Mental Condition Monitoring Based on Multimodality Biometry

Abstract

We have developed a system with multimodality that monitors objective biomarkers for screening the mental distress in the office. A field study using a prototype of the system was performed over four months with 39 volunteers. We obtained PC operation patterns using a PC logger, sleeping time and activity levels using a wrist-band-type activity tracker, and brain activity and behavior data during a working memory task using optical topography. We also administered two standard questionnaires: the Brief Job Stress Questionnaire (BJS) and the Kessler 6 scale (K6). Supervised machine learning and cross validation were performed. The objective variables were mental scores obtained from the questionnaires and the explanatory variables were the biomarkers obtained from the modalities. Multiple linear regression models for mental scores were comprehensively searched and the optimum models were selected from 2,619,785 candidates. Each mental score estimated with each optimum model was well correlated with each mental score obtained with the questionnaire (correlation coefficient = 0.6-0.8) within a 24% of estimation error. Mental scores obtained by means of questionnaires have been in general use in mental health care for a while, so our multimodality system is potentially useful for mental healthcare due to the quantitative agreement on the mental scores estimated with biomarkers and the mental scores obtained with questionnaires.

Keywords: PC logger; activity tracker; multimodality; multivariate linear regression; near-infrared spectroscopy (fNIRS).

Figure 1

Devices used for monitoring mental conditons: (A) PC logger, (B) Life Scope (LS), and (C) HOT-1000 optical topography (OT). (D) The data acquisition and database system.

Figure 2

Verbal and spatial delayed matching tasks for optical topography measurement. Four Japanese characters (hiragana) or four squares were displayed for 1.5 s on a tablet PC as a target in the verbal or spatial working memory task, respectively. After memory retention for 7.0 s, another Japanese character (katakana) or one square was shown as a probe. In the verbal task, participants were asked to click the circle button or the cross button displayed on the tablet PC when the probe character had the same pronunciation as one of the target characters or when it did not. In the spatial task, the agreement of the position between the probe and one of the targets was answered in the same way.

Figure 3

Comparison of mental scores and values estimated using optimized multivariate linear regression model.

Figure 4

Coefficients of variation of mean squared errors (mse) across participants for the target variables.