Related Experiment Video
Updated: Nov 14, 2025
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Diagnostic accuracy of brief cognitive screening tools to diagnose vascular cognitive impairment in Peru
Nilton Custodio1,2,3, Rosa Montesinos2,3,4, Carlos Alva-Diaz5,6
1Servicio de Neurología, Instituto Peruano de Neurociencias, Lima, Perú.
Introduction:
To evaluate the diagnostic accuracy of three brief cognitive screening (BCS) tools, Peruvian version of Addenbrooke's Cognitive Examination (ACE-Pe), of INECO Frontal Screening (IFS-Pe) and of the Mini-Mental State Examination (MMSE-Pe), for the diagnosis of vascular cognitive impairment (VCI) and its non-dementia stages (VCI-ND) and vascular dementia (VD) in patients with cerebral stroke in Lima-Peru.
Materials And Methods:
A cohort analysis to evaluate the diagnostic accuracy of three BCS for VCI.
Results:
Two hundred and four patients were evaluated: 61% Non-VCI, 30% VCI-ND and 9% VD. To discriminate patients with VCI from controls, the area under the curve (AUC) of ACE-Pe, IFS-Pe and MMs-Pe were 0.99 (95% confidence interval [CI] 0.98-0.99), 0.99 (95%CI 0.98-0.99) and 0.87 (95%CI 0.82-0.92), respectively. Of the three BCS, the IFS-Pe presented a larger AUC to discriminate VCI-ND from VD (AUC = 0.98 [95%CI 0.95-1]) compared to ACE-Pe (AUC = 0.84 [95%CI 0.74-0.95]) and MMSE-Pe (0.92 [95%CI 0.86-0.99]). The IFS-Pe presented a higher sensitivity (S), specificity (Sp), and positive (+LR) and negative likelihood ratios (-LR) (S = 96.72%, Sp = 89.47%, +LR = 9.1 and -LR = 0.03) than ACE-Pe (S = 96.72%, Sp = 63.16%, +LR = 2.62 and -LR = 0.05) and MMSE-Pe (S = 90.16%, Sp = 78.95%, +LR = 4.28 and -LR = 0.12). In the multiple regression analysis, the IFS-Pe was not affected by age, sex or years of schooling.
Conclusion:
The IFS-Pe has the best diagnostic accuracy for detecting VCI and discriminating between pre-dementia (VCI-ND) and dementia (VD) stages.
