Analyzing the contribution of different passively collected data to predict Stress and Depression (2310.13607v1)
Abstract: The possibility of recognizing diverse aspects of human behavior and environmental context from passively captured data motivates its use for mental health assessment. In this paper, we analyze the contribution of different passively collected sensor data types (WiFi, GPS, Social interaction, Phone Log, Physical Activity, Audio, and Academic features) to predict daily selfreport stress and PHQ-9 depression score. First, we compute 125 mid-level features from the original raw data. These 125 features include groups of features from the different sensor data types. Then, we evaluate the contribution of each feature type by comparing the performance of Neural Network models trained with all features against Neural Network models trained with specific feature groups. Our results show that WiFi features (which encode mobility patterns) and Phone Log features (which encode information correlated with sleep patterns), provide significative information for stress and depression prediction.
- I. Perez-Pozuelo, D. Spathis, E. A. Clifton, and C. Mascolo, “Wearables, smartphones, and artificial intelligence for digital phenotyping and health,” in Digital Health. Elsevier, 2021.
- I. Moura, A. Teles, D. Viana, J. Marques, L. Coutinho, and F. Silva, “Digital phenotyping of mental health using multimodal sensing of multiple situations of interest: A systematic literature review,” Journal of Biomedical Informatics, 2022.
- S. Z. Williams, G. S. Chung, and P. A. Muennig, “Undiagnosed depression: A community diagnosis,” SSM-population health, 2017.
- R. Wang, F. Chen, Z. Chen, T. Li, G. Harari, S. Tignor, X. Zhou, D. Ben-Zeev, and A. T. Campbell, “Studentlife: assessing mental health, academic performance and behavioral trends of college students using smartphones,” in Proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing, 2014.
- T. Umematsu, A. Sano, S. Taylor, and R. W. Picard, “Improving students’ daily life stress forecasting using lstm neural networks,” in 2019 IEEE EMBS international conference on biomedical & health informatics (BHI). IEEE, 2019.
- J. Kim, J. Hong, and Y. Choi, “Automatic depression prediction using screen lock/unlock data on the smartphone,” in 2021 18th International Conference on Ubiquitous Robots (UR). IEEE, 2021.
- R. Colbaugh, K. Glass, and V. Global, “Detecting and monitoring brain disorders using smartphones and machine learning,” medRxiv, 2020.
- J. A. R. Rojas, J. Rosas, Y. Shen, H. Jin, and A. K. Dey, “Activity recommendation: Optimizing life in the long term,” in IEEE International Conference on Pervasive Computing and Communications, 2020.
- F. Chen, R. Wang, X. Zhou, and A. T. Campbell, “My smartphone knows i am hungry,” in Proceedings of the 2014 workshop on physical analytics, 2014.
- H. Djeghri, H. Seridi, M. Messaadia, and M. T. Khadir, “A recommendation system for improving student life based on neural network and matrix vectorization,” in 2021 1st International Conference On Cyber Management And Engineering (CyMaEn). IEEE, 2021.
- X. Ma, X. Yang, J. Gao, and C. Xu, “Health status prediction with local-global heterogeneous behavior graph,” ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2021.
- A. Shaw, N. Simsiri, I. Deznaby, M. Fiterau, and T. Rahaman, “Personalized student stress prediction with deep multitask network,” arXiv preprint arXiv:1906.11356, 2019.
- Y. Acikmese and S. E. Alptekin, “Prediction of stress levels with lstm and passive mobile sensors,” Procedia Computer Science, 2019.
- N. Kadri, S. H. Turki, A. Ellouze, and M. Ksantini, “An hybrid deep learning approach for prediction and binary classification of student’s stress,” in Intelligent Systems and Pattern Recognition: Second International Conference. Springer, 2022.
- G. Mikelsons, M. Smith, A. Mehrotra, and M. Musolesi, “Towards deep learning models for psychological state prediction using smartphone data: Challenges and opportunities,” arXiv:1711.06350, 2017.
- W. Gerych, E. Agu, and E. Rundensteiner, “Classifying depression in imbalanced datasets using an autoencoder-based anomaly detection approach,” in 2019 IEEE 13th International Conference on Semantic Computing (ICSC). IEEE, 2019.
- S. Saeb, E. G. Lattie, S. M. Schueller, K. P. Kording, and D. C. Mohr, “The relationship between mobile phone location sensor data and depressive symptom severity,” PeerJ, 2016.
- D. C. Mohr, M. Zhang, and S. M. Schueller, “Personal sensing: understanding mental health using ubiquitous sensors and machine learning,” Annual review of clinical psychology, 2017.