Ensemble Learning-Based Alzheimer’s Disease Classification Using Electroencephalogram Signals and Clock Drawing Test Images DOI Creative Commons

Young Huh,

Junha Park, Young Jae Kim

и другие.

Sensors, Год журнала: 2025, Номер 25(9), С. 2881 - 2881

Опубликована: Май 2, 2025

Ensemble learning (EL), a machine technique that combines the results of multiple algorithms to obtain predicted values, aims achieve better predictive performance than single algorithm alone. Machine techniques, including EL, have been applied in field medicine assist clinical interpretation specific diseases. Although neurodegenerative diseases, especially Alzheimer’s disease (AD), are interest clinicians and researchers due their rapid increase cases, application EL AD diagnosis has relatively less attempted. In this research, we demonstrate three algorithms, trained on an ensemble electroencephalogram (EEG) clock drawing test (CDT) feature data for classification task, show improved detection accuracy compared when either EEG or CDT dataset is used independently. We also explore which contributes most decision-making healthy control (HC) classification. conclusion, current study suggests can be novel (ML) automated screening process.

Язык: Английский

Ensemble Learning-Based Alzheimer’s Disease Classification Using Electroencephalogram Signals and Clock Drawing Test Images DOI Creative Commons

Young Huh,

Junha Park, Young Jae Kim

и другие.

Sensors, Год журнала: 2025, Номер 25(9), С. 2881 - 2881

Опубликована: Май 2, 2025

Ensemble learning (EL), a machine technique that combines the results of multiple algorithms to obtain predicted values, aims achieve better predictive performance than single algorithm alone. Machine techniques, including EL, have been applied in field medicine assist clinical interpretation specific diseases. Although neurodegenerative diseases, especially Alzheimer’s disease (AD), are interest clinicians and researchers due their rapid increase cases, application EL AD diagnosis has relatively less attempted. In this research, we demonstrate three algorithms, trained on an ensemble electroencephalogram (EEG) clock drawing test (CDT) feature data for classification task, show improved detection accuracy compared when either EEG or CDT dataset is used independently. We also explore which contributes most decision-making healthy control (HC) classification. conclusion, current study suggests can be novel (ML) automated screening process.

Язык: Английский

Процитировано

0