Details

Autor(en) / Beteiligte

• Moodely, Govana Vetrimani
• Amiree, S. M. Ihtasham Hossain
• Thazin, May
• R N, Ravikumar
• Habib, Masruk
• Kumar Singh, Sushil

Titel

A Comparative Study on Hybrid Machine Learning Voting Classifier Models for Alzheimer's Disease Prediction

Ist Teil von

• 2023 International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), 2023, Vol.1, p.1-6

Ort / Verlag

IEEE

Erscheinungsjahr

2023

Quelle

IEEE Xplore

Beschreibungen/Notizen

• Alzheimer's dementia, a neurological disease that affects millions of people worldwide, is a huge public health problem. It is critical to develop accurate prediction models since early detection can lead to more effective management and treatment. In this work, we investigate a range of hybrid machine-learning approaches that include Random Forest (RF) and Decision Tree (DT) as distinct models. Tree Forest Hybrid (TFH), TFH + Gradient Boosting (GB), Multi-Model Voting Ensemble (MVE), Multi Classifier Ensemble (MCE), and Naïve Bayes + GB are some of the models we investigate utilizing demographic and clinical features from the "oasis_longitudinal.csv" dataset. A comparison of the accuracy of numerous models indicates that four notable models, TFH MCE, MVE, and RF, each obtained an accuracy of 86.67%. NB + GB model with an accuracy of 85.33%, while the TFH+GB and DT models achieved an accuracy of 84%. Following a closer evaluation of these models' Root Mean Square Error (RMSE) and cross-validation scores, 'TFH' emerged as the highest performer, highlighting the promise of hybrid machine learning for improving Alzheimer's disease prediction.