JTEHM presents

A Bayesian Algorithm for Anxiety Index Prediction Based on Cerebral Blood Oxygenation in the Prefrontal Cortex Measured by Near Infrared Spectroscopy

Published Articles

Stress-induced psychological and somatic diseases are virtually endemic nowadays. Written self-report anxiety measures are available; however, these indices tend to be time consuming to acquire. For medical patients, completing written reports can be burdensome if they are weak, in pain, or in acute anxiety states. Consequently, simple and fast non-invasive methods for assessing stress response from neurophysiological data are essential. In this paper, we report on a study that makes predictions of the state-trait anxiety inventory (STAI) index from oxy and deoxy hemoglobin concentration changes of the prefrontal cortex (PFC) using a two-channel portable near-infrared spectroscopy (NIRS) device. Predictions are achieved by constructing machine learning algorithms within a Bayesian framework with nonlinear basis function together with Markov Chain Monte Carlo (MCMC) implementation. In the study, prediction experiments were performed against four different datasets, two comprising young subjects, and the remaining two comprising elderly subjects. The number of subjects in each dataset varied between 17 and 20 and each subject participated only once. They were not asked to perform any task; instead, they were at rest. The root mean square errors for the four groups were 6.20, 6.62, 4.50, and 6.38 respectively. There appeared to be no significant distinctions of prediction accuracies between age groups and since the STAI are defined between 20 and 80, the predictions appeared reasonably accurate. The results indicate potential applications to practical situations such as stress management and medical practice.
A Bayesian Algorithm for Anxiety Index Prediction Based on CerebralBlood Oxygenation in the Prefrontal Cortex Measured by Near Infrared Spectroscopy
View full article

Authors

See complete bios of the authors in the full version of this article.
Y FukudaY Fukuda
Mr. Fukuda received a B.E. degree from the Department of Electrical Engineering and Bioscience, Waseda University, Tokyo, Japan, and is currently pursuing an M.S. degree at the same institution. His current research interests include Bayesian machine learning for prediction problems with Monte Carlo implementations, using Near Infrared Spectroscopy data.

Y IdaY Ida
Mr. Ida received a B.E. degree from the Department of Electrical Engineering and Bioscience, Waseda University, Tokyo, Japan, and is currently pursuing an M.S. degree at the same institution. His current research interests include sentiment analysis and relational model by Bayesian method. He is working on handling relational data with side-information via Bayesian model.

T MatsumotoT Matsumoto
Dr. Matsumoto is a professor in the Faculty of Advanced Science and Engineering, Waseda University. He has had visiting positions at U.C. Berkeley and Cambridge University, U.K. His research interests are Bayesian machine learning with Monte Carlo implementations and Bootstrap method, with target data including biological data, image data, and time series data. He also has interests in non-parametric priors for Bayesian learning.

N TakemuraN Takemura
Mr. Takemura received a B.Sc. degree in engineering in 2003 and a M.Sc. degree in Informatics in 2005, from Kyoto University, Japan. He is currently a researcher in College of Engineering, Nihon University, Japan. His research interests include neuroscience and biomedical engineering.

K SakataniK Sakatani
Dr. Sakatani is a Professor at Nihon University College of Engineering and School of Medicine. He is also a Board-certified Neurosurgeon in Japan. His research interests include biomedical engineering, optical engineering, neuroimaging, and neuroscience.

Related Articles