Deep Depression Prediction on Longitudinal Data via Joint Anomaly Ranking and Classification
This work provides a method for early prediction of depression for individuals, potentially enabling earlier intervention, which is a significant step beyond current methods that only identify current depression.
This paper addresses the prediction of future depression using longitudinal socio-demographic data, demonstrating that factors like housing status and family environment can predict psychiatric disorders. The authors developed a deep multi-task recurrent neural network, jointly optimized with two auxiliary anomaly ranking tasks, which accurately predicts depression 2-4 years before onset, outperforming eight comparators.
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.