Keio University

Liang Kuo-ching

Takanori Fujita

Taishiro Kishimoto

Michitaka Yoshimura

Momoko Kitazawa

Yuki Tazawa

Masaru Mimura

A method for predicting a depressive state using a wearable device. Each data type of biological data for several days from plurality of subjects is converted into data in predetermined time unit (S). Next, quantiles of the distribution of obtained sample data are determined for each subject and each data type (S). The standard deviation of distribution of the obtained sample data is calculated for each subject and each data type (S). The Pearson correlation coefficient is calculated for each combination of data types for each subject (S). Next, a prediction model for the classification problem of whether subject is in a depressive state is trained by machine leaning (S), wherein quantiles, standard deviations, and Pearson correlation coefficients extracted from the biological data are features used for an input vector, and an evaluation of existence or non-existence of a depressive state by an expert is a label used as teacher data.

Growing community of inventors

Shinjuku-ku, Japan

Liang Kuo-ching