vol. 20, no. 1, p. 1997–2017, .

Lu, Z., Cheng, R., Jin, Y., Tan, K. and Deb, K. (2022) “Neural Architecture Search as Multiobjective Optimization Benchmarcks: Problem Formulation and Performance Assessment”, IEEE Transactions on Evolutionary Computation.

Wen, L., Gao, L., Li, X. and Li, H. (2022) “A new genetic algorithm based evolutionary neural architecture search for image classification”, Swarm and Evolutionary Computation, Volume 75.

Yu, C., Wang, Y., Tang, C., Feng, W. and Lv, J. (2023) “EU-Net: Automatic U-NET neural architecture search with differential evolutionary algorithm for medical image segmentation”, Computers in Biology and Medicine, Volume 167.

Garcia-Garcia, C., Morales-Reyes, A. and Escalante, H.J. (2023) “Continuous Cartesian Genetic Programming based representation for multi-objective neural architecture search”, Applied Soft Computing, Volume 147.

Butler, H.J., Brennan, P.M., Cameron, J.M., Finlayson, D., Hegarty, M.G., Jenkinson, M.D. and Palmer, D.S. (2019) “Development of high-throughput ATR-FTIR technology for rapid triage of brain cancer”, Nat. Commun.

Akulich, F., Anahideh, H., Sheyyab, M. and Ambre, D.J.C. (2022) “Explainable predict modeling for limited spectral data”, Chemometrics and Intelligent Laboratory Systems, Volume 225.