“…5-left), which was comparable to prior studies 7,24 .Figure 5Prediction of future development of AD. Five different classification machines were applied to predict future development of AD from MCI patients who have been followed for >3 years.…”
Utilizing the publicly available neuroimaging database enabled by Alzheimer’s disease Neuroimaging Initiative (ADNI; http://adni.loni.usc.edu/), we have compared the performance of automated classification algorithms that differentiate AD vs. normal subjects using Positron Emission Tomography (PET) with fluorodeoxyglucose (FDG). General linear model, scaled subprofile modeling and support vector machines were examined. Among the tested classification methods, support vector machine with Iterative Single Data Algorithm produced the best performance, i.e., sensitivity (0.84) × specificity (0.95), by 10-fold cross-validation. We have applied the same classification algorithm to four different datasets from ADNI, Health Science Centre (Winnipeg, Canada), Dong-A University Hospital (Busan, S. Korea) and Asan Medical Centre (Seoul, S. Korea). Our data analyses confirmed that the support vector machine with Iterative Single Data Algorithm showed the best performance in prediction of future development of AD from the prodromal stage (mild cognitive impairment), and that it was also sensitive to other types of dementia such as Parkinson’s Disease Dementia and Dementia with Lewy Bodies, and that perfusion imaging using single photon emission computed tomography may achieve a similar accuracy to that of FDG-PET.
“…5-left), which was comparable to prior studies 7,24 .Figure 5Prediction of future development of AD. Five different classification machines were applied to predict future development of AD from MCI patients who have been followed for >3 years.…”
Utilizing the publicly available neuroimaging database enabled by Alzheimer’s disease Neuroimaging Initiative (ADNI; http://adni.loni.usc.edu/), we have compared the performance of automated classification algorithms that differentiate AD vs. normal subjects using Positron Emission Tomography (PET) with fluorodeoxyglucose (FDG). General linear model, scaled subprofile modeling and support vector machines were examined. Among the tested classification methods, support vector machine with Iterative Single Data Algorithm produced the best performance, i.e., sensitivity (0.84) × specificity (0.95), by 10-fold cross-validation. We have applied the same classification algorithm to four different datasets from ADNI, Health Science Centre (Winnipeg, Canada), Dong-A University Hospital (Busan, S. Korea) and Asan Medical Centre (Seoul, S. Korea). Our data analyses confirmed that the support vector machine with Iterative Single Data Algorithm showed the best performance in prediction of future development of AD from the prodromal stage (mild cognitive impairment), and that it was also sensitive to other types of dementia such as Parkinson’s Disease Dementia and Dementia with Lewy Bodies, and that perfusion imaging using single photon emission computed tomography may achieve a similar accuracy to that of FDG-PET.
“…One fold was left for validation and the remaining 2 1 K − fold for training was combined with the grid search to determine the optimal parameters. In the grid search, the values of C and γ varied logarithmically from -5 20 2 to 2 and from -15 15 2 to 2 , respectively. The inner loop was repeated 2 K times and the accuracy of the classifier was obtained across the 2 K folds for every combination of C and γ .…”
Section: The Svmmentioning
confidence: 99%
“…The proposed work was accomplished using four steps to develop an automatic computer-aided diagnosis (CAD) technique for AD diagnosis. First, a statistical method was used based on the VBM technique plus Diffeomorphic Anatomical Registration using the Exponentiated Lie algebra (DARTEL) approach to analyze group-wise comparisons between a cross-sectional structural MRI scans diseased group and normal controls [6,14,15]. Based on the VBM plus DARTEL approach, overall and regional structural gray matter alterations were investigated to define regions with a significant decline of gray matter in patients with AD compared to the healthy controls (HCs).…”
“…In our view, it would be important to define a target conversion time window. This is indeed a relevant topic, partly investigated by Cabral et al [11]. Their results clearly show that (using a specific machine learning approach) the sensitivity for detection critically increases during the last 12 months prior to conversion.…”
Section: Methodsmentioning
confidence: 87%
“…A patient who still has Bstable^MCI after 1 year may still convert to AD after 2 or 3 years [10]. In this respect, it should be noted that it is hard to say whether positive [ 18 F]FDG PET findings in patients with clinically stable MCI should be considered false-positive if the follow-up time is less than 3 years [11,12]. In our view, it would be important to define a target conversion time window.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
