Unipolar and Bipolar Depression Detection and Classification Based on Actigraphic Registration of Motor Activity Using Machine Learning and Uniform Manifold Approximation and Projection Methods

Abstract

Modern technology frequently uses wearable sensors to monitor many aspects of human behavior. Since continuous records of heart rate and activity levels are typically gathered, the data generated by these devices have a lot of promise beyond counting the number of daily steps or calories expended. Due to the patient’s inability to obtain the necessary information to understand their conditions and detect illness, such as depression, objectively, methods for evaluating various mental disorders, such as the Montgomery–Asberg depression rating scale (MADRS) and observations, currently require a significant amount of effort on the part of specialists. In this study, a novel dataset was provided, comprising sensor data gathered from depressed patients. The dataset included 32 healthy controls and 23 unipolar and bipolar depressive patients with motor activity recordings. Along with the sensor data collected over several days of continuous measurement for each patient, some demographic information was also offered. The result of the experiment showed that less than 70 of the 100 epochs of the model’s training were completed. The Cohen Kappa score did not even pass 0.1 in the validation set, due to an imbalance in the class distribution, whereas in the second experiment, the majority of scores peaked in about 20 epochs, but because training continued during each epoch, it took much longer for the loss to decline before it fell below 0.1. In the second experiment, the model soon reached an accuracy of 0.991, which is as expected given the outcome of the UMAP dimensionality reduction. In the last experiment, UMAP and neural networks worked together to produce the best outcomes. They used a variety of machine learning classification algorithms, including the nearest neighbors, linear kernel SVM, Gaussian process, and random forest. This paper used the UMAP unsupervised machine learning dimensionality reduction without the neural network and showed a slightly lower score (QDA). By considering the ratings of the patient’s depressive symptoms that were completed by medical specialists, it is possible to better understand the relationship between depression and motor activity.

A survey of autonomous monitoring systems in mental health

“…The most popular machine learning tools are outlined in Table 4, which can be found here. Weka was utilized for the diagnosis of bipolar disorder in Alvarez‐Lozano et al (2014), Faurholt‐Jepsen, Vinberg, Frost, Debel, Margrethe Christensen, Bardram, and Kessing (2016), Grunerbl et al (2014), Grünerbl et al (2015), and De Vos et al (2016), for instance, in Zakariah and Alotaibi (2023) scikit‐learn was utilized for the recognition of anxiousness. However, authors rarely reveal the tools and libraries they employed.…”

“…Scikit learn (Bendig et al, 2022;Zakariah & Alotaibi, 2023) Python library Scikit-Learn, often known as sklearn, is used to create machine learning models and statistical modeling. It is also known by its original name.…”

“…Wang et al found that heart rate variability is a potential objective biological marker associated with generalized anxiety disorder (Wang et al, 2023), who studied the behavioral effects of psychosis and depression, found that patients with both diseases participated in much less motor activity than controls, as evaluated by actigraphs. Zakariah and Alotaibi investigated whether or not motor activity recording with actigraphy could be used to diagnose unipolar and bipolar depression (Zakariah & Alotaibi, 2023).…”

A comparative study of machine learning algorithms for predicting domestic violence vulnerability in Liberian women

“…Furthermore, there is no investigation of the interpretability and explainability of depression categorization models in the study. Understanding how these models make predictions is critical, especially when trust and transparency are essential in a therapeutic setting [ 25 ]. To address these limitations and advance the field of machine learning in depression detection, future research should consider strategies for class imbalance mitigation, more extensive and diverse datasets, improved model interpretability, validation in clinical settings, and comparison of dimensionality reduction techniques.…”