Dataset Information

Influence of Subject-Specific Effects in Longitudinal Modelling of Cognitive Decline in Alzheimer's Disease.

ABSTRACT:

Background

Accurate longitudinal modelling of cognitive decline is a major goal of Alzheimer's disease and related dementia (ADRD) research. However, the impact of subject-specific effects is not well characterized and may have implications for data generation and prediction.

Objective

This study seeks to address the impact of subject-specific effects, which are a less well-characterized aspect of ADRD cognitive decline, as measured by the Alzheimer's Disease Assessment Scale's Cognitive Subscale (ADAS-Cog).

Methods

Prediction errors and biases for the ADAS-Cog subscale were evaluated when using only population-level effects, robust imputation of subject-specific effects using model covariances, and directly known individual-level effects fit during modelling as a natural control. Evaluated models included pre-specified parameterizations for clinical trial simulation, analogous mixed-effects regression models parameterized directly, and random forest ensemble models. Assessment used a meta-database of Alzheimer's disease studies with validation in simulated synthetic cohorts.

Results

All models observed increases in variance under imputation leading to increased prediction error. Bias decreased with imputation except under the pre-specified parameterization, which increased in the meta-database, but was attenuated under simulation. Known fitted subject effects gave the best prediction results.

Conclusion

Subject-specific effects were found to have a profound impact on predicting ADAS-Cog. Reductions in bias suggest imputing random effects assists in calculating results on average, as when simulating clinical trials. However, reduction in error emphasizes population-level effects when attempting to predict outcomes for individuals. Forecasting future observations greatly benefits from using known subject-specific effects.

SUBMITTER: Murchison CF

PROVIDER: S-EPMC9198753 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Alzheimer's disease (AD) is characterised by a dynamic process of neurocognitive changes from normal cognition to mild cognitive impairment (MCI) and progression to dementia. However, not all individuals with MCI develop dementia. Predicting whether individuals with MCI will decline (i.e. progressive MCI) or remain stable (i.e. stable MCI) is impeded by patient heterogeneity due to comorbidities that may lead to MCI diagnosis without progression to AD. Despite the importance of early diagnosis of AD for prognosis and personalised interventions, we still lack robust tools for predicting individual progression to dementia. Here, we propose a novel trajectory modelling approach based on metric learning (Generalised Metric Learning Vector Quantization) that mines multimodal data from MCI patients in the Alzheimer's disease Neuroimaging Initiative (ADNI) cohort to derive individualised prognostic scores of cognitive decline due to AD. We develop an integrated biomarker generation- using partial least squares regression- and classification methodology that extends beyond binary patient classification into discrete subgroups (i.e. stable vs. progressive MCI), determines individual profiles from baseline (i.e. cognitive or biological) data and predicts individual cognitive trajectories (i.e. change in memory scores from baseline). We demonstrate that a metric learning model trained on baseline cognitive data (memory, executive function, affective measurements) discriminates stable vs. progressive MCI individuals with high accuracy (81.4%), revealing an interaction between cognitive (memory, executive functions) and affective scores that may relate to MCI comorbidity (e.g. affective disturbance). Training the model to perform the same binary classification on biological data (mean cortical β-amyloid burden, grey matter density, APOE 4) results in similar prediction accuracy (81.9%). Extending beyond binary classifications, we develop and implement a trajectory modelling approach that shows significantly better performance in predicting individualised rate of future cognitive decline (i.e. change in memory scores from baseline), when the metric learning model is trained with biological (r = -0.68) compared to cognitive (r = -0.4) data. Our trajectory modelling approach reveals interpretable and interoperable markers of progression to AD and has strong potential to guide effective stratification of individuals based on prognostic disease trajectories, reducing MCI patient misclassification, that is critical for clinical practice and discovery of personalised interventions.

Project description:PurposeBiomarkers used for predicting longitudinal cognitive change in Alzheimer's disease (AD) continuum are still elusive. Tau pathology, neuroinflammation, and neurodegeneration are the leading candidate predictors. We aimed to determine these three aspects of biomarkers in cerebrospinal fluid (CSF) and plasma to predict longitudinal cognition status using Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort.Patients and methodsA total of 430 subjects including, 96 cognitive normal (CN) with amyloid β (Aβ)-negative, 54 CN with Aβ-positive, 195 mild cognitive impairment (MCI) with Aβ-positive, and 85 AD with amyloid-positive (Aβ-positive are identified by CSF Aβ42/Aβ40 < 0.138). Aβ burden was evaluated by CSF and plasma Aβ42/Aβ40 ratio; tau pathology was evaluated by CSF and plasma phosphorylated-tau (p-tau181); microglial activation was measured by CSF soluble TREM2 (sTREM2) and progranulin (PGRN); neurodegeneration was measured by CSF and plasma t-tau and structural magnetic resonance imaging (MRI); cognition was examined annually over the subsequent 8 years using the Alzheimer's Disease Assessment Scale Cognition 13-item scale (ADAS13) and Mini-Mental State Exam (MMSE). Linear mixed-effects models (LME) were applied to assess the correlation between biomarkers and longitudinal cognition decline, as well as their effect size on the prediction of longitudinal cognitive decline.ResultsBaseline CSF Aβ42/Aβ40 ratio was decreased in MCI and AD compared to CN, while CSF p-tau181 and t-tau increased. Baseline CSF sTREM2 and PGRN did not show any differences in MCI and AD compared to CN. Baseline brain volumes (including the hippocampal, entorhinal, middle temporal lobe, and whole-brain) decreased in MCI and AD groups. For the longitudinal study, there were significant interaction effects of CSF p-tau181 × time, plasma p-tau181 × time, CSF sTREM2 × time, and brain volumes × time, indicating CSF, and plasma p-tau181, CSF sTREM2, and brain volumes could predict longitudinal cognition deterioration rate. CSF sTREM2, CSF, and plasma p-tau181 had similar medium prediction effects, while brain volumes showed stronger effects in predicting cognition decline.ConclusionOur study reported that baseline CSF sTREM2, CSF, and plasma p-tau181, as well as structural MRI, could predict longitudinal cognitive decline in subjects with positive AD pathology. Plasma p-tau181 can be used as a relatively noninvasive reliable biomarker for AD longitudinal cognition decline prediction.