1
|
Caixeta DC, Carneiro MG, Rodrigues R, Alves DCT, Goulart LR, Cunha TM, Espindola FS, Vitorino R, Sabino-Silva R. Salivary ATR-FTIR Spectroscopy Coupled with Support Vector Machine Classification for Screening of Type 2 Diabetes Mellitus. Diagnostics (Basel) 2023; 13:diagnostics13081396. [PMID: 37189497 DOI: 10.3390/diagnostics13081396] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Revised: 02/04/2023] [Accepted: 02/08/2023] [Indexed: 05/17/2023] Open
Abstract
The blood diagnosis of diabetes mellitus (DM) is highly accurate; however, it is an invasive, high-cost, and painful procedure. In this context, the combination of ATR-FTIR spectroscopy and machine learning techniques in other biological samples has been used as an alternative tool to develop a non-invasive, fast, inexpensive, and label-free diagnostic or screening platform for several diseases, including DM. In this study, we used the ATR-FTIR tool associated with linear discriminant analysis (LDA) and a support vector machine (SVM) classifier in order to identify changes in salivary components to be used as alternative biomarkers for the diagnosis of type 2 DM. The band area values of 2962 cm-1, 1641 cm-1, and 1073 cm-1 were higher in type 2 diabetic patients than in non-diabetic subjects. The best classification of salivary infrared spectra was by SVM, showing a sensitivity of 93.3% (42/45), specificity of 74% (17/23), and accuracy of 87% between non-diabetic subjects and uncontrolled type 2 DM patients. The SHAP features of infrared spectra indicate the main salivary vibrational modes of lipids and proteins that are responsible for discriminating DM patients. In summary, these data highlight the potential of ATR-FTIR platforms coupled with machine learning as a reagent-free, non-invasive, and highly sensitive tool for screening and monitoring diabetic patients.
Collapse
Affiliation(s)
- Douglas Carvalho Caixeta
- Innovation Center in Salivary Diagnostic and Nanotheranostics, Department of Physiology, Institute of Biomedical Sciences, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| | | | - Ricardo Rodrigues
- Innovation Center in Salivary Diagnostic and Nanotheranostics, Department of Physiology, Institute of Biomedical Sciences, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| | - Deborah Cristina Teixeira Alves
- Innovation Center in Salivary Diagnostic and Nanotheranostics, Department of Physiology, Institute of Biomedical Sciences, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| | - Luís Ricardo Goulart
- Institute of Biotechnology, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| | - Thúlio Marquez Cunha
- School of Medicine, Federal University of Uberlandia (UFU), Uberlandia 38408-100, Minas Gerais, Brazil
| | - Foued Salmen Espindola
- Institute of Biotechnology, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| | - Rui Vitorino
- Institute of Biomedicine, Department of Medical Sciences, University of Aveiro, 3810-193 Aveiro, Portugal
| | - Robinson Sabino-Silva
- Innovation Center in Salivary Diagnostic and Nanotheranostics, Department of Physiology, Institute of Biomedical Sciences, Federal University of Uberlandia, Uberlandia 38408-100, Minas Gerais, Brazil
| |
Collapse
|
2
|
Veettil TCP, Wood BR. A Combined Near-Infrared and Mid-Infrared Spectroscopic Approach for the Detection and Quantification of Glycine in Human Serum. SENSORS (BASEL, SWITZERLAND) 2022; 22:s22124528. [PMID: 35746311 PMCID: PMC9228712 DOI: 10.3390/s22124528] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 06/03/2022] [Accepted: 06/10/2022] [Indexed: 05/16/2023]
Abstract
Serum is an important candidate in proteomics analysis as it potentially carries key markers on health status and disease progression. However, several important diagnostic markers found in the circulatory proteome and the low-molecular-weight (LMW) peptidome have become analytically challenging due to the high dynamic concentration range of the constituent protein/peptide species in serum. Herein, we propose a novel approach to improve the limit of detection (LoD) of LMW amino acids by combining mid-IR (MIR) and near-IR spectroscopic data using glycine as a model LMW analyte. This is the first example of near-IR spectroscopy applied to elucidate the detection limit of LMW components in serum; moreover, it is the first study of its kind to combine mid-infrared (25-2.5 μm) and near-infrared (2500-800 nm) to detect an analyte in serum. First, we evaluated the prediction model performance individually with MIR (ATR-FTIR) and NIR spectroscopic methods using partial least squares regression (PLS-R) analysis. The LoD was found to be 0.26 mg/mL with ATR spectroscopy and 0.22 mg/mL with NIR spectroscopy. Secondly, we examined the ability of combined spectral regions to enhance the detection limit of serum-based LMW amino acids. Supervised extended wavelength PLS-R resulted in a root mean square error of prediction (RMSEP) value of 0.303 mg/mL and R2 value of 0.999 over a concentration range of 0-50 mg/mL for glycine spiked in whole serum. The LoD improved to 0.17 mg/mL from 0.26 mg/mL. Thus, the combination of NIR and mid-IR spectroscopy can improve the limit of detection for an LMW compound in a complex serum matrix.
Collapse
Affiliation(s)
- Thulya Chakkumpulakkal Puthan Veettil
- Centre for Biospectroscopy, Monash University, Clayton, VIC 3800, Australia;
- Centre for Sustainable and Circular Technologies (CSCT), University of Bath, Bath BA2 7AY, UK
| | - Bayden R. Wood
- Centre for Biospectroscopy, Monash University, Clayton, VIC 3800, Australia;
- Correspondence:
| |
Collapse
|