Comparison of feature representations in MRI-based MCI-to-AD conversion prediction

Gómez-Sancho, Marta; Tohka, Jussi; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1016/j.mri.2018.03.003

Cited by 33 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Broad spectra of individual anatomical differences, cognitive reserve, and varieties in brain structural changes exist due to normal aging compared to that of neurodegenerative diseases. Therefore, separating patients with MCI from cognitively nonimpaired individuals based exclusively on structural MRI is difficult (Gómez-Sancho et al, 2018 ). More research in this field have been recommend by the Geneva Task Force for the Roadmap of Alzheimer's Biomarkers (Ten Kate et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Cognitive Profiles and Atrophy Ratings on MRI in Senior Patients With Mild Cognitive Impairment

Flak

Hol

Hernes

et al. 2018

Front. Aging Neurosci.

View full text Add to dashboard Cite

In this cross-sectional study, we sought to describe cognitive and neuroimaging profiles of Memory clinic patients with Mild Cognitive Impairment (MCI). 51 MCI patients and 51 controls, matched on age, sex, and socio-economic status (SES), were assessed with an extensive neuropsychological test battery that included a measure of intelligence (General Ability Index, “GAI,” from WAIS-IV), and structural magnetic resonance imaging (MRI). MCI subtypes were determined after inclusion, and z-scores normalized to our control group were generated for each cognitive domain in each MCI participant. MR-images were scored by visual rating scales. MCI patients performed significantly worse than controls on 23 of 31 cognitive measures (Bonferroni corrected p = 0.001), and on 8 of 31 measures after covarying for intelligence (GAI). Compared to nonamnestic MCI patients, amnestic MCI patients had lower test results in 13 of 31 measures, and 5 of 31 measures after co-varying for GAI. Compared to controls, the MCI patients had greater atrophy on Schelten's Medial temporal lobe atrophy score (MTA), especially in those with amnestic MCI. The only structure-function correlation that remained significant after correction for multiple comparisons was the MTA—long delay recall domain. Intelligence operationalized as GAI appears to be an important moderator of the neuropsychological outcomes. Atrophy of the medial temporal lobe, based on MTA scores, may be a sensitive biomarker for the functional episodic memory deficits associated with MCI.

show abstract

Section: Introductionmentioning

confidence: 99%

Cognitive Profiles and Atrophy Ratings on MRI in Senior Patients With Mild Cognitive Impairment

Flak

Hol

Hernes

et al. 2018

Front. Aging Neurosci.

View full text Add to dashboard Cite

show abstract

“…The reported AUC performance of the methods ranged from 0.67 to 0.73 for their potential to detect patients at risk of conversion. This performance was slightly lower to other methods based on SVM or Logistic Regression classifiers [46]. To test the impact of using all subjects in ROC AUC analysis, we conducted a post hoc experiment.…”

Section: A ML Methods Validationmentioning

confidence: 93%

Exploring Survival Models Associated with MCI to AD Conversion: A Machine Learning Approach

Orozco-Sanchez

Treviño

Martinez-Ledesma

et al. 2019

Preprint

View full text Add to dashboard Cite

Several studies have documented that structural MRI findings are associated with the presence of earlystage Alzheimer Disease (AD). However, the association of each MRI feature with the rate of conversion from mild cognitive impairment (MCI) to AD in a multivariate setting has not been studied fully. The objective of this work is the comprehensive exploration of four different machine learning (ML) strategies to build MRI-based multivariate Cox regression models. These models evaluated the association of MRI features with the time of MCI to clinical AD conversion. We used 442 MCI subjects from the Alzheimer's disease Neuroimaging Initiative (ADNI) study. Each subject was described by 346 MRI features and time to AD conversion. Cox regression models then estimated the rate of conversion. Models were built using four ML methodologies in a cross-validation (CV) setting. All the ML methods returned successful Cox models with different CV performances. The best model exhibited a concordance index of 0.84 (95% CI: 0.82-0.86). The final analysis described the hazard ratios (HR) of the top ten MRI features associated with MCI to AD conversion. Our results suggest ML exploration is a viable strategy for building and analyzing survival models that predict subjects at risk of AD conversion.

show abstract

“…As MRI features, we used 9 features: intracranial volume (ICV), and volumes of the hippocampus, entorhinal cortex, and lateral ventricles as well as the latter four divided by the ICV. These features were selected based on previous studies [25]. We included volumes divided by the ICV as it is unclear whether raw or ICV-corrected volumes are better predictors of dementia [25,26].…”

Section: Mrimentioning

confidence: 99%

“…These features were selected based on previous studies [25]. We included volumes divided by the ICV as it is unclear whether raw or ICV-corrected volumes are better predictors of dementia [25,26]. MR imaging protocol details are provided by ADNI at http://adni.loni.usc.edu/methods/mri-tool/mri-analysis/.…”

Section: Mrimentioning

confidence: 99%

Quantitative Longitudinal Predictions of Alzheimer’s Disease by Multi-Modal Predictive Learning

Prakash

Abdelaziz

Zhang

et al. 2021

JAD

Self Cite

View full text Add to dashboard Cite

Background: Quantitatively predicting the progression of Alzheimer’s disease (AD) in an individual on a continuous scale, such as the Alzheimer’s Disease Assessment Scale-cognitive (ADAS-cog) scores, is informative for a personalized approach as opposed to qualitatively classifying the individual into a broad disease category. Objective: To evaluate the hypothesis that the multi-modal data and predictive learning models can be employed for future predicting ADAS-cog scores. Methods: Unimodal and multi-modal regression models were trained on baseline data comprised of demographics, neuroimaging, and cerebrospinal fluid based markers, and genetic factors to predict future ADAS-cog scores for 12, 24, and 36 months. We subjected the prediction models to repeated cross-validation and assessed the resulting mean absolute error (MAE) and cross-validated correlation (ρ) of the model. Results: Prediction models trained on multi-modal data outperformed the models trained on single modal data in predicting future ADAS-cog scores (MAE12, 24 & 36 months= 4.1, 4.5, and 5.0, ρ 12, 24 & 36 months= 0.88, 0.82, and 0.75). Including baseline ADAS-cog scores to prediction models improved predictive performance (MAE12, 24 & 36 months= 3.5, 3.7, and 4.6, ρ 12, 24 & 36 months= 0.89, 0.87, and 0.80). Conclusion: Future ADAS-cog scores were predicted which could aid clinicians in identifying those at greater risk of decline and apply interventions at an earlier disease stage and inform likely future disease progression in individuals enrolled in AD clinical trials.

show abstract

Comparison of feature representations in MRI-based MCI-to-AD conversion prediction

Cited by 33 publications

References 45 publications

Cognitive Profiles and Atrophy Ratings on MRI in Senior Patients With Mild Cognitive Impairment

Cognitive Profiles and Atrophy Ratings on MRI in Senior Patients With Mild Cognitive Impairment

Exploring Survival Models Associated with MCI to AD Conversion: A Machine Learning Approach

Quantitative Longitudinal Predictions of Alzheimer’s Disease by Multi-Modal Predictive Learning

Contact Info

Product

Resources

About