Article: Study of biomarker variation and severity prediction in dementia using intelligent system Journal: International Journal of Biomedical Engineering and Technology (IJBET) 2024 Vol.44 No.1 pp.1 - 25 Abstract: Precise detection of dementia biomarkers in the brain enables early understanding of pathology variations. Owing to which there is a need for studying different dementia biomarker in magnetic resonance (MR) image for its specific changes between normal and severity stages to categorise the prognostic difference. The present study is an attempt to utilise an optimised framework with fused radiomic and deep features based on least absolute shrinkage and selection operator (LASSO) using a hybrid meta-heuristic optimiser for classification. The investigation is attempted on Alzheimer's disease neuroimaging initiative (ADNI) database. The radiomic and deep features were extracted from the considered biomarkers and then fused. Further, the significant features were obtained using LASSO model. Then, those features were input to hybrid meta-heuristic optimiser with machine learning model for classification. From the result, it was identified that hippocampus, along with the brainstem, gave higher classification accuracy of 97.87% to identify prognostic differences for considered classes. Therefore, the quantifiable interpretation was claimed to improve clinical assessment. Inderscience Publishers - linking academia, business and industry through research

Title: Study of biomarker variation and severity prediction in dementia using intelligent system

Authors: Ahana Priyanka; G. Kavitha

Addresses: Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chrompet, Chennai, India ' Department of Electronics Engineering, Madras Institute of Technology, Anna University, Chrompet, Chennai, India

Abstract: Precise detection of dementia biomarkers in the brain enables early understanding of pathology variations. Owing to which there is a need for studying different dementia biomarker in magnetic resonance (MR) image for its specific changes between normal and severity stages to categorise the prognostic difference. The present study is an attempt to utilise an optimised framework with fused radiomic and deep features based on least absolute shrinkage and selection operator (LASSO) using a hybrid meta-heuristic optimiser for classification. The investigation is attempted on Alzheimer's disease neuroimaging initiative (ADNI) database. The radiomic and deep features were extracted from the considered biomarkers and then fused. Further, the significant features were obtained using LASSO model. Then, those features were input to hybrid meta-heuristic optimiser with machine learning model for classification. From the result, it was identified that hippocampus, along with the brainstem, gave higher classification accuracy of 97.87% to identify prognostic differences for considered classes. Therefore, the quantifiable interpretation was claimed to improve clinical assessment.

Keywords: dementia; hybrid optimiser; fused feature; biomarker and prognostic difference; least absolute shrinkage and selection operator; LASSO; Alzheimer's disease neuroimaging initiative; ADNI.

DOI: 10.1504/IJBET.2024.136371

International Journal of Biomedical Engineering and Technology, 2024 Vol.44 No.1, pp.1 - 25

Received: 07 Oct 2022
Accepted: 24 Jan 2023
Published online: 31 Jan 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Study of biomarker variation and severity prediction in dementia using intelligent system

Keep up-to-date