In　this　study,　we　employed　diffusion　tensor　imaging　(DTI)　to　construct　brain　structural　network　and　then　derive　the　connection　matrices　from　96　healthy　elderly　subjects.　The　correlation　analysis　between　these　topological　properties　of　network　based　on　graph　theory　and　the　Cognitive　Abilities　Screening　Instrument　(CASI)　index　were　processed　to　extract　the　significant　network　characteristics.　These　characteristics　were　then　integrated　to　estimate　the　models　by　various　machine-learning　algorithms　to　predict　user＇s　cognitive　performance.　From　the　results,　linear　regression　model　and　Gaussian　processes　model　showed　presented　better　abilities　with　lower　mean　absolute　errors　of　5.8120　and　6.25　to　predict　the　cognitive　performance　respectively.　Moreover,　these　extracted　topological　properties　of　brain　structural　network　derived　from　DTI　also　could　be　regarded　as　the　bio-signatures　for　further　evaluation　of　brain　degeneration　in　healthy　aged　and　early　diagnosis　of　mild　cognitive　impairment　(MCI).　©　2013　IEEE.