Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementiaShow others and affiliations
2023 (English)In: Frontiers in Bioengineering and Biotechnology, E-ISSN 2296-4185, Vol. 11, article id 1336255Article in journal (Refereed) Published
Abstract [en]
Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia. Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew’s correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system’s efficiency. Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535. Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.
Place, publisher, year, edition, pages
Frontiers Media S.A., 2023. Vol. 11, article id 1336255
Keywords [en]
dementia, F-score, feature selection, machine learning, voting classifier, Decision trees, Deterioration, Diagnosis, Forecasting, Hybrid systems, Learning systems, Logistic regression, Neurodegenerative diseases, Noninvasive medical procedures, Support vector machines, Baseline machines, Breakings, Correlation coefficient, Diagnostic systems, Features selection, Machine learning models, Machine-learning, Voting classifiers
National Category
Computer Sciences Gerontology, specialising in Medical and Health Sciences Geriatrics Biomedical Laboratory Science/Technology
Research subject
Family-Centred Health
Identifiers
URN: urn:nbn:se:his:diva-23566DOI: 10.3389/fbioe.2023.1336255ISI: 001153187700001PubMedID: 38260734Scopus ID: 2-s2.0-85182656352OAI: oai:DiVA.org:his-23566DiVA, id: diva2:1833576
Funder
Blekinge Institute of Technology
Note
CC BY 4.0 DEED
© 2024 Javeed, Anderberg, Ghazi, Noor, Elmståhl and Berglund
Correspondence Address: J.S. Berglund; Department of Health, Blekinge Institute of Technology, Karlskrona, Sweden; email: johan.sanmartin.berglund@bth.se
The author(s) declare financial support was received for the research, authorship, and/or publication of this article. Open access funding provided by Blekinge Institute of Technology. The first author’s learning process was supported by the National E-Infrastructure for Aging Research (NEAR), Sweden. NEAR is working on improving the health condition of older adults in Sweden.
2024-02-012024-02-012024-04-15Bibliographically approved