Saliva FTIR Spectra and Machine Learning for Autism Spectrum Disorder Diagnosis-Preliminary Study
Data
Título da Revista
ISSN da Revista
Título de Volume
Editor
Resumo
The diagnosis of Autism Spectrum Disorder (ASD) remains a challenge due to the lack of specific tests and biological markers. ASD is a neurodevelopmental disorder that affects in- dividuals throughout their lives, and its diagnosis allows access to treatments that improve their prognosis. Saliva analysis by Fourier Transform Infrared Spectroscopy (FTIR), which was not previ- ously reported, appears to be a promising diagnostic tool for ASD. This study acquired spectra from samples of 19 ASD and 19 control children. Spectral signatures suggest the dominance of protein secondary structures, β-pleated sheet and α-helix structures in ASD and control children, respectively. Support Vector Machine (SVM) gave the best diagnosis, with sensitivity, precision, and specificity being 92%, 94%, and 95%, respectively. Shapley values analysis to understand the impact of spectral features on the SVM classifier identified β-pleated and β-turn sheets as responsible for classification. Results indicate the potential of saliva-based FTIR for autism diagnosis, warranting a large-scale trial.