Age group classification based on optical measurement of brain pulsation using machine learning

• Published in: Scientific reports Vol. 15; no. 1; pp. 3166 - 15
• Main Authors: Ilvesmäki, Martti, Ferdinando, Hany, Noponen, Kai, Seppänen, Tapio, Korhonen, Vesa, Kiviniemi, Vesa, Myllylä, Teemu
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 25.01.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/985; 639/624/1075; Accuracy; Adult; Age Factors; Age groups; Aged; Aging; Aging - physiology; Brain - blood supply; Brain - diagnostic imaging; Brain - physiology; Brain research; Cerebrovascular Circulation - physiology; Classification; Feature selection; Female; Functional magnetic resonance imaging; Geriatrics; Hemodynamics; Humanities and Social Sciences; Humans; Infrared spectroscopy; Learning algorithms; Learning curves; Machine Learning; Magnetic Resonance Imaging; Male; Measurement techniques; Middle Aged; multidisciplinary; Neuroimaging; Older people; Principal components analysis; Sample size; Science; Science (multidisciplinary); Spectroscopy, Near-Infrared - methods; Spectrum analysis; Support Vector Machine; Veins & arteries; Young Adult
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-87645-w

Optical techniques, such as functional near-infrared spectroscopy (fNIRS), contain high potential for the development of non-invasive wearable systems for evaluating cerebral vascular condition in aging, due to their portability and ability to monitor real-time changes in cerebral hemodynamics. In this study, thirty-six healthy adults were measured by single channel fNIRS to explore differences between two age groups using machine learning (ML). The subjects, measured during functional magnetic resonance imaging (fMRI) at Oulu University Hospital, were divided into young (age ≤ 32) and elderly (age ≥ 57) groups. Brain pulses were extracted from fNIRS using a single 830 nm wavelength. Four feature sets were derived from log-normal parameters estimated by pulse decomposition algorithm. ML experiments utilized support vector machines and random forest learners, along with maximum relevance minimum redundancy and principal component analysis for feature selection. Performance with increasing sample size was estimated using learning curve method. The best mean balanced accuracies for each feature set were over 75% (75.9%, 76.4%, 79.3%, 76.9%), indicating the pulse features containing age related information. Learning curves indicated stable classification performance with increasing sample size. The results demonstrate the potential of using single channel fNIRS in the analysis of aging.