This study reports on the successful use of a machine learning approach using attenuated total reflectance Fourier transform infrared (ATR FT-IR) spectroscopy for the classification and prediction of a donor's sex from the fingernails of 63 individuals. A significant advantage of ATR FT-IR is its ability to provide a specific spectral signature for different samples based on their biochemical composition. The infrared spectrum reveals unique vibrational features of a sample based on the different absorption frequencies of the individual functional groups. This technique is fast, simple, non-destructive, and requires only small quantities of measured material with minimal-to-no sample preparation. However, advanced multivariate techniques are needed to elucidate multiplex spectral information and the small differences caused by donor characteristics. We developed an analytical method using ATR FT-IR spectroscopy advanced with machine learning (ML) based on 63 donors' fingernails (37 males, 26 females). The PLS-DA and ANN models were established, and their generalization abilities were compared. Here, the PLS scores from the PLS-DA model were used for an artificial neural network (ANN) to create a classification model. The proposed ANN model showed a greater potential for predictions, and it was validated against an independent dataset, which resulted in 92% correctly classified spectra. The results of the study are quite impressive, with 100% accuracy achieved in correctly classifying donors as either male or female at the donor level. Here, we underscore the potential of ML algorithms to leverage the selectivity of ATR FT-IR spectroscopy and produce predictions along with information about the level of certainty in a scientifically defensible manner. This proof-of-concept study demonstrates the value of ATR FT-IR spectroscopy as a forensic tool to discriminate between male and female donors, which is significant for forensic applications.

Cannabis Facility International Clinical Research Centre St Anne's University Hospital 602 00 Brno Czech Republic

Department of Environmental Toxicology Texas Tech University Lubbock TX 79409 USA

Department of Natural Drugs Faculty of Pharmacy Masaryk University 612 00 Brno Czech Republic

Zobrazit více v PubMed

Parmar P., Rathod G.B. Forensic Onychology: An essential entity against crime. J. Indian Acad. Forensic Med. 2012;34:355–357.

Parabon Snapshot D. Phenotyping Service—Powered by Parabon NanoLabs. Parabon NanoLabs; Reston, VA, USA: 2017.

Suzuki O., Hattori H., Asano M. Nails as useful materials for detection of methamphetamine or amphetamine abuse. Forensic Sci. Int. 1984;24:9–16. doi: 10.1016/0379-0738(84)90146-4. PubMed DOI

Lander H., Hodge P.R., Crisp C.S. Arsenis in the Hair and Nails: Its Significance in Acute Arsenical Poisoning. J. Forensic Med. 1965;12:52–67. PubMed

Mitu B., Cerda M., Hrib R., Trojan V., Halámková L. Attenuated Total Reflection Fourier Transform Infrared Spectroscopy for Forensic Screening of Long-Term Alcohol Consumption from Human Nails. ACS Omega. 2023;8:22203–22210. doi: 10.1021/acsomega.3c02579. PubMed DOI PMC

Toprak S., Kahriman F., Dogan Z., Ersoy G., Can E.Y., Akpolat M., Can M. The potential of Raman and FT-IR spectroscopic methods for the detection of chlorine in human nail samples. Forensic Sci. Med. Pathol. 2020;16:633–640. doi: 10.1007/s12024-020-00313-5. PubMed DOI

Grover C., Bansal S. The nail as an investigative tool in medicine: What a dermatologist ought to know. Indian J. Dermatol. Venereol. Leprol. 2017;83:635–643. doi: 10.4103/ijdvl.IJDVL_1050_16. PubMed DOI

Sharma A., Verma R., Kumar R., Chauhan R., Sharma V. Chemometric analysis of ATR-FTIR spectra of fingernail clippings for classification and prediction of sex in forensic context. Microchem. J. 2020;159:105504. doi: 10.1016/j.microc.2020.105504. DOI

Daniel C.R., III, Piraccini B.M., Tosti A. The nail and hair in forensic science. J. Am. Acad. Dermatol. 2004;50:258–261. doi: 10.1016/j.jaad.2003.06.008. PubMed DOI

Widjaja E., Lim G.H., An A. A novel method for human gender classification using Raman spectroscopy of fingernail clippings. Analyst. 2008;133:493–498. doi: 10.1039/b712389b. PubMed DOI

Liu G.-L., Kazarian S.G. Recent advances and applications to cultural heritage using ATR-FTIR spectroscopy and ATR-FTIR spectroscopic imaging. Analyst. 2022;147:1777–1797. doi: 10.1039/D2AN00005A. PubMed DOI

Dittmar M., Dindorf W., Banerjee A. Organic elemental composition in fingernail plates varies between sexes and changes with increasing age in healthy humans. Gerontology. 2008;54:100–105. doi: 10.1159/000128269. PubMed DOI

Sukumar A. Human nails as a biomarker of element exposure. In: Ware G.W., Nigg H.N., Doerge D.R., editors. Reviews of Environmental Contamination and Toxicology. Volume 185. Springer; New York, NY, USA: 2005. pp. 141–177.

Baswan S., Kasting G.B., Li S.K., Wickett R., Adams B., Eurich S., Schamper R. Understanding the formidable nail barrier: A review of the nail microstructure, composition and diseases. Mycoses. 2017;60:284–295. doi: 10.1111/myc.12592. PubMed DOI PMC

Park M.S., Kwon K.H. A Comparative Analysis of Major Mineral Contents of Nails by Gender in Adolescents. Korean J. Aesthet. Cosmetol. 2014;12:837–843.

Rodushkin I., Axelsson M.D. Application of double focusing sector field ICP-MS for multielemental characterization of human hair and nails. Part I. Analytical methodology. Sci. Total Environ. 2000;250:83–100. doi: 10.1016/S0048-9697(00)00369-7. PubMed DOI

Benzeval I., Bowen C.R., Guy R.H., Delgado-Charro M.B. Effects of iontophoresis, hydration, and permeation enhancers on human nail plate: Infrared and impedance spectroscopy assessment. Pharm. Res. 2013;30:1652–1662. doi: 10.1007/s11095-013-1010-y. PubMed DOI

Muddasani S., Lin G., Hooper J., Sloan S.B. Nutrition and nail disease. Clin. Dermatol. 2021;39:819–828. doi: 10.1016/j.clindermatol.2021.05.009. PubMed DOI

Brzózka P., Kolodziejski W. Sex-related chemical differences in keratin from fingernail plates: A solid-state carbon-13 NMR study. Rsc Adv. 2017;7:28213–28223. doi: 10.1039/C7RA03487C. DOI

He K. Trace elements in nails as biomarkers in clinical research. Eur. J. Clin. Investig. 2011;41:98–102. doi: 10.1111/j.1365-2362.2010.02373.x. PubMed DOI PMC

Coopman R., Van de Vyver T., Kishabongo A.S., Katchunga P., Van Aken E.H., Cikomola J., Monteyne T., Speeckaert M.M., Delanghe J.R. Glycation in human fingernail clippings using ATR-FTIR spectrometry, a new marker for the diagnosis and monitoring of diabetes mellitus. Clin. Biochem. 2017;50:62–67. doi: 10.1016/j.clinbiochem.2016.09.001. PubMed DOI

Jurgeleviciene I., Stanislovaitiene D., Tatarunas V., Jurgelevicius M., Zaliuniene D. Assessment of absorption of glycated nail proteins in patients with diabetes mellitus and diabetic retinopathy. Medicina. 2020;56:658. doi: 10.3390/medicina56120658. PubMed DOI PMC

Farhan K.M., Sastry T.P., Mandal A.B. Comparative study on secondary structural changes in diabetic and non-diabetic human finger nail specimen by using FTIR spectra. Clin. Chim. Acta. 2011;412:386–389. doi: 10.1016/j.cca.2010.11.016. PubMed DOI

Sakudo A., Kuratsune H., Kato Y.H., Ikuta K. Secondary structural changes of proteins in fingernails of chronic fatigue syndrome patients from Fourier-transform infrared spectra. Clin. Chim. Acta. 2009;402:75–78. doi: 10.1016/j.cca.2008.12.020. PubMed DOI

Al-Jorani K., Rüther A., Martin M., Haputhanthri R., Deacon G.B., Li H.L., Wood B.R. The application of ATR-FTIR spectroscopy and the reversible DNA conformation as a sensor to test the effectiveness of platinum (II) anticancer drugs. Sensors. 2018;18:4297. doi: 10.3390/s18124297. PubMed DOI PMC

Vigano C., Ruysschaert J.-M., Goormaghtigh E. Sensor applications of attenuated total reflection infrared spectroscopy. Talanta. 2005;65:1132–1142. doi: 10.1016/j.talanta.2004.07.052. PubMed DOI

Mizaikoff B. Peer reviewed: Mid-IR fiber-optic sensors. Anal. Chem. 2003;75:258A–267A. doi: 10.1021/ac031340g. PubMed DOI

Rigler P., Ulrich W.P., Hoffmann P., Mayer M., Vogel H. Reversible immobilization of peptides: Surface modification and in situ detection by attenuated total reflection FTIR spectroscopy. ChemPhysChem. 2003;4:268–275. doi: 10.1002/cphc.200390043. PubMed DOI

Lucena R., Cárdenas S., Gallego M., Valcárcel M. ATR-FTIR membrane-based sensor for the simultaneous determination of surfactant and oil total indices in industrial degreasing baths. Analyst. 2006;131:415–421. doi: 10.1039/B515163E. PubMed DOI

Srivastava R., Mallick P.K., Rautaray S.S., Pandey M. Computational Intelligence for Machine Learning and Healthcare Informatics. Volume 1 Walter de Gruyter GmbH & Co KG; Berlin, Germany: Boston, MA, USA: 2020.

Alzubaidi L., Zhang J., Humaidi A.J., Al-Dujaili A., Duan Y., Al-Shamma O., Santamaría J., Fadhel M.A., Al-Amidie M., Farhan L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data. 2021;8:53. doi: 10.1186/s40537-021-00444-8. PubMed DOI PMC

Günther F., Fritsch S. neuralnet: Training of Neural Networks. R J. 2010;2:30–38. doi: 10.32614/RJ-2010-006. DOI

Robin X., Turck N., Hainard A., Tiberti N., Lisacek F., Sanchez J.-C., Müller M. pROC: An open-source package for R and S+ to analyze and compare ROC curves. BMC Bioinform. 2011;12:77. doi: 10.1186/1471-2105-12-77. PubMed DOI PMC

Baker M.J., Hussain S.R., Lovergne L., Untereiner V., Hughes C., Lukaszewski R.A., Thiéfin G., Sockalingum G.D. Developing and understanding biofluid vibrational spectroscopy: A critical review. Chem. Soc. Rev. 2016;45:1803–1818. doi: 10.1039/C5CS00585J. PubMed DOI

Balki I., Amirabadi A., Levman J., Martel A.L., Emersic Z., Meden B., Garcia-Pedrero A., Ramirez S.C., Kong D., Moody A.R., et al. Sample-Size Determination Methodologies for Machine Learning in Medical Imaging Research: A Systematic Review. Can. Assoc. Radiol. J. 2019;7:344–353. doi: 10.1016/j.carj.2019.06.002. PubMed DOI

Rutledge D.N., Roger J.-M., Lesnoff M. Different Methods for Determining the Dimensionality of Multivariate Models. Front. Anal. Sci. 2021;1:754447. doi: 10.3389/frans.2021.754447. DOI

Mendez K.M., Reinke S.N., Broadhurst D.I. A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification. Metabolomics. 2019;15:150. doi: 10.1007/s11306-019-1612-4. PubMed DOI PMC

Riedmiller M. Advanced supervised learning in multi-layer perceptrons—From backpropagation to adaptive learning algorithms. Comput. Stand. Interfaces. 1994;16:265–278. doi: 10.1016/0920-5489(94)90017-5. DOI

Diago M.P., Fernández-Novales J., Gutiérrez S., Marañón M., Tardaguila J. Development and Validation of a New Methodology to Assess the Vineyard Water Status by On-the-Go Near Infrared Spectroscopy. Front. Plant Sci. 2018;9:59. doi: 10.3389/fpls.2018.00059. PubMed DOI PMC

Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer; Berlin/Heidelberg, Germany: 2009. p. 764.

Wang B., Yang W., McKittrick J., Meyers M.A. Keratin: Structure, mechanical properties, occurrence in biological organisms, and efforts at bioinspiration. Prog. Mater. Sci. 2016;76:229–318. doi: 10.1016/j.pmatsci.2015.06.001. DOI

Barton P.M. Ph.D. Thesis. Queensland University of Technology; Brisbane City, Australia: 2011. A Forensic Investigation of Single Human Hair Fibres Using FTIR-ATR Spectroscopy and Chemometrics.

Al-Hetlani E., Halámková L., Amin M.O., Lednev I.K. Differentiating smokers and nonsmokers based on Raman spectroscopy of oral fluid and advanced statistics for forensic applications. J. Biophotonics. 2020;13:e201960123. doi: 10.1002/jbio.201960123. PubMed DOI

Golik P., Doetsch P., Ney H. Cross-Entropy vs. Squared Error Training: A Theoretical and Experimental Comparison. Interspeech; Dublin, Ireland: 2013.

Biancolillo A., Marini F., Ruckebusch C., Vitale R. Chemometric strategies for spectroscopy-based food authentication. Appl. Sci. 2020;10:6544. doi: 10.3390/app10186544. DOI

Takamura A., Halámková L., Ozawa T., Lednev I.K. Phenotype Profiling for Forensic Purposes: Determining Donor Sex Based on Fourier Transform Infrared Spectroscopy of Urine Traces. Anal. Chem. 2019;91:6288–6295. doi: 10.1021/acs.analchem.9b01058. PubMed DOI

Berrueta L.A., Alonso-Salces R.M., Héberger K. Supervised pattern recognition in food analysis. J. Chromatogr. A. 2007;1158:196–214. doi: 10.1016/j.chroma.2007.05.024. PubMed DOI

Montesinos López O.A., Montesinos López A., Crossa J. Fundamentals of Artificial Neural Networks and Deep Learning. In: Montesinos López O.A., Montesinos López A., Crossa J., editors. Multivariate Statistical Machine Learning Methods for Genomic Prediction. Springer International Publishing; Cham, Switzerland: 2022. pp. 379–425. PubMed

Song K., Li L., Li S., Tedesco L.P., Duan H., Li Z., Shi K., Du J., Zhao Y., Shao T. Using Partial Least Squares-Artificial Neural Network for Inversion of Inland Water Chlorophyll-a. Geosci. Remote Sens. IEEE Trans. 2014;52:1502–1517. doi: 10.1109/TGRS.2013.2251888. DOI

Lavine B.K., Workman J., Jr. Chemometrics: Past, Present, and Future. ACS Publications; Washington, DC, USA: 2005. (ACS Symposium Series).

Lavine B., Workman J. Chemometrics. Anal. Chem. 2008;80:4519–4531. doi: 10.1021/ac800728t. PubMed DOI

Ralbovsky N.M., Halámková L., Wall K., Anderson-Hanley C., Lednev I.K. Screening for Alzheimer’s Disease Using Saliva: A New Approach Based on Machine Learning and Raman Hyperspectroscopy. J. Alzheimers Dis. 2019;71:1351–1359. doi: 10.3233/JAD-190675. PubMed DOI

Krogh A. What are artificial neural networks? Nat. Biotechnol. 2008;26:195–197. doi: 10.1038/nbt1386. PubMed DOI

From Spectra to Signatures: Detecting Fentanyl in Human Nails with ATR-FTIR and Machine Learning