Diabetes Monitoring through Urine Analysis Using ATR-FTIR Spectroscopy and Machine Learning
Abstract
:1. Introduction
2. Methods and Materials
2.1. Experimental Analysis
2.2. Samples Collection
2.3. ATR-FTIR Data Analysis
2.3.1. Principle Component Analysis
- Scores—these are employed to investigate the interrelationships among individual measurements or observations, thus facilitating the detection of trends, groupings, outliers, and other pertinent patterns.
- Loadings—loadings are instrumental in exploring the connections between variables and discerning their influence on the PCs extracted through PCA.
- Distances—distance plots are used to identify outliers and extreme objects within the PCA model constructed with a specified number of components, thus aiding in the detection of data points that deviate significantly from the norm.
- Residual/Explained Variance—variance plots lead the objective of determining the optimal number of components to include in the PCA model, thus offering insight into the proportion of variance accounted for by each component.
2.3.2. Classification Analysis Based on Machine Learning
2.4. Performance Parameter for Quality Evaluation
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Ogurtsova, K.; Guariguata, L.; Barengo, N.C.; Ruiz, P.L.D.; Sacre, J.W.; Karuranga, S.; Sun, H.; Boyko, E.J.; Magliano, D.J. IDF diabetes Atlas: Global estimates of undiagnosed diabetes in adults for 2021. Diabetes Res. Clin. Pract. 2022, 183, 109118. [Google Scholar] [CrossRef] [PubMed]
- Cole, J.B.; Florez, J.C. Genetics of diabetes mellitus and diabetes complications. Nat. Rev. Nephrol. 2020, 16, 377–390. [Google Scholar] [CrossRef] [PubMed]
- Poznyak, A.; Grechko, A.V.; Poggio, P.; Myasoedova, V.A.; Alfieri, V.; Orekhov, A.N. The diabetes mellitus–atherosclerosis connection: The role of lipid and glucose metabolism and chronic inflammation. Int. J. Mol. Sci. 2020, 21, 1835. [Google Scholar] [CrossRef] [PubMed]
- Roep, B.O.; Thomaidou, S.; van Tienhoven, R.; Zaldumbide, A. Type 1 diabetes mellitus as a disease of the β-cell (do not blame the immune system?). Nat. Rev. Endocrinol. 2021, 17, 150–161. [Google Scholar] [CrossRef] [PubMed]
- Padhi, S.; Nayak, A.K.; Behera, A. Type II diabetes mellitus: A review on recent drug based therapeutics. Biomed. Pharmacother. 2020, 131, 110708. [Google Scholar] [CrossRef]
- Chitneni, A.; Rupp, A.; Ghorayeb, J.; Abd-Elsayed, A. Early detection of diabetic peripheral neuropathy by fMRI: An evidence-based review. Brain Sci. 2022, 12, 557. [Google Scholar] [CrossRef]
- Liccardo, D.; Cannavo, A.; Spagnuolo, G.; Ferrara, N.; Cittadini, A.; Rengo, C.; Rengo, G. Periodontal disease: A risk factor for diabetes and cardiovascular disease. Int. J. Mol. Sci. 2019, 20, 1414. [Google Scholar] [CrossRef]
- Yamazaki, T.; Mimura, I.; Tanaka, T.; Nangaku, M. Treatment of diabetic kidney disease: Current and future. Diabetes Metab. J. 2021, 45, 11–26. [Google Scholar] [CrossRef]
- Ansari, P.; Tabasumma, N.; Snigdha, N.N.; Siam, N.H.; Panduru, R.V.; Azam, S.; Hannan, J.; Abdel-Wahab, Y.H. Diabetic retinopathy: An overview on mechanisms, pathophysiology and pharmacotherapy. Diabetology 2022, 3, 11. [Google Scholar] [CrossRef]
- Tomic, D.; Shaw, J.E.; Magliano, D.J. The burden and risks of emerging complications of diabetes mellitus. Nat. Rev. Endocrinol. 2022, 18, 525–539. [Google Scholar] [CrossRef]
- Das, T.; Harshey, A.; Srivastava, A.; Nigam, K.; Yadav, V.K.; Sharma, K.; Sharma, A. Analysis of the ex-vivo transformation of semen, saliva and urine as they dry out using ATR-FTIR spectroscopy and chemometric approach. Sci. Rep. 2021, 11, 11855. [Google Scholar] [CrossRef] [PubMed]
- Sarigul, N.; Kurultak, İ.; Uslu Gökceoğlu, A.; Korkmaz, F. Urine analysis using FTIR spectroscopy: A study on healthy adults and children. J. Biophotonics 2021, 14, e202100009. [Google Scholar] [CrossRef] [PubMed]
- Pan, S.W.; Lu, H.C.; Lo, J.I.; Ho, L.I.; Tseng, T.R.; Ho, M.L.; Cheng, B.M. Using an ATR-FTIR Technique to Detect Pathogens in Patients with Urinary Tract Infections: A Pilot Study. Sensors 2022, 22, 3638. [Google Scholar] [CrossRef]
- Cano-Trujillo, C.; Barbaro, A.; Ortega-Ojeda, F.E.; García-Ruiz, C.; Montalvo, G. Source determination of human and animal oral fluid stains on porous substrates by chemometrics-assisted ATR FTIR spectroscopy: A preliminary study. Microchem. J. 2023, 190, 108648. [Google Scholar] [CrossRef]
- Silva, L.G.; Péres, A.F.; Freitas, D.L.; Morais, C.L.; Martin, F.L.; Crispim, J.C.; Lima, K.M. ATR-FTIR spectroscopy in blood plasma combined with multivariate analysis to detect HIV infection in pregnant women. Sci. Rep. 2020, 10, 20156. [Google Scholar] [CrossRef]
- Kharratian, S.; Conteduca, D.; Procacci, B.; Shaw, D.J.; Hunt, N.T.; Krauss, T.F. Metasurface-enhanced mid-infrared spectroscopy in the liquid phase. Chem. Sci. 2022, 13, 12858–12864. [Google Scholar] [CrossRef]
- Praja, R.K.; Wongwattanakul, M.; Tippayawat, P.; Phoksawat, W.; Jumnainsong, A.; Sornkayasit, K.; Leelayuwat, C. Attenuated Total Reflectance-Fourier Transform Infrared (ATR-FTIR) Spectroscopy Discriminates the Elderly with a Low and High Percentage of Pathogenic CD4+ T Cells. Cells 2022, 11, 458. [Google Scholar] [CrossRef]
- Lilo, T.; Morais, C.L.; Ashton, K.M.; Pardilho, A.; Davis, C.; Dawson, T.P.; Gurusinghe, N.; Martin, F.L. Spectrochemical differentiation of meningioma tumours based on attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy. Anal. Bioanal. Chem. 2020, 412, 1077–1086. [Google Scholar] [CrossRef]
- Perez-Guaita, D.; Richardson, Z.; Heraud, P.; Wood, B. Quantification and identification of microproteinuria using ultrafiltration and ATR-FTIR spectroscopy. Anal. Chem. 2020, 92, 2409–2416. [Google Scholar] [CrossRef]
- Lin, T.L.; Evans, R.D.; Unwin, R.J.; Norman, J.T.; Rich, P.R. Assessment of Measurement of Salivary Urea by ATR-FTIR Spectroscopy to Screen for CKD. Kidney360 2022, 3, 357. [Google Scholar] [CrossRef]
- Ergün, E.; Kart, Ş.; Zeybek, D.K.; Zeybek, B. Simultaneous electrochemical determination of ascorbic acid and uric acid using poly (glyoxal-bis (2-hydroxyanil)) modified glassy carbon electrode. Sens. Actuators B Chem. 2016, 224, 55–64. [Google Scholar] [CrossRef]
- Oliver, K.V.; Vilasi, A.; Maréchal, A.; Moochhala, S.H.; Unwin, R.J.; Rich, P.R. Infrared vibrational spectroscopy: A rapid and novel diagnostic and monitoring tool for cystinuria. Sci. Rep. 2016, 6, 34737. [Google Scholar] [CrossRef] [PubMed]
- Naseer, K.; Ali, S.; Qazi, J. ATR-FTIR spectroscopy as the future of diagnostics: A systematic review of the approach using bio-fluids. Appl. Spectrosc. Rev. 2021, 56, 85–97. [Google Scholar] [CrossRef]
- Caixeta, D.C.; Lima, C.; Xu, Y.; Guevara-Vega, M.; Espindola, F.S.; Goodacre, R.; Zezell, D.M.; Sabino-Silva, R. Monitoring glucose levels in urine using FTIR spectroscopy combined with univariate and multivariate statistical methods. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2023, 290, 122259. [Google Scholar] [CrossRef]
- Meza Ramirez, C.A.; Greenop, M.; Ashton, L.; Rehman, I.U. Applications of machine learning in spectroscopy. Appl. Spectrosc. Rev. 2021, 56, 733–763. [Google Scholar] [CrossRef]
- Iannucci, L. Chemometrics for data interpretation: Application of principal components analysis (pca) to multivariate spectroscopic measurements. IEEE Instrum. Meas. Mag. 2021, 24, 42–48. [Google Scholar] [CrossRef]
- Rodionova, O.; Kucheryavskiy, S.; Pomerantsev, A. Efficient tools for principal component analysis of complex data—A tutorial. Chemom. Intell. Lab. Syst. 2021, 213, 104304. [Google Scholar] [CrossRef]
- Rukundo, I.R.; Danao, M.G.C. Identifying turmeric powder by source and metanil yellow adulteration levels using near-infrared spectra and PCA-SIMCA modeling. J. Food Prot. 2020, 83, 968–974. [Google Scholar] [CrossRef]
- Sitnikova, V.E.; Kotkova, M.A.; Nosenko, T.N.; Kotkova, T.N.; Martynova, D.M.; Uspenskaya, M.V. Breast cancer detection by ATR-FTIR spectroscopy of blood serum and multivariate data-analysis. Talanta 2020, 214, 120857. [Google Scholar] [CrossRef]
- Wu, W.; Mallet, Y.; Walczak, B.; Penninckx, W.; Massart, D.; Heuerding, S.; Erni, F. Comparison of regularized discriminant analysis linear discriminant analysis and quadratic discriminant analysis applied to NIR data. Anal. Chim. Acta 1996, 329, 257–265. [Google Scholar] [CrossRef]
- Morais, C.L.; Martin-Hirsch, P.L.; Martin, F.L. A three-dimensional principal component analysis approach for exploratory analysis of hyperspectral data: Identification of ovarian cancer samples based on Raman microspectroscopy imaging of blood plasma. Analyst 2019, 144, 2312–2319. [Google Scholar] [CrossRef] [PubMed]
- Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification; John Wiley & Sons: Hoboken, NJ, USA, 2006. [Google Scholar]
- Eilers, P.H. A perfect smoother. Anal. Chem. 2003, 75, 3631–3636. [Google Scholar] [CrossRef] [PubMed]
- Rohman, A.; Windarsih, A.; Lukitaningsih, E.; Rafi, M.; Betania, K.; Fadzillah, N.A. The use of FTIR and Raman spectroscopy in combination with chemometrics for analysis of biomolecules in biomedical fluids: A review. Biomed. Spectrosc. Imaging 2019, 8, 55–71. [Google Scholar] [CrossRef]
- Giamougiannis, P.; Morais, C.L.; Rodriguez, B.; Wood, N.J.; Martin-Hirsch, P.L.; Martin, F.L. Detection of ovarian cancer (±neo-adjuvant chemotherapy effects) via ATR-FTIR spectroscopy: Comparative analysis of blood and urine biofluids in a large patient cohort. Anal. Bioanal. Chem. 2021, 413, 5095–5107. [Google Scholar] [CrossRef]
- Navarrete, J.L.; Hernández, V.; Ramirez, F. Ir and Raman spectra of L-aspartic acid and isotopic derivatives. Biopolym. Orig. Res. Biomol. 1994, 34, 1065–1077. [Google Scholar] [CrossRef]
- Khajehpour, M.; Dashnau, J.L.; Vanderkooi, J.M. Infrared spectroscopy used to evaluate glycosylation of proteins. Anal. Biochem. 2006, 348, 40–48. [Google Scholar] [CrossRef]
- Simonova, D.; Karamancheva, I. Application of Fourier transform infrared spectroscopy for tumor diagnosis. Biotechnol. Biotechnol. Equip. 2013, 27, 4200–4207. [Google Scholar] [CrossRef]
- Petrich, W. Mid-infrared and Raman spectroscopy for medical diagnostics. Appl. Spectrosc. Rev. 2001, 36, 181–237. [Google Scholar] [CrossRef]
- Skolik, P.; Morais, C.L.; Martin, F.L.; McAinsh, M.R. Attenuated total reflection fourier-transform infrared spectroscopy coupled with chemometrics directly detects pre-and post-symptomatic changes in tomato plants infected with botrytis cinerea. Vib. Spectrosc. 2020, 111, 103171. [Google Scholar] [CrossRef]
- Caixeta, D.C.; Aguiar, E.M.; Cardoso-Sousa, L.; Coelho, L.M.; Oliveira, S.W.; Espindola, F.S.; Raniero, L.; Crosara, K.T.; Baker, M.J.; Siqueira, W.L.; et al. Salivary molecular spectroscopy: A sustainable, rapid and non-invasive monitoring tool for diabetes mellitus during insulin treatment. PLoS ONE 2020, 15, e0223461. [Google Scholar] [CrossRef]
- Bernardes-Oliveira, E.; de Freitas, D.L.D.; de Morais, C.d.L.M.; Cornetta, M.d.C.d.M.; Camargo, J.D.d.A.S.; de Lima, K.M.G.; Crispim, J.C.d.O. Spectrochemical differentiation in gestational diabetes mellitus based on attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy and multivariate analysis. Sci. Rep. 2020, 10, 19259. [Google Scholar] [CrossRef] [PubMed]
Wavenumber (cm) | Tentative Assignment |
---|---|
978 | (C-C), -sheet of proteins (=) of lipids |
1015 | v(C-O), v(C-C), () |
1075 | P-O, , S=O stretching |
1154 | v(C-O) of proteins and carbohydrate |
1461 | bending |
1468 | (C-N) |
1564 | Amide II |
1587 | stretch |
1620 | (C-N) bending |
1643 | Amide I |
1662 | Amide I |
1755 | lipids |
Methods | PCA-LDA | 3D-PCA-LDA | |||
---|---|---|---|---|---|
Non-Diabetes | Diabetes | Non-Diabetes | Diabetes | ||
Testing | Non-Diabetes | 94% | 6% | 100% | 0% |
Diabetes | 1% | 99% | 0% | 100% | |
CV | Non-diabetes | 96% | 4% | 100% | 0% |
Diabetes | 1% | 99% | 0% | 100% |
Data Analysis | Methods | Accuracy | Sensitivity | Specificity |
---|---|---|---|---|
PCA-LDA | Test | 97% | 94% | ∼99% |
CV | 98% | 96% | ∼99% | |
3D-PCA-LDA | Test | 100% | 100% | 100% |
CV | 100% | 100% | 100% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Farooq, S.; Zezell, D.M. Diabetes Monitoring through Urine Analysis Using ATR-FTIR Spectroscopy and Machine Learning. Chemosensors 2023, 11, 565. https://doi.org/10.3390/chemosensors11110565
Farooq S, Zezell DM. Diabetes Monitoring through Urine Analysis Using ATR-FTIR Spectroscopy and Machine Learning. Chemosensors. 2023; 11(11):565. https://doi.org/10.3390/chemosensors11110565
Chicago/Turabian StyleFarooq, Sajid, and Denise Maria Zezell. 2023. "Diabetes Monitoring through Urine Analysis Using ATR-FTIR Spectroscopy and Machine Learning" Chemosensors 11, no. 11: 565. https://doi.org/10.3390/chemosensors11110565