Real-Time Inferencing Using Transfer Learning for a Screening of Depression Detection Using Actigraphy

Automated depression screening and diagnosis is a highly relevant problem today. There are several limitations of the traditional depression detection methods, namely high dependence on clinicians and biased self-reporting. In recent years, research has suggested strong potential in machine learning (ML)-based methods that make use of the user’s passive data collected via wearable devices. However, ML is data-hungry. Especially in the healthcare domain primary data collection is challenging. In this work, we present an approach based on transfer learning, from a model trained on a secondary dataset, for the real-time deployment of the depression screening tool based on the actigraphy data of users. This approach enables real-time inferencing on a trained model for a limited primary data. A modified version of leave-one-out cross-validation approach performed on the primary set resulted in mean accuracy of 0.96, where in each iteration one subject’s data from the primary set was set aside for testing. Such an approach can be useful in understanding the capability of a trained model on secondary data in situations where primary data is limited.