How are you feeling?: A personalized methodology for predicting mental states from temporally observable physical and behavioral information

Abstract

It is believed that anomalous mental states such as stress and anxiety not only cause suffering for the individuals, but also lead to tragedies in some extreme cases. The ability to predict the mental state of an individual at both current and future time periods could prove critical to healthcare practitioners. Currently, the practical way to predict an individual's mental state is through mental examinations that involve psychological experts performing the evaluations. However, such methods can be time and resource consuming, mitigating their broad applicability to a wide population. Furthermore, some individuals may also be unaware of their mental states or may feel uncomfortable to express themselves during the evaluations. Hence, their anomalous mental states could remain undetected for a prolonged period of time. The objective of this work is to demonstrate the ability of using advanced machine learning based approaches to generate mathematical models that predict current and future mental states of an individual. The problem of mental state prediction is transformed into the time series forecasting problem, where an individual is represented as a multivariate time series stream of monitored physical and behavioral attributes. A personalized mathematical model is then automatically generated to capture the dependencies among these attributes, which is used for prediction of mental states for each individual. In particular, we first illustrate the drawbacks of traditional multivariate time series forecasting methodologies such as vector autoregression. Then, we show that such issues could be mitigated by using machine learning regression techniques which are modified for capturing temporal dependencies in time series data. A case study using the data from 150 human participants illustrates that the proposed machine learning based forecasting methods are more suitable for high-dimensional psychological data than the traditional vector autoregressive model in terms of both magnitude of error and directional accuracy. These results not only present a successful usage of machine learning techniques in psychological studies, but also serve as a building block for multiple medical applications that could rely on an automated system to gauge individuals' mental states.

Keywords: Machine learning; Mental state prediction; Multivariate time series.

Figure 1

The high-level diagram of the methodology.

Figure 2

Illustration of the three bursts during which the data was collected.

Figure 3

Distribution of the Positive Affect (PosAffect_d) attribute of the 150 participants. The Y axis marks the level (0 to 100), and the X axis represents ages in years of the participants. Each line/color is corresponding to a participant. Each dot represents a daily positive effect level.

Figure 4

(Left) Comparison of example forecasting results by RF with different horizons (i.e. h = 0, 1, 2, 3) against the actual values of the attribute S AT LIFE d of a participant. (Right) Comparison of absolute error of each horizon (i.e. h = 0, 1, 2, 3).

Figure 5

Comparison of average mean absolute error (MAE) with error bars showing standard errors, produced by Random Forest forecasters trained with different information sources (i.e. OU = both observable and latent information, O = only observable information, U = only latent information) at each horizon (days ahead of prediction). Each prediction is an average of prediction using different lags (i.e. lags = 1, 3, 5, and 7). Each attribute value has a range of [0, 100].

Figure 6

Comparison of directional accuracy (DAC), range between [0, 1], produced by Random Forest forecaster trained with different information sources (i.e. OU = both observable and latent information, O = only observable information, U = only latent information) at each horizon (days ahead of prediction). Each prediction is an average of prediction using different lags (i.e. lags = 1, 3, 5, and 7).