An unsupervised machine learning approach using passive movement data to understand depression and schizophrenia

Price, George D.; Heinz, Michael V.; Zhao, Daniel; Nemesure, Matthew D.; Ruan, Franklin; Jacobson, Nicholas C.

doi:10.1016/j.jad.2022.08.013

Cited by 8 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two experiments' results confirmed what was predicted: the best results were obtained when UMAP and neural networks collaborated. Price et al's paper [41] used the UMAP unsupervised machine learning dimensionality reduction without the neural network in forward and showed a marginally lower score compared to Garcia-Ceja et al [43] who used of a variety of machine learning classification algorithms, including the nearest neighbor, linear kernel SVM, radial basis function kernel, SVM, Gaussian process, decision tree, and random forest (QDA). A score of more than 0.72 was not achieved by any algorithm.…”

Section: Discussionmentioning

confidence: 99%

“…The z-score can be calculated using Equation (1) above for a given number from any distribution; it is always calculated by taking X, minus the distribution's mean, and then dividing by the distribution's standard deviation [41]. Each sample was labeled according to the tape it was derived from in order to produce a rigorous target value, resulting in 4 classes overall.…”

Section: Feature Extractionmentioning

confidence: 99%

“…The findings of the two trials were as expected: UMAP and neural networks worked together to produce the best outcomes. While Garcia-Ceja et al [43] used a variety of machine learning classification algorithms, including the nearest neighbors, linear kernel SVM, radial basis function kernel (RBF) SVM, Gaussian process, decision tree, and random forest, Price et al's paper [41] used the UMAP unsupervised machine learning dimensionality reduction without the network in forward and showed a slightly lower score (QDA). None of the algorithms had a score greater than 0.727.…”

Section: Umap Neural Networkmentioning

confidence: 99%

See 2 more Smart Citations

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

Zakariah

Alotaibi

2023

Diagnostics

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%