Search

A schizophrenia relapse has severe consequences for a patient’s health, work, and sometimes even life safety. If an oncoming relapse can be predicted on time, for example by detecting early behavioral changes in patients, then interventions could be provided to prevent the relapse. In this work, we investigated a machine learning based schizophrenia relapse prediction model using mobile sensing data to characterize behavioral features. A patient-independent model providing sequential predictions, closely representing the clinical deployment scenario for relapse prediction, was evaluated. The model uses the mobile sensing data from the recent four weeks to predict an oncoming relapse in the next week. We used the behavioral rhythm features extracted from daily templates of mobile sensing data, self-reported symptoms collected via EMA (Ecological Momentary Assessment), and demographics to compare different classifiers for the relapse prediction. Naive Bayes based model gave the best results with an F2 score of 0.083 when evaluated in a dataset consisting of 63 schizophrenia patients, each monitored for up to a year. The obtained F2 score, though low, is better than the baseline performance of random classification (F2 score of 0.02 ± 0.024). Thus, mobile sensing has predictive value for detecting an oncoming relapse and needs further investigation to improve the current performance. Towards that end, further feature engineering and model personalization based on the behavioral idiosyncrasies of a patient could be helpful.

Schizophrenia is a severe psychiatric disorder. We use the CrossCheck study dataset to develop methods to predict whether or not a patient with schizophrenia is going to relapse from mobile phone data. Out of 75 patients in the year long randomized controlled trial only 27 relapse episodes occur. We apply various techniques to address predicting rare events in a longitudinal dataset. We apply resampling methods combining oversampling relapse examples and undersampling non-relapse examples and impute missing data. To avoid overfitting, we apply feature selection and transformation (i.e., PCA) to reduce the feature dimensionality. We find the best relapse prediction result using the first 100 principal components from both passive sensing and self-reports with 30-day prediction windows (precision=26.8%, recall=28.4%). If we demand the recall to be greater than 50%, we find the best result using 25 principle components from both passive sensing and self-reports with 30-day prediction windows (precision=15.4%, recall=51.6%).

We propose "SmileWave", the first selfie social networking service to reveal the existence of emotional cognation through smiling selfies on the social network. We conducted multiple rounds of in-the-wild user studies with 86 cumulative total users for total duration of 5 weeks. Throughout the entire study, we confirmed the occurrence of smile-based emotional contagion over social network, not only in the momentary duration but in longer term period.

Investigating users' interruptibility as an indicator of his/her attention status has been essential in recent pervasive computing where the users' attention resources get scarce against ever increasing amounts of information. In this paper, we address research problems related to the users' available interruptibility, their physical activities, and their current locations and situations. We propose the “Interruptibility Map”, a geographical tool for analyzing and visualizing the user's local interruptibility status in the context of smart city research. Our map describes where citizens are expected to feel more or less interruptive against notifications produced by computing devices, which are known to have negative effects on work productivity, emotion, and psychological state. We conducted a continuous analysis from our previous research and a new additional in-the-wild user study for 2 weeks with 29 participants to investigate the relationship between one's interruptibility and their locations and situations. As a highlight of our findings, we found certain pairs of user activity change and a location that showed better interruptibility to users, such as an activity change of “when user's riding car(bus) stops” in the bus commute situation.