HSI-LFS-BERT: Novel Hybrid Swarm Intelligence Based Linguistics Feature Selection and Computational Intelligent Model for Alzheimer’s Prediction Using Audio Transcript

Abstract

Alzheimer's dementia (AD) affects memory, language, and cognition which worsens over time. It is critical to develop a reliable early detection method before permanent brain atrophy and cognitive impairment. This study uses clinical transcripts, a text-based adaptation of the original audio recordings of Alzheimer's patients. This audio transcript data is taken from DementiaBank which is the largest public dataset of AD transcripts. The study aims to show how transfer learning-based models and swarm intelligence optimization techniques can be used to predict Alzheimer's disease. To enhance the prediction performance for Alzheimer's disease, a hybrid swarm intelligence linguistic feature selection (HSI-LFS) approach is proposed that extracts a combined feature set using Particle Swarm Optimization (PSO), Dragonfly Optimization (DO), and Grey Wolf Optimization (GWO) algorithms. In addition, a transfer learning-based model called HSI-LFS-BERT, a combination of the HSI-LFS feature selection method and Bidirectional Encoder Representations from Transformer (BERT) algorithm is proposed. The proposed model is compared using two feature sets: first set consists of the initial feature set and the second set contains hybrid feature set that has been extracted using the suggested HSI-LFS method. The BERT embedding with HSI-LFS outperformed the conventional feature set providing the most accurate modeling parameters while reducing the computations by 27.19%. The proposed HSI-LFS-BERT model excelled state-of-the-art models achieving 98.24% accuracy, 91.56% precision, and 98.78% recall.

A Novel Dual Feature Extraction using Fine-Tuned ResNet with GWO and Deep Dense Neural Network for Multiple Lung Disease Classification

“…Their research showed that when Adam was used as the optimiser for GoogleNet, accuracy increased to 92.08%. Wang et al (2020) [30] tested a novel residual neural network with a transfer learning approach on medical images [20,21] to identify pathology in lung cancer subtypes for an accurate and reliable diagnosis. They enhanced the algorithm using their proprietary lung cancer dataset from Shandong Provincial Hospital after initial training on the open medical image dataset luna16.…”

A Novel Dual Feature Extraction using Fine-Tuned ResNet with GWO and Deep Dense Neural Network for Multiple Lung Disease Classification

“…Healthcare informatics can benefit significantly from machine learning. It can be used for the prognosis, classification, and diagnosis of diseases [6][7][8][9][10]. One of the most popular radiological tests for lung disease screening is the chest X-ray.…”

“…Another study [34] tested a novel residual neural network with a transfer learning approach on medical images [20,21] to identify pathology in lung cancer subtypes for an accurate and reliable diagnosis. They enhanced the algorithm using their proprietary lung cancer dataset from Shandong Provincial Hospital after initial training on the open medical image dataset luna16.…”

From beasts to bytes: Revolutionizing zoological research with artificial intelligence

“…Consequently, future work should focus on these issues and refine AI models for application in diverse natural environments. Moreover, wildlife data covers not only images but also an abundance of text and voiceprint data, which are inherently sequential and more amenable for analysis using transformer-based frameworks, such as BERT ( Khan et al, 2022 ). Although the use of CNNs for classifying bird species based on raw sound waveforms has achieved suboptimal accuracy ( Bravo Sanchez et al, 2021 ), the application of transformer-based approaches, though presently limited (Supplementary Table S3), holds considerable promise for future research.…”

“…Given their sequential nature, time series and video recording data may be better processed using transformer-based architectures. The pre-trained large language models underpinning BERT (homologous transformer architecture) have already set new benchmarks in sequence-dependent bioresearch ( Khan et al, 2022 ; Lin et al, 2022). Hence, we propose that future studies, particularly those involving time-series analyses of continuous data from animal vocalizations, locomotion positions, and text data, may benefit from the utilization of language models, rather than solely relying on CNNs.…”