Enhancing Early Dementia Detection: A Machine Learning Approach Leveraging Cognitive and Neuroimaging Features for Optimal Predictive Performance

Irfan, Muhammad; Shahrestani, Seyed; Elkhodr, Mahmoud

doi:10.3390/app131810470

Cited by 4 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagnostic process for dementia requires an overall review of the patient's medical history, genetic testing, psychiatric evaluations, and cognitive assessments, often supplemented by neuroimaging techniques 2,3 . This multi-faceted nature of dementia diagnosis is complex, leading to growing interest in simplifying the process using more accessible and lower-cost methods [4][5][6] . Among the cognitive problems caused by dementia, verbal and speech impairments can be easily observed.…”

Section: Multimodal Deep Learning For Dementia Classification Using T...mentioning

confidence: 99%

Multimodal deep learning for dementia classification using text and audio

Lin,

Washington

2024

Sci Rep

View full text Add to dashboard Cite

Dementia is a progressive neurological disorder that affects the daily lives of older adults, impacting their verbal communication and cognitive function. Early diagnosis is important to enhance the lifespan and quality of life for affected individuals. Despite its importance, diagnosing dementia is a complex process. Automated machine learning solutions involving multiple types of data have the potential to improve the process of automated dementia screening. In this study, we build deep learning models to classify dementia cases from controls using the Pitt Cookie Theft dataset from DementiaBank, a database of short participant responses to the structured task of describing a picture of a cookie theft. We fine-tune Wav2vec and Word2vec baseline models to make binary predictions of dementia from audio recordings and text transcripts, respectively. We conduct experiments with four versions of the dataset: (1) the original data, (2) the data with short sentences removed, (3) text-based augmentation of the original data, and (4) text-based augmentation of the data with short sentences removed. Our results indicate that synonym-based text data augmentation generally enhances the performance of models that incorporate the text modality. Without data augmentation, models using the text modality achieve around 60% accuracy and 70% AUROC scores, and with data augmentation, the models achieve around 80% accuracy and 90% AUROC scores. We do not observe significant improvements in performance with the addition of audio or timestamp information into the model. We include a qualitative error analysis of the sentences that are misclassified under each study condition. This study provides preliminary insights into the effects of both text-based data augmentation and multimodal deep learning for automated dementia classification.

show abstract

Section: Multimodal Deep Learning For Dementia Classification Using T...mentioning

confidence: 99%

Multimodal deep learning for dementia classification using text and audio

Lin,

Washington

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia

Galanakis,

Soldatos,

Karanikolas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset.

show abstract

Synthetic data analysis for early detection of Alzheimer progression through machine learning algorithms

Sánchez Reyna,

Mendoza-Gonzalez,

Luna-García

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is a serious neurodegenerative disorder that causes incurable and irreversible neuronal loss and synaptic dysfunction. The progress of this disease is gradual and depending on the stage of its detection, only its progression can be treated, reducing the most aggressive symptoms and the speed of its neurodegenerative progress. This article proposes an early detection model for the diagnosis of AD by performing analyses in Alzheimer’s progression patient datasets, provided by the Alzheimer’s Disease Neuroimaging Initiative (ADNI), including only neuropsychological assessments and making use of feature selection techniques and machine learning models. The focus of this research is to build an ensemble machine learning model capable of early detection of a patient with Alzheimer’s or a cognitive state that leads to it, based on their results in neuropsychological assessments identified as highly relevant for the detection of Alzheimer’s. The proposed approach for the detection of AD is presented with the inclusion of the feature selection technique recursive feature elimination (RFE) and the Akaike Information Criterion (AIC), the ensemble model consists of logistic regression (LR), artificial neural networks (ANN), support vector machines (SVM), K-nearest neighbors (KNN) and nearest centroid (Nearcent). The datasets downloaded from ADNI were divided into 13 subsets including: cognitively normal (CN) vs subjective memory concern (SMC), CN vs early mild cognitive impairment (EMCI), CN vs late mild cognitive impairment (LMCI), CN vs AD, SMC vs EMCI, SMC vs LMCI, SMC vs AD, EMCI vs LMCI, EMCI vs AD, LMCI vs AD, MCI vs AD, CN vs AD and CN vs MCI. From all the feature results, a custom model was created using RFE, AIC and testing each model. This work presents a customized model for a backend platform to perform one-versus-all analysis and provide a basis for early diagnosis of Alzheimer’s at its current stage.

show abstract

Enhancing Early Dementia Detection: A Machine Learning Approach Leveraging Cognitive and Neuroimaging Features for Optimal Predictive Performance

Cited by 4 publications

References 31 publications

Multimodal deep learning for dementia classification using text and audio

Multimodal deep learning for dementia classification using text and audio

A MediaPipe Holistic Behavior Classification Model as a Potential Model for Predicting Aggressive Behavior in Individuals with Dementia

Synthetic data analysis for early detection of Alzheimer progression through machine learning algorithms

Contact Info

Product

Resources

About