MRI and cognitive scores complement each other to accurately predict Alzheimer’s dementia 2 to 7 years before clinical onset

Zandifar, Azar; Fonov, Vladimir S.; Ducharme, Simon; Belleville, Sylvie; Collins, D. Louis

doi:10.1101/567867

Cited by 5 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work, we showed that when predicting onset of dementia in subjects with mild cognitive impairment, MRI-based features (SNIPE) are more sensitive compared to cognitive features, and even more so with longer follow-up periods, while cognitive features contribute more to the specificity of the prediction [15]. Here, we also show that cognitive features lose sensitivity when it comes to predicting cognitive decline at 36 months compared to that at 24 months.…”

Section: Discussionsupporting

confidence: 55%

“…At three years, prediction sensitivity of MOCA and ADAS dropped to 66.4%, but adding HC SNIPE features raises it to 75.4%, a 9% increase. As we have previously shown [15], MRI-driven features help contribute more sensitivity to the prediction at later followup periods. Despite the fact that predicting subtle cognitive decline is harder than predicting conversion from MCI to AD, the predictive accuracy of cognitive decline remains high.…”

Section: Discussionmentioning

confidence: 59%

“…In our previous work, we showed that baseline SNIPE scores could differentiate patients with mild cognitive impairment (MCI) that remain stable vs those that progress to AD [13], and that baseline SNIPE scores enable AD prediction in a group of cognitively intact subjects seven years before the clinical diagnosis of AD dementia [14]. More recently, we demonstrated that combining MRI features and neurocognitive test results at baseline could yield 78% accuracy in prediction of conversion from MCI to AD at 2 and 3 years before diagnosis of AD (and up to 87% accuracy, five years before diagnosis) [15]. While these results were promising, conversion to AD as a categoricaldiagnosis may be too late an event when testing new neuroprotective therapies.…”

Section: Introductionmentioning

confidence: 90%

See 2 more Smart Citations

Automatic Prediction of Cognitive and Functional Decline Can Significantly Decrease the Number of Subjects Required for Clinical Trials in Early Alzheimer’s Disease

Shafiee

Dadar

Ducharme

et al. 2021

JAD

Self Cite

View full text Add to dashboard Cite

Background: While both cognitive and magnetic resonance imaging (MRI) data has been used to predict progression in Alzheimer’s disease, heterogeneity between patients makes it challenging to predict the rate of cognitive and functional decline for individual subjects. Objective: To investigate prognostic power of MRI-based biomarkers of medial temporal lobe atrophy and macroscopic tissue change to predict cognitive decline in individual patients in clinical trials of early Alzheimer’s disease. Methods: Data used in this study included 312 patients with mild cognitive impairment from the ADNI dataset with baseline MRI, cerebrospinal fluid amyloid-β, cognitive test scores, and a minimum of two-year follow-up information available. We built a prognostic model using baseline cognitive scores and MRI-based features to determine which subjects remain stable and which functionally decline over 2 and 3-year follow-up periods. Results: Combining both sets of features yields 77%accuracy (81%sensitivity and 75%specificity) to predict cognitive decline at 2 years (74%accuracy at 3 years with 75%sensitivity and 73%specificity). When used to select trial participants, this tool yields a 3.8-fold decrease in the required sample size for a 2-year study (2.8-fold decrease for a 3-year study) for a hypothesized 25%treatment effect to reduce cognitive decline. Conclusion: When used in clinical trials for cohort enrichment, this tool could accelerate development of new treatments by significantly increasing statistical power to detect differences in cognitive decline between arms. In addition, detection of future decline can help clinicians improve patient management strategies that will slow or delay symptom progression.

show abstract

Section: Discussionsupporting

confidence: 55%

Section: Discussionmentioning

confidence: 59%

Section: Introductionmentioning

confidence: 90%

See 1 more Smart Citation

Automatic Prediction of Cognitive and Functional Decline Can Significantly Decrease the Number of Subjects Required for Clinical Trials in Early Alzheimer’s Disease

Shafiee

Dadar

Ducharme

et al. 2021

JAD

Self Cite

View full text Add to dashboard Cite

show abstract

“…These processing methods have previously shown patterns of atrophy in cognitively normal, MCI, dementia, and neurodegenerative disease populations, including ADNI (37)(38)(39)(40). These techniques thus have the required sensitivity to reveal group differences between SCD-and SCD+.…”

Section: Discussionmentioning

confidence: 99%

Regional atrophy and cognitive decline depend on definition of subjective cognitive decline

Morrison

Dadar

Shafiee

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundPeople with subjective cognitive decline (SCD) may be at increased risk for Alzheimer’s disease (AD). However, not all studies have observed this increased risk. Inconsistencies may be related to different methods used to define SCD. The current project examined whether four methods of defining SCD (applied to the same sample) results in different patterns of atrophy and future cognitive decline between cognitively normal older adults with (SCD+) and without SCD (SCD-).MethodsMRI scans and questionnaire data for 273 cognitively normal older adults from Alzheimer’s Disease Neuroimaging Initiative were examined. To operationalize SCD we used four common methods: Cognitive Change Index (CCI), Everyday Cognition Scale (ECog), ECog + Worry, and Worry only. A previously validated MRI analysis method (SNIPE) was used to measure hippocampal volume and grading. Deformation-based morphometry was performed to examine volume at regions known to be vulnerable to AD. Logistic regressions were completed to determine whether diagnostic method was associated with volume differences between SCD- and SCD+. Linear mixed effects models were performed to examine the relationship between the definitions of SCD and future cognitive decline.ResultsResults varied between the four methods of defining SCD. Left hippocampal grading was lower in SCD+ than SCD-when using the CCI (p=.041) and Worry (p=.021) definitions. The right (p=.008) and left (p=.003) superior temporal regions were smaller in SCD+ than SCD-, but only with the ECog. SCD+ was associated with greater future cognitive decline measured by Alzheimer’s Disease Assessment Scale, but only with the CCI definition. In contrast, only the ECog definition of SCD was associated with future decline on the Montreal Cognitive Assessment.ConclusionThe current findings suggest that the various methods used to differentiate between SCD- and SCD+ influence whether volume differences and findings of cognitive decline are observed between groups in this retrospective analysis.

show abstract

“…Several studies have analyzed the role of ADAS-Cog scores in the evaluation of AD, as well as the relationship between ADAS-Cog and MRI ( [25]- [30], [66], [67]). For instance, Wang et al [66] proposed a multitask exclusive relationship learning model to automatically capture the intrinsic relationship among tasks at different time points for estimating clinical measures based on longitudinal imaging data.…”

Section: Discussionmentioning

confidence: 99%

Comparison of single and multitask learning for predicting cognitive decline based on MRI data

Imani¹,

Prakash²,

Zare³

et al. 2021

Preprint

View full text Add to dashboard Cite

The Alzheimer's Disease Assessment Scale-Cognitive subscale (ADAS-Cog) is a neuropsychological tool that has been designed to assess the severity of cognitive symptoms of dementia. Personalized prediction of the changes in ADAS-Cog scores could help in timing therapeutic interventions in dementia and at-risk populations. In the present work, we compared single and multitask learning approaches to predict the changes in ADAS-Cog scores based on T1-weighted anatomical magnetic resonance imaging (MRI). In contrast to most machine learning-based prediction methods ADAS-Cog changes, we stratified the subjects based on their baseline diagnoses and evaluated the prediction performances in each group. Our experiments indicated a positive relationship between the predicted and observed ADAS-Cog score changes in each diagnostic group, suggesting that T1-weighted MRI has a predictive value for evaluating cognitive decline in the entire AD continuum. We further studied whether correction of the differences in the magnetic field strength of MRI would improve the ADAS-Cog score prediction. The partial least square-based domain adaptation slightly improved the prediction performance, but the improvement was marginal. In summary, this study demonstrated that ADAS-Cog change could be, to some extent, predicted based on anatomical MRI. Based on this study, the recommended method for learning the predictive models is a single-task regularized linear regression due to its simplicity and good performance. It appears important to combine the training data across all subject groups for the most effective predictive models.

show abstract

MRI and cognitive scores complement each other to accurately predict Alzheimer’s dementia 2 to 7 years before clinical onset

Cited by 5 publications

References 27 publications

Automatic Prediction of Cognitive and Functional Decline Can Significantly Decrease the Number of Subjects Required for Clinical Trials in Early Alzheimer’s Disease

Automatic Prediction of Cognitive and Functional Decline Can Significantly Decrease the Number of Subjects Required for Clinical Trials in Early Alzheimer’s Disease

Regional atrophy and cognitive decline depend on definition of subjective cognitive decline

Comparison of single and multitask learning for predicting cognitive decline based on MRI data

Contact Info

Product

Resources

About