Survival Analysis in Cognitively Normal Subjects and in Patients with Mild Cognitive Impairment Using a Proportional Hazards Model with Extreme Gradient Boosting Regression

2021 ◽  
pp. 1-14
Author(s):  
Boshra Khajehpiri ◽  
Hamid Abrishami Moghaddam ◽  
Mohamad Forouzanfar ◽  
Reza Lashgari ◽  
Jaime Ramos-Cejudo ◽  
...  
Keyword(s):  
Survival Analysis ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Proportional Hazards ◽  
Risk Estimation ◽  
Linear Predictor ◽  
Cognitively Normal ◽  
Dementia Risk ◽  
Extreme Gradient Boosting ◽  
Non Linear

Background: Evaluating the risk of Alzheimer’s disease (AD) in cognitively normal (CN) and patients with mild cognitive impairment (MCI) is extremely important. While MCI-to-AD progression risk has been studied extensively, few studies estimate CN-to-MCI conversion risk. The Cox proportional hazards (PH), a widely used survival analysis model, assumes a linear predictor-risk relationship. Generalizing the PH model to more complex predictor-risk relationships may increase risk estimation accuracy. Objective: The aim of this study was to develop a PH model using an Xgboost regressor, based on demographic, genetic, neuropsychiatric, and neuroimaging predictors to estimate risk of AD in patients with MCI, and the risk of MCI in CN subjects. Methods: We replaced the Cox PH linear model with an Xgboost regressor to capture complex interactions between predictors, and non-linear predictor-risk associations. We endeavored to limit model inputs to noninvasive and more widely available predictors in order to facilitate future applicability in a wider setting. Results: In MCI-to-AD (n = 882), the Xgboost model achieved a concordance index (C-index) of 84.5%. When the model was used for MCI risk prediction in CN (n = 100) individuals, the C-index was 73.3%. In both applications, the C-index was statistically significantly higher in the Xgboost in comparison to the Cox PH model. Conclusion: Using non-linear regressors such as Xgboost improves AD dementia risk assessment in CN and MCI. It is possible to achieve reasonable risk stratification using predictors that are relatively low-cost in terms of time, invasiveness, and availability. Future strategies for improving AD dementia risk estimation are discussed.

scholarly journals The Risk of Incident Mild Cognitive Impairment and Progression to Dementia Considering Mild Cognitive Impairment Subtypes

2017 ◽  
Vol 7 (1) ◽  
pp. 15-29 ◽  
Author(s):  
Tzeyu L. Michaud ◽  
Dejun Su ◽  
Mohammad Siahpush ◽  
Daniel L. Murman
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Proportional Hazards ◽  
Normal Subjects ◽  
Cox Proportional Hazards ◽  
Cognitively Normal ◽  
Apoe Ε4 ◽  
Cox Proportional Hazards Models ◽  
Ε4 Allele ◽  
Cognitively Normal Subjects

Background: It remains unclear how demographic and clinical characteristics are related to the risk of incident mild cognitive impairment (MCI) by its subtypes. Moreover, the contribution of the subtypes of incident MCI to the progression to dementia remains puzzling. Methods: We used data collected by the National Alzheimer Coordinating Center. Our analysis sample included cognitively normal subjects at baseline. The associations were examined using competing-risks survival regression models and Cox proportional hazards models. Results: About 16.3% of subjects developed incident MCI of whom 15.8% progressed to Alz­heimer disease (overall mean follow-up of 4.3 years). The risk of incident amnestic MCI (aMCI) was greater in subjects with 1 copy (subhazard ratio [SHR]: 1.23; 95% CI: 1.00–1.50) or 2 copies (SHR: 2.14; 95% CI: 1.49–3.05) of the APOE ε4 allele than in those who had no ε4 allele. Multiple-domain aMCI patients were more likely to progress to dementia than single-domain aMCI patients (hazard ratio: 2.14; 95% CI: 1.28–3.58). Conclusions: Cognitively normal subjects with an APOE ε4 allele had a higher likelihood of developing aMCI and the MCI subtype was associated with the dementia subtype. Our findings provide important information about practical indicators for the prediction of cognitive decline.

Biomarker-Based Risk Prediction of Alzheimer’s Disease Dementia in Mild Cognitive Impairment: Psychosocial, Ethical, and Legal Aspects

2021 ◽  
Vol 80 (2) ◽  
pp. 601-617
Author(s):  
Ayda Rostamzadeh ◽  
Carolin Schwegler ◽  
Silvia Gil-Navarro ◽  
Maitée Rosende-Roca ◽  
Vanessa Romotzky ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Risk Prediction ◽  
Risk Estimation ◽  
Legal Framework ◽  
Risk Disclosure ◽  
Health Lifestyle ◽  
Dementia Risk

Background: Today, a growing number of individuals with mild cognitive impairment (MCI) wish to assess their risk of developing Alzheimer’s disease (AD) dementia. The expectations as well as the effects on quality of life (QoL) in MCI patients and their close others through biomarker-based dementia risk estimation are not well studied. Objective: The PreDADQoL project aims at providing empirical data on effects of such prediction on QoL and at developing an ethical and legal framework of biomarker-based dementia risk estimation in MCI. Methods: In the empirical study, 100 MCI-patients and their close others will be recruited from two sites (Germany and Spain). They receive standardized counselling on cerebrospinal fluid (CSF) biomarker-based prediction of AD dementia and a risk disclosure based on their AD biomarker status. A mixed methods approach will be applied to assess outcomes. Results: The pilot-study yielded a specification of the research topics and newly developed questionnaires for the main assessment. Within this binational quantitative and qualitative study, data on attitudes and expectations toward AD risk prediction, QoL, risk communication, coping strategies, mental health, lifestyle changes, and healthcare resource utilization will be obtained. Together with the normative part of the project, an empirically informed ethical and legal framework for biomarker-based dementia risk estimation will be developed. Conclusion: The empirical research of the PreDADQoL study together with the ethical and legal considerations and implications will help to improve the process of counselling and risk disclosure and thereby positively affect QoL and health of MCI-patients and their close others in the context of biomarker-based dementia risk estimation.

scholarly journals Lower functional hippocampal redundancy in mild cognitive impairment

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Stephanie Langella ◽  
◽  
Muhammad Usman Sadiq ◽  
Peter J. Mucha ◽  
Kelly S. Giovanello ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Decline ◽  
Resting State ◽  
Memory Performance ◽  
Potential Mechanism ◽  
Network Efficiency ◽  
Cognitively Normal ◽  
Normal Individuals ◽  
The Relationship

AbstractWith an increasing prevalence of mild cognitive impairment (MCI) and Alzheimer’s disease (AD) in response to an aging population, it is critical to identify and understand neuroprotective mechanisms against cognitive decline. One potential mechanism is redundancy: the existence of duplicate elements within a system that provide alternative functionality in case of failure. As the hippocampus is one of the earliest sites affected by AD pathology, we hypothesized that functional hippocampal redundancy is protective against cognitive decline. We compared hippocampal functional redundancy derived from resting-state functional MRI networks in cognitively normal older adults, with individuals with early and late MCI, as well as the relationship between redundancy and cognition. Posterior hippocampal redundancy was reduced between cognitively normal and MCI groups, plateauing across early and late MCI. Higher hippocampal redundancy was related to better memory performance only for cognitively normal individuals. Critically, functional hippocampal redundancy did not come at the expense of network efficiency. Our results provide support that hippocampal redundancy protects against cognitive decline in aging.

scholarly journals Financial Capacity and Regional Cerebral Tau in Cognitively Normal Older Adults, Mild Cognitive Impairment, and Alzheimer’s Disease Dementia

2020 ◽  
pp. 1-10
Author(s):  
Christopher Gonzalez ◽  
Nicole S. Tommasi ◽  
Danielle Briggs ◽  
Michael J. Properzi ◽  
Rebecca E. Amariglio ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Older Adults ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Early Stage ◽  
Cognitively Normal ◽  
Financial Capacity ◽  
Posterior Cingulate ◽  
Dorsolateral Prefrontal

Background: Financial capacity is often one of the first instrumental activities of daily living to be affected in cognitively normal (CN) older adults who later progress to amnestic mild cognitive impairment (MCI) and Alzheimer’s disease (AD) dementia. Objective: The objective of this study was to investigate the association between financial capacity and regional cerebral tau. Methods: Cross-sectional financial capacity was assessed using the Financial Capacity Instrument –Short Form (FCI-SF) in 410 CN, 199 MCI, and 61 AD dementia participants who underwent flortaucipir tau positron emission tomography from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Linear regression models with backward elimination were used with FCI-SF total score as the dependent variable and regional tau and tau-amyloid interaction as predictors of interest in separate analyses. Education, age sex, Rey Auditory Verbal Learning Test Total Learning, and Trail Making Test B were used as covariates. Results: Significant associations were found between FCI-SF and tau regions (entorhinal: p <  0.001; inferior temporal: p <  0.001; dorsolateral prefrontal: p = 0.01; posterior cingulate: p = 0.03; precuneus: p <  0.001; and supramarginal gyrus: p = 0.005) across all participants. For the tau-amyloid interaction, significant associations were found in four regions (amyloid and dorsolateral prefrontal tau interaction: p = 0.005; amyloid and posterior cingulate tau interaction: p = 0.005; amyloid and precuneus tau interaction: p <  0.001; and amyloid and supramarginal tau interaction: p = 0.002). Conclusion: Greater regional tau burden was modestly associated with financial capacity impairment in early-stage AD. Extending this work with longitudinal analyses will further illustrate the utility of such assessments in detecting clinically meaningful decline, which may aid clinical trials of early-stage AD.

scholarly journals Depressive symptoms in relation to clinical symptom onset of mild cognitive impairment

2018 ◽  
Vol 31 (04) ◽  
pp. 561-569 ◽  
Author(s):  
Carol K. Chan ◽  
Anja Soldan ◽  
Corinne Pettigrew ◽  
Mei-Cheng Wang ◽  
Jiangxia Wang ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Depressive Symptoms ◽  
Mild Cognitive Impairment ◽  
Clinical Symptom ◽  
Symptom Onset ◽  
Symptom Severity ◽  
Hamilton Depression Scale ◽  
Cognitively Normal ◽  
Increased Risk ◽  
Time To Onset

ABSTRACTObjective:There is increasing evidence of an association between depressive symptoms and mild cognitive impairment (MCI) in cross-sectional studies, but the longitudinal association between depressive symptoms and risk of MCI onset is less clear. The authors investigated whether baseline symptom severity of depression was predictive of time to onset of symptoms of MCI.Method:These analyses included 300 participants from the BIOCARD study, a cohort of individuals who were cognitively normal at baseline (mean age = 57.4 years) and followed for up to 20 years (mean follow-up = 2.5 years). Depression symptom severity was measured using the Hamilton Depression Scale (HAM-D). The authors assessed the association between dichotomous and continuous HAM-D and time to onset of MCI within 7 years versus after 7 years from baseline (reflecting the mean time from baseline to onset of clinical symptoms in the cohort) using Cox regression models adjusted for gender, age, and education.Results:At baseline, subjects had a mean HAM-D score of 2.2 (SD = 2.8). Higher baseline HAM-D scores were associated with an increased risk of progression from normal cognition to clinical symptom onset ≤ 7 years from baseline (p= 0.043), but not with progression &gt; 7 years from baseline (p= 0.194). These findings remained significant after adjustment for baseline cognition.Conclusions:These results suggest that low levels of depressive symptoms may be predictive of clinical symptom onset within approximately 7 years among cognitively normal individuals and may be useful in identifying persons at risk for MCI due to Alzheimer’s disease.

scholarly journals 12-year prediction of mild cognitive impairment aided by Alzheimer’s brain signatures at mean age 56

2021 ◽  
Author(s):  
McKenna E Williams ◽  
Jeremy A Elman ◽  
Linda K McEvoy ◽  
Ole A Andreassen ◽  
Anders M Dale ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Mean Diffusivity ◽  
Area Under The Curve ◽  
Polygenic Risk Score ◽  
Age Difference ◽  
Cognitively Normal ◽  
Brain Age

Abstract Neuroimaging signatures based on composite scores of cortical thickness and hippocampal volume predict progression from mild cognitive impairment to Alzheimer’s disease. However, little is known about the ability of these signatures among cognitively normal adults to predict progression to mild cognitive impairment. Toward that end, a signature sensitive to microstructural changes that may predate macrostructural atrophy should be useful. We hypothesized that: 1) a validated MRI-derived Alzheimer’s disease signature based on cortical thickness and hippocampal volume in cognitively normal middle-aged adults would predict progression to mild cognitive impairment; and 2) a novel gray matter mean diffusivity signature would be a better predictor than the thickness/volume signature. This cohort study was part of the Vietnam Era Twin Study of Aging. Concurrent analyses compared cognitively normal and mild cognitive impairment groups at each of three study waves (ns = 246–367). Predictive analyses included 169 cognitively normal men at baseline (age = 56.1, range = 51–60). Our previously published thickness/volume signature derived from independent data, a novel mean diffusivity signature using the same regions and weights as the thickness/volume signature, age, and an Alzheimer’s disease polygenic risk score were used to predict incident mild cognitive impairment an average of 12 years after baseline (follow-up age = 67.2, range = 61–71). Additional analyses adjusted for predicted brain age difference scores (chronological age minus predicted brain age) to determine if signatures were Alzheimer-related and not simply aging-related. In concurrent analyses, individuals with mild cognitive impairment had higher (worse) mean diffusivity signature scores than cognitively normal participants, but thickness/volume signature scores did not differ between groups. In predictive analyses, age and polygenic risk score yielded an area under the curve of 0.74 (sensitivity = 80.00%; specificity = 65.10%). Prediction was significantly improved with addition of the mean diffusivity signature (area under the curve = 0.83; sensitivity = 85.00%; specificity = 77.85%; P=0.007), but not with addition of the thickness/volume signature. A model including both signatures did not improve prediction over a model with only the mean diffusivity signature. Results held up after adjusting for predicted brain age difference scores. The novel mean diffusivity signature was limited by being yoked to the thickness/volume signature weightings. An independently-derived mean diffusivity signature may thus provide even stronger prediction. The young age of the sample at baseline is particularly notable. Given that the brain signatures were examined when participants were only in their 50 s, our results suggest a promising step toward improving very early identification of Alzheimer’s disease risk and the potential value of mean diffusivity and/or multimodal brain signatures.

scholarly journals Modifiable Factors Associated with Reversion from Mild Cognitive Impairment to Cognitively Normal Status: A Prospective Cohort Study

2021 ◽  
Author(s):  
Feng Sha ◽  
Ziyi Zhao ◽  
Chang Wei ◽  
Zhirong Yang ◽  
Bingyu Li
Keyword(s):  
Cohort Study ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Psychological Factors ◽  
Large Scale ◽  
Cox Regression ◽  
Lifestyle Factors ◽  
Cognitively Normal ◽  
Factors Associated ◽  
Modifiable Factors

Abstract Background Previous studies found that about 24% of the mild cognitive impairment (MCI) patients reverse to cognitively normal (CN) status. However, it is unclear which modifiable factors are associated with this reversion. Method We conducted a prospective community-based cohort study based on 2002-2018 Chinese Longitudinal Health Longevity Survey (CLHLS). Of 35,474 older adults from 22 provinces in China in the 5 waves of CLHLS, 7,422 eligible participants with MCI were included. Multivariable Cox regression with least absolute shrinkage and selection operator (LASSO) penalty for variable selection was adopted to investigate the associations between reversion to CN and potential modifiable dietary/lifestyle, cardiometabolic, and psychological factors. Results Our analysis included 7,422 MCI participants [average age: 90.0 (SD 9.5) years]. Among these participants, 1,604 (21.6%) reversed from MCI to CN with a mean (SD) follow-up of 2.9 (1.8) years. Several dietary/lifestyle factors, including daily consumption of fresh fruits (Hazard Ratio [HR]: 1.28, 95% CI: 1.15 to 1.42; P༜.001), engagement in reading (HR: 1.24, 95% CI: 1.00 to 1.54; P =.047), housework (HR: 1.21, 95% CI: 1.08 to 1.35; P =.001), and mah-jong or other card games (HR: 1.23, 95% CI: 1.08 to 1.39; P =.001), were positively associated with possibility of reversion. Cigarette smoking (HR: 0.92, 95% CI: 0.84 to 1.00; P= .041) and duration of alcohol drinking (HR: 0.97, 95% CI: 0.94 to 0.99; P = .012) were negatively associated with possibility of reversion. None of the modifiable cardiometabolic and psychological factors was found to be significantly associated with reversion to CN. Difference was identified among different age and gender group. Conclusion This study identified several dietary/lifestyle factors associated with MCI reversion that may transfer into large-scale dementia prevention practices.

Sign in / Sign up

Export Citation Format

Share Document