Optimizing HSSE-GC-MS and Machine Learning for Forensic Gender Classification from Human Scent

Clothes are considered a valuable piece of evidence in forensic investigations because of the underlying information that can be extracted from them, such as human scent. Smell left behind on a clothing sample is an example of trace evidence that can be extracted from clothes to link a specific person or location to the crime. A joint study conducted by researchers from the University of Cádiz (Spain) and Goethe-University (Kennedyallee, Germany) optimized a headspace sorptive extraction (HSSE) method coupled with gas chromatography-mass spectrometry (GC-MS) in combination with machine learning for objective discrimination of gender from human scent traces on clothing for forensic applications. A paper based on their work was published in Analytica Chimica Acta.¹

Human clothing, among the assorted forms of evidence which can be collected at crime scenes, is considered especially useful because of its ability to retain a diverse array of information, such as physical, biological, and chemical traces.^2,3 Scent is a crucial type of trace evidence that can be extracted from clothing due to its ability to offer potential after analysis to connect a specific individual to a crime,⁴A complex chemical signature composed of volatile (VOCs) and semi-volatile organic compounds (SVOCs) that are primarily emitted from human skin, scent is affected by interactions with dead skin cells, air currents, and symbiotic bacteria.⁵ The human scent profile is accepted to be highly individualistic, transferable, and collectable, and offers the possibility for computerized database development, all of which being features of an ideal example of trace evidence.⁴

The research team optimized the HSSE using the Box-Behnken design and Response Surface Methodology to maximize the Euclidean distance between the total ion sum spectrum (TIS) of two independent samples. The optimized extraction parameters were determined at 100 °C extraction temperature, 180 min extraction time, and 5 × 5 cm cloth dimension at m/z range 101 - 250 which produced an R² of 0.9874. Method validation demonstrated an acceptable absolute error of 6.60%. Intra- and inter-day precisions were calculated for each m/z from 101 to 250 to remove outliers from the dataset for the multivariate analysis.¹

Using the optimized extraction method, 62 samples were analyzed and the pre-processed TIS from the samples were subjected to various supervised machine learning algorithms. Support vector machine (SVM) and partial least squares-discriminant analysis (PLS-DA) models achieved perfect 100% accuracy for gender classification in both training and test sets. Random forest (RF) and linear discriminant analysis (LDA) also showed high test set accuracies of 93% and 86%, respectively.¹

“Combining optimized stir bar HSSE-GC-MS with different machine learning algorithms using the TIS untargeted approach,’ write the authors of the study,¹ “provides a fast and automatic gender classification from human scent traces on clothes that can be used as a rapid screening technique in forensic investigations to narrow down suspect or victim profiles.”

Based on their results, the researchers suggest that future work build on these findings by expanding the sample size and increasing the population diversity, including varying habits, to further reinforce and generalize the observed patterns in this study.¹

Read More on Similar Topics
How Mass Spectrometry and Ambient Ionization Techniques Are Improving Drug Detection in Forensics

References

1. Mateo, J. M. C.; Calle, J. L. P.; Durán-Guerrero, E. et al. Optimized HSSE-GC-MS and Machine Learning for Forensic Gender Classification of Human Scent from Clothing. Anal Chim Acta 2026, 1400, 345337. DOI: 10.1016/j.aca.2026.345337
2. Taupin, J. M.; Cwiklik. C. Scientific Protocols for Forensic Examination of Clothing. CRC Press, 2010. DOI: 10.1201/b10381
3. V. Warrier, V.; T. Kanchan, T. Clothes and the Evidences They Carry: A Perspective on its Forensic Examination. J. Indian Acad. Forensic Med. 2021, 43 (3), 296-299. DOI: 10.5958/0974-0848.2021.00076.2
4. Procter, F. A.; Swindles, G. T.; Barlow, N. L. M. Examining the Transfer of Soils to Clothing Materials: Implications for Forensic Investigations. Forensic Sci. Int.2019, 305, 110030. DOI: 10.1016/j.forsciint.2019.110030
5. McQueen, R. H.; Eyres, G. T.; Laing, R. M. Textile Sorption and Release of Odorous Volatile Organic Compounds from a Synthetic Sweat Solution. Textil. Res. J.2024. DOI: 10.1177/00405175241249462