Generalizability of the Disease State Index Prediction Model for Identifying Patients Progressing from Mild Cognitive Impairment to Alzheimer's Disease

作者：Hall Anette^*; Munoz Ruiz Miguel; Mattila Jussi; Koikkalainen Juha; Tsolaki Magda; Mecocci Patrizia; Kloszewska Iwona; Vellas Bruno; Lovestone Simon; Visser Pieter Jelle; Lotjonen Jyrki; Soininen Hilkka

来源：Journal of Alzheimer's Disease, 2015, 44(1): 79-92.

DOI：10.3233/JAD-140942

• Alzheimer's disease
• computer-assisted diagnosis
• dementia
• magnetic resonance imaging (MRI)
• mild cognitive impairment

Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease.
Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study.
Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 x 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF).
Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results.
Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.

• 出版日期2015