Predicting Dementia and Influencing Factors Investigation Based on Machine Learning Algorithms

DOI

10.2991/978-94-6463-512-6_37How to use a DOI?

Keywords

Machine Learning; Dementia; Random Forest

Abstract

Dementia is a serious problem worldwide, which brings great trouble to people’s life. Therefore, to better control this disease, it is necessary to find out the main factors of dementia. Artificial Intelligence and machine learning can be very good at solving this kind of issue. This research is based on the usual physical data of patients to analyze the causes of dementia, using Dementia Patient Health, Prescriptions ML Dataset from Kaggle. First of all, data preprocessing and some other relative operations are carried out to make sure the dataset can be processed. Then 5 different models are taken into consideration, including Support Vector Machines (SVM), Naïve Bayes, decision trees, Random Forest (RF) and AdaBoost. After training these models and using them to predict dementia prevalence respectively, this research compares their performances by evaluation metrics like the accuracy, f1-score, confusion matrix and the Receiver Operating Characteristic (ROC) curve. Decision trees, RF and AdaBoost work best on this dataset, with accuracy up to 100%. Then RF is chosen for calculating and ranking feature importance. It is found that cognitive test scores, depression status and Apolipoprotein E (APOE ε4) carrying conditions are the three most important features that is related to dementia. However, some results are inconsistent with reality, such as judging important factors as unimportant. In this way, more work and improvement will need to be done in the future.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Qiya Feng
PY  - 2024
DA  - 2024/09/23
TI  - Predicting Dementia and Influencing Factors Investigation Based on Machine Learning Algorithms
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 342
EP  - 352
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_37
DO  - 10.2991/978-94-6463-512-6_37
ID  - Feng2024
ER  -