Salivary ATR-FTIR Spectroscopy Coupled with Support Vector Machine Classification for Screening of Type 2 Diabetes Mellitus

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.

[1]  L.F.C.S. Carvalho,et al.  FTIR spectroscopy as a point of care diagnostic tool for diabetes and periodontitis: a saliva analysis approach. , 2022, Photodiagnosis and photodynamic therapy.

[2]  H. Anahideh,et al.  Explainable Predictive Modeling for Limited Spectral Data , 2022, Chemometrics and Intelligent Laboratory Systems.

[3]  D. Paul,et al.  Haemoprocessor: A Portable Platform Using Rapid Acoustically Driven Plasma Separation Validated by Infrared Spectroscopy for Point-of-Care Diagnostics , 2022, Biosensors.

[4]  G. Minas,et al.  Fourier Transform Infrared (FTIR) Spectroscopy to Analyse Human Blood over the Last 20 Years: A Review towards Lab-on-a-Chip Devices , 2022, Micromachines.

[5]  James M. Cameron,et al.  Clinical Spectroscopy: Lost in Translation? , 2021, Applied spectroscopy.

[6]  M. M. Mata-Miranda,et al.  A machine-learning strategy to evaluate the use of FTIR spectra of saliva for a good control of type 2 diabetes. , 2021, Talanta.

[7]  C. Toumazou,et al.  Assessing a novel, lab-free, point-of-care test for SARS-CoV-2 (CovidNudge): a diagnostic accuracy study , 2020, The Lancet Microbe.

[8]  Camilo L. M. Morais,et al.  Spectrochemical analysis in blood plasma combined with subsequent chemometrics for fibromyalgia detection , 2020, Scientific Reports.

[9]  E. Pięta,et al.  Saliva as a first-line diagnostic tool: A spectral challenge for identification of cancer biomarkers , 2020, Journal of Molecular Liquids.

[10]  Anam Azhar,et al.  A systematic review on clinical implication of continuous glucose monitoring in diabetes management , 2020, Journal of pharmacy & bioallied sciences.

[11]  K. Crosara,et al.  Salivary molecular spectroscopy: A sustainable, rapid and non-invasive monitoring tool for diabetes mellitus during insulin treatment , 2020, PloS one.

[12]  David J. Anderson,et al.  Biofluid Diagnostics by FTIR Spectroscopy: A Platform Technology for Cancer Detection. , 2020, Cancer letters.

[13]  L. Goulart,et al.  Attenuated Total Reflection-Fourier Transform Infrared (ATR-FTIR) Spectroscopy Analysis of Saliva for Breast Cancer Diagnosis , 2020, Journal of oncology.

[14]  2. Classification and Diagnosis of Diabetes: Standards of Medical Care in Diabetes—2020 , 2019, Diabetes Care.

[15]  James M. Cameron,et al.  Development of high-throughput ATR-FTIR technology for rapid triage of brain cancer , 2019, Nature Communications.

[16]  Matthew J. Baker,et al.  Is Infrared Spectroscopy Ready for the Clinic? , 2019, Analytical chemistry.

[17]  Dimitris Tousoulis,et al.  The Role of Inflammation in Diabetes: Current Concepts and Future Perspectives , 2018, European cardiology.

[18]  Wenfeng Xu,et al.  New insights into oxidative stress and inflammation during diabetes mellitus-accelerated atherosclerosis , 2018, Redox biology.

[19]  R. Naseri,et al.  Effect of diabetes mellitus type 2 on salivary glucose, immunoglobulin A, total protein, and amylase levels in adults: A systematic review and meta-analysis of case–control studies , 2018, Journal of research in medical sciences : the official journal of Isfahan University of Medical Sciences.

[20]  Jürgen Popp,et al.  Application of Vibrational Spectroscopy and Imaging to Point-of-Care Medicine: A Review , 2018, Applied spectroscopy.

[21]  Hyung-Ryong Kim,et al.  Compliance with Saliva Collection Protocol in Healthy Volunteers: Strategies for Managing Risk and Errors , 2018, International journal of medical sciences.

[22]  Marilyn A. Corbin,et al.  Outcomes and Economic Benefits of Penn State Extension’s Dining With Diabetes Program , 2018, Preventing chronic disease.

[23]  Dermot Diamond,et al.  Glucose Sensing for Diabetes Monitoring: Recent Developments , 2017, Sensors.

[24]  R. Shaw,et al.  Application of laboratory and portable attenuated total reflectance infrared spectroscopic approaches for rapid quantification of alpaca serum immunoglobulin G , 2017, PloS one.

[25]  N. Maruthur,et al.  The Case for Diabetes Population Health Improvement: Evidence-Based Programming for Population Outcomes in Diabetes , 2017, Current Diabetes Reports.

[26]  F. Alsaraj Pathogenesis of Type 2 Diabetes Mellitus , 2015 .

[27]  Tiinamaija Tuomi,et al.  The many faces of diabetes: a disease with increasing heterogeneity , 2014, The Lancet.

[28]  Nirmal Singh,et al.  Advanced Glycation End Products and Diabetic Complications , 2014, The Korean journal of physiology & pharmacology : official journal of the Korean Physiological Society and the Korean Society of Pharmacology.

[29]  M. Okamoto,et al.  Increased SGLT1 expression in salivary gland ductal cells correlates with hyposalivation in diabetic and hypertensive rats , 2013, Diabetology & Metabolic Syndrome.

[30]  Francis L Martin,et al.  Fourier-transform infrared spectroscopy coupled with a classification machine for the analysis of blood plasma or serum: a novel diagnostic approach for ovarian cancer. , 2013, The Analyst.

[31]  M. Cooper,et al.  Mechanisms of diabetic complications. , 2013, Physiological reviews.

[32]  M. Dittrich,et al.  Fourier transform infrared spectroscopy for molecular analysis of microbial cells. , 2012, Methods in molecular biology.

[33]  Claudio Sorio,et al.  Infrared spectroscopy and microscopy in cancer research and diagnosis. , 2012, American journal of cancer research.

[34]  Å. Lernmark,et al.  Guidelines and Recommendations for Laboratory Analysis in the Diagnosis and Management of Diabetes Mellitus , 2002, Diabetes Care.

[35]  Kan-Zhi Liu,et al.  Diabetes-related molecular signatures in infrared spectra of human saliva , 2010, Diabetology & metabolic syndrome.

[36]  J. Greener,et al.  Attenuated total reflection Fourier transform infrared spectroscopy for on-chip monitoring of solute concentrations. , 2010, Lab on a chip.

[37]  S. Rehman,et al.  Fourier Transform Infrared (FTIR) Spectroscopy of Biological Tissues , 2008 .

[38]  Martyn Poliakoff,et al.  Sustainable technology: Green chemistry , 2007, Nature.

[39]  T. Dudley,et al.  Screening for diabetes in an outpatient clinic population , 2007, Journal of General Internal Medicine.

[40]  C. Palmeira,et al.  Diabetes and mitochondrial function: role of hyperglycemia and oxidative stress. , 2006, Toxicology and applied pharmacology.

[41]  Brenda Eskenazi,et al.  Biological sample collection and processing for molecular epidemiological studies. , 2003, Mutation research.

[42]  E. Goormaghtigh,et al.  Attenuated total reflection infrared spectroscopy of proteins and lipids in biological membranes. , 1999, Biochimica et biophysica acta.