Intersubject Variability in Cerebrovascular Hemodynamics and Systemic Physiology during a Verbal Fluency Task under Colored Light Exposure: Clustering of Subjects by Unsupervised Machine Learning

Abstract

There is large intersubject variability in cerebrovascular hemodynamic and systemic physiological responses induced by a verbal fluency task (VFT) under colored light exposure (CLE). We hypothesized that machine learning would enable us to classify the response patterns and provide new insights into the common response patterns between subjects. In total, 32 healthy subjects (15 men and 17 women, age: 25.5 ± 4.3 years) were exposed to two different light colors (red vs. blue) in a randomized cross-over study design for 9 min while performing a VFT. We used the systemic physiology augmented functional near-infrared spectroscopy (SPA-fNIRS) approach to measure cerebrovascular hemodynamics and oxygenation at the prefrontal cortex (PFC) and visual cortex (VC) concurrently with systemic physiological parameters. We found that subjects were suitably classified by unsupervised machine learning into different groups according to the changes in the following parameters: end-tidal carbon dioxide, arterial oxygen saturation, skin conductance, oxygenated hemoglobin in the VC, and deoxygenated hemoglobin in the PFC. With hard clustering methods, three and five different groups of subjects were found for the blue and red light exposure, respectively. Our results highlight the fact that humans show specific reactivity types to the CLE-VFT experimental paradigm.

Possible effect of natural light on emotion recognition and the prefrontal cortex: A scoping review of near-infrared (NIR) spectroscopy

“…83 However, interindividual differences can be the main plausible cause of varying results, as mentioned. [70][71][72] Blue light activates intrinsically photosensitive retinal ganglion cells (ipRGCs), and the signal is projected to several brain regions, including the ventral tegmental area, raphe and LC via the suprachiasmatic nucleus, to modulate circadian rhythms. 89 The ipRGCs do not form a vision, suggesting that even in blind people exposure to colored light may result in circadian modulation.…”

“…Due to the inhomogeneous signal processing methods, comparing oxy-Hb concentrations between studies would be inappropriate. In 4 studies, [70][71][72][73] the reported number, male/female proportion, standard deviation (SD), mean (M), and age ranges of participants were identical. In 1 study, a machine learning technique was used.…”

“…In 1 study, a machine learning technique was used. 71 However, although the machine learning technique is overused in various fields, artificial intelligence (AI) does not apply to small biased datasets. 74 Fig.…”

“…Wolf's research group extensively focused on the color of light and conducted 8 fNIRS studies in the years 2011-2022. [70][71][72][73]77,78,82,83 In 2011, they first investigated the effect of red and blue light on oxygen consumption in the brain and muscles of 10 participants. 77 Then, they exposed the 12 volunteers to these 2-colored lights sequentially to examine the hypothesis stating that red light enhances the effects of BL.…”

“…83 In 2021, followed by another SPA-fNIRS study to investigate the colored light effect (CLE) during a VFT, 73 Wolf's research group delved into the interindividual differences of hemodynamic responses and consecutively published 4 studies in January 2021, April 2021, May 2022, and October 2022. [70][71][72][73] Briefly, followed by performing a VFT under CLE, they patterned or clustered hemodynamic responses using various techniques, including unsupervised machine learning, 71 namely k-means.…”