Skip to main content
Fig. 1 | Alzheimer's Research & Therapy

Fig. 1

From: Quantification of identifying cognitive impairment using olfactory-stimulated functional near-infrared spectroscopy with machine learning: a post hoc analysis of a diagnostic trial and validation of an external additional trial

Fig. 1

Our proposed overall architecture for the two models: the classification of MCI and CN uses an ensemble approach combining the three models of XGBoost, GB, and LGB, and the classification of MCI-AD and CN uses an ensemble approach combining the four models of XGBoost, GB, LGB, and AdaBoost. The balanced accuracy values from five models via fivefold cross-validation were used for cross-validation model weights to combine the five models. CN, cognitively normal; MCI, mild cognitive impairment; XGBoost, extreme gradient boosting; GB, gradient boosting; LBG, light gradient boosting; AdaBoost, adaptive boosting; AD, Alzheimer’s disease

Back to article page

Alzheimer's Research & Therapy

ISSN: 1758-9193