Abstract
A wide variety of methods have been developed for identifying depression, but they focus primarily on measuring the degree to which individuals are suffering from depression currently. In this work we explore the possibility of predicting future depression using machine learning applied to longitudinal socio-demographic data. In doing so we show that data such as housing status, and the details of the family environment, can provide cues for predicting future psychiatric disorders. To this end, we introduce a novel deep multi-task recurrent neural network to learn time-dependent depression cues. The depression prediction task is jointly optimized with two auxiliary anomaly ranking tasks, including contrastive one-class feature ranking and deviation ranking. The auxiliary tasks address two key challenges of the problem: 1) the high within class variance of depression samples: they enable the learning of representations that are robust to highly variant in-class distribution of the depression samples; and 2) the small labeled data volume: they significantly enhance the sample efficiency of the prediction model, which reduces the reliance on large depression-labeled datasets that are difficult to collect in practice. Extensive empirical results on large-scale child depression data show that our model is sample-efficient and can accurately predict depression 2–4 years before the illness occurs, substantially outperforming eight representative comparators.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Supplementary material is available at https://tinyurl.com/MTNetPAKDD22.
- 2.
‘Ongoing conditions’ means that the conditions “exist for some period of time (weeks, months or years) or re-occur regularly. They do not have to be diagnosed by a doctor”.
- 3.
- 4.
References
Burdisso, S.G., Errecalde, M., Montes-y Gómez, M.: \(\tau \)-ss3: a text classifier with dynamic n-grams for early risk detection over text streams. Pattern Recogn. Lett. 138, 130–137 (2020)
Gong, Y., Poellabauer, C.: Topic modeling based multi-modal depression detection. In: AVEC, pp. 69–76 (2017)
Gray, M., Sanson, A., et al.: Growing up in Australia: the longitudinal study of australian children. Family Matters 72, 4 (2005)
Hassani, K., Haley, M.: Unsupervised multi-task feature learning on point clouds. In: ICCV, pp. 8160–8171 (2019)
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)
Henry, M., et al.: A screening algorithm for early detection of major depressive disorder in head and neck cancer patients post-treatment: longitudinal study. Psycho-oncology 27(6), 1622–1628 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Korsten, L.H., et al.: Factors associated with depression over time in head and neck cancer patients: a systematic review. Psycho-oncology 28(6), 1159–1183 (2019)
Lamers, F., Milaneschi, Y., Smit, J.H., Schoevers, R.A., Wittenberg, G., Penninx, B.W.: Longitudinal association between depression and inflammatory markers: results from the Netherlands study of depression and anxiety. Biol. Psychiatry 85(10), 829–837 (2019)
Losada, D.E., Crestani, F., Parapar, J.: Overview of eRisk: early risk prediction on the internet. In: Bellot, P., et al.: (eds.) CLEF 2018. LNCS, vol. 11018, pp. 343–361. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-98932-7_30
Mann, P., Paes, A., Matsushima, E.H.: See and read: detecting depression symptoms in higher education students using multimodal social media data. In: ICWSM, vol. 14, pp. 440–451 (2020)
Masood, R.: Adapting models for the case of early risk prediction on the internet. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) ECIR 2019. LNCS, vol. 11438, pp. 353–358. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-15719-7_48
Nasir, M., Jati, A., Shivakumar, P.G., Nallan Chakravarthula, S., Georgiou, P.: Multimodal and multiresolution depression detection from speech and facial landmark features. In: AVEC, pp. 43–50 (2016)
Pang, G., Shen, C., Cao, L., Hengel, A.V.D.: Deep learning for anomaly detection: a review. ACM Comput. Surv. 54(2), 1–38 (2021)
Pang, G., Shen, C., van den Hengel, A.: Deep anomaly detection with deviation networks. In: KDD, pp. 353–362 (2019)
Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017)
Ruff, L., et al.: Deep one-class classification. In: International Conference on Machine Learning, pp. 4393–4402. PMLR (2018)
Sadeque, F., Xu, D., Bethard, S.: Measuring the latency of depression detection in social media. In: WSDM, pp. 495–503 (2018)
Shen, T., et al.: Cross-domain depression detection via harvesting social media. In: IJCAI, pp. 1611–1617 (2018)
Standley, T., Zamir, A., Chen, D., Guibas, L., Malik, J., Savarese, S.: Which tasks should be learned together in multi-task learning? In: ICML, pp. 9120–9132. PMLR (2020)
Strezoski, G., Noord, N.V., Worring, M.: Many task learning with task routing. In: ICCV, pp. 1375–1384 (2019)
Uddin, M.A., Joolee, J.B., Lee, Y.K.: Depression level prediction using deep spatiotemporal features and multilayer bi-lTSM. IEEE Trans. Affect. Comput. (2020)
WHO. Depression and Other Common Mental Disorders: Global Health Estimates. Technical Report, World Health Organization (2017)
Yang, Y., Fairbairn, C., Cohn, J.F.: Detecting depression severity from vocal prosody. IEEE Trans. Affect. Comput. 4(2), 142–150 (2012)
Zhang, Y., Yang, Q.: A survey on multi-task learning. arXiv preprint arXiv:1707.08114 (2017)
Zhou, X., Jin, K., Shang, Y., Guo, G.: Visually interpretable representation learning for depression recognition from facial images. IEEE Trans. Affect. Comput. (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pang, G., Pham, N.T.A., Baker, E., Bentley, R., van den Hengel, A. (2022). Deep Depression Prediction on Longitudinal Data via Joint Anomaly Ranking and Classification. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13281. Springer, Cham. https://doi.org/10.1007/978-3-031-05936-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-05936-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05935-3
Online ISBN: 978-3-031-05936-0
eBook Packages: Computer ScienceComputer Science (R0)