Optimizing Depression Prediction in Older Adults: A Comparative Study of Feature Extraction and Machine Learning ModelsShow others and affiliations
2024 (English)In: International Conference on Control, Automation and Diagnosis, ICCAD 2024, Institute of Electrical and Electronics Engineers (IEEE), 2024Conference paper, Published paper (Refereed)
Abstract [en]
Depression emerged as a major public health concern in older adults, and timely prediction of depression has become a difficult problem in medical informatics. The latest studies have attentiveed on feature transformation and selection for better depression prediction. In this study, we assess the performance of various feature extraction algorithms, including principal component analysis (PCA), independent component analysis (ICA), locally linear Embedding (LLE), and t-distributed stochastic neighbor embedding (TSNE). These algorithms are combined with machine learning (ML) classifier algorithms such as Gaussian Naive Bayes (GNB), Logistic Regression (LR), K-nearest-neighbor (KNN), and Decision Tree (DT) to enhance depression prediction. In total, sixteen automated integrated systems are constructed based on the above-mentioned feature extraction methods and ML classifiers. The performance of all of these integrated models is assessed using data from the Swedish National Study on Aging and Care (SNAC). According to the experimental results, the PCA algorithm combined with the Logistic Regression (LR) model provides 89.04% depression classification accuracy. As a result, it is demonstrated that the PCA is a more suitable feature extraction method for depression data than ICA, LLE, and TSNE. © 2024 IEEE.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024.
Keywords [en]
classification, depression, feature extraction, machine learning, Decision trees, Embeddings, Extraction, Forecasting, Independent component analysis, Nearest neighbor search, Principal component analysis, Stochastic systems, Features extraction, Independent components analysis, Learning classifiers, Locally linear embedding, Machine-learning, Older adults, Performance, Principal-component analysis, Stochastic neighbor embedding
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-26768DOI: 10.1109/ICCAD60883.2024.10553890Scopus ID: 2-s2.0-85197920799ISBN: 9798350361025 (print)OAI: oai:DiVA.org:bth-26768DiVA, id: diva2:1887439
Conference
2024 International Conference on Control, Automation and Diagnosis, ICCAD 2024, Paris, May 15-17 2024
Projects
SNAC2024-08-082024-08-082024-10-02Bibliographically approved