The use of various machine learning algorithms to analyse text data has increased dramatically in studies into Alzheimer's disease (AD). This overview of the literature examines how sentiment analysis and NLP (Natural Language Processing) are used to comprehend texts about Alzheimer's disease. Tokenization, stop-word removal, as well as lemmatization were used to process more than 500 documents, including academic articles, patient narratives, and carer blogs. While sentiment analysis highlighted the emotional undertones in patient and carer tales, the use of LDA identified the predominate study themes. Key terms associated to Alzheimer's disease were detected via named entity recognition. Significant research findings include early detection and novel therapies, a wide range of emotional expressing in patient and carer texts, and critical terms related to AD. The study highlights future directions and emphasises the possibility for text data analysis to further Alzheimer's disease research as well as patient care.
Machine Learning-Based Alzheimer's Disease Prediction using Textual Data
2023-11-22
475417 byte
Conference paper
Electronic Resource
English
Machine learning approaches to analysing textual injury surveillance data: a systematic review
Online Contents | 2015
|Prediction of Heart Disease Using Machine Learning
IEEE | 2018
|Heart Disease Prediction Using Machine Learning Algorithms
Springer Verlag | 2023
|