In　healthcare　sector,　it　is　of　crucial　importance　to　accurately　diagnose　Alzheimer＇s　disease　(AD)　and　its　prophase　called　mild　cognitive　impairment　(MCI)　so　as　to　prevent　degeneration　and　provide　early　treatment　for　AD　patients.　In　this　paper,　a　framework　is　proposed　for　the　diagnosis　of　AD,　which　consists　of　MRI　images　preprocessing,　feature　extraction,　principal　component　analysis,　and　the　support　vector　machine　(SVM)　model.　In　particular,　a　new　switching　delayed　particle　swarm　optimization　(SDPSO)　algorithm　is　proposed　to　optimize　the　SVM　parameters.　The　developed　framework　based　on　the　SDPSO-SVM　model　is　successfully　applied　to　the　classification　of　AD　and　MCI　using　MRI　scans　from　ADNI　dataset.　Our　developed　algorithm　can　achieve　excellent　classification　accuracies　for　6　typical　cases.　Furthermore,　experiment　results　demonstrate　that　the　proposed　algorithm　outperforms　several　SVM　models　and　also　two　other　state-of-art　methods　with　deep　learning　embedded,　thereby　serving　as　an　effective　AD　diagnosis　method.　©　2018　Elsevier　B.V.