Detection of Dementia Signals from Longitudinal Clinical Visits Using One-Class Classification

Causal Explanation from Mild Cognitive Impairment Progression using Graph Neural Networks

Mild Cognitive Impairment (MCI) is a transitional stage between normal cognitive aging and dementia. Some individuals with MCI revert to normal, while others progress to dementia. There are limited studies using explainable artificial intelligence on longitudinal data, particularly including genotypes, biomarkers and chronic diseases, to explore these differences. This study introduces a novel approach to understanding MCI progression using explainable graph neural networks. Utilizing longitudinal temporal data, we constructed a comprehensive graph representation of each individual in the study cohort. Our temporal graph convolutional network achieved 72.4% accuracy in predicting MCI transitions, while our causal explanation method outperformed existing explanation techniques in stability, accuracy, and faithfulness. We identified a causal subgraph with informative variables including hypertension, arrhythmia, congestive heart failure, coronary artery disease, stroke, lipid-related issues, and sex.

Characterizing the progression from mild cognitive impairment to dementia: a network analysis of longitudinal clinical visits

BACKGROUND

With the recent surge in the utilization of electronic health records for cognitive decline, the research community has turned its attention to conducting fine-grained analyses of dementia onset using advanced techniques. Previous works have mostly focused on machine learning-based prediction of dementia, lacking the analysis of dementia progression and its associations with risk factors over time. The black box nature of machine learning models has also raised concerns regarding their uncertainty and safety in decision making, particularly in sensitive domains like healthcare.

OBJECTIVE

We aimed to characterize the progression of health conditions, such as chronic diseases and neuropsychiatric symptoms, of the participants in Mayo Clinic Study of Aging (MCSA) from initial mild cognitive impairment (MCI) diagnosis to dementia onset through network analysis.

METHODS

We used the data from the MCSA, a prospective population-based cohort study of cognitive aging, and examined the changing association among variables (i.e., participants' health conditions) from the first visit of MCI diagnosis to the visit of dementia onset using network analysis. The number of participants for this study are 97 with the number of visits ranging from 2 visits (30 months) to 7 visits (105 months). We identified the network communities among variables from three-fold collection of instances: (i) the first MCI diagnosis, (ii) progression to dementia, and (iii) dementia diagnosis. We determine the variables that play a significant role in the dementia onset, aiming to identify and prioritize specific variables that prominently contribute towards developing dementia. In addition, we explore the sex-specific impact of variables in relation to dementia, aiming to investigate potential differences in the influence of certain variables on dementia onset between males and females.

RESULTS

We found correlation among certain variables, such as neuropsychiatric symptoms and chronic conditions, throughout the progression from MCI to dementia. Our findings, based on patterns and changing variables within specific communities, reveal notable insights about the time-lapse before dementia sets in, and the significance of progression of correlated variables contributing towards dementia onset. We also observed more changes due to certain variables, such as cognitive and functional scores, in the network communities for the people who progressed to dementia compared to those who does not. Most changes for sex-specific analysis are observed in clinical dementia rating and functional activities questionnaire during MCI onset are followed by chronic diseases, and then by NPI-Q scores.

CONCLUSIONS

Network analysis has shown promising potential to capture significant longitudinal changes in health conditions, spanning from the MCI diagnosis to dementia progression. It can serve as a valuable analytic approach for monitoring the health status of individuals in cognitive impairment assessment. Furthermore, our findings indicate a notable sex difference in the impact of specific health conditions on the progression of dementia.

Dementia Prediction in Older Adults Using Sex-Specific Health Trajectory Clustering

With increasing number of people living with dementia, the problem of late diagnosis significantly impacts a person's quality of life while early signs of dementia may provide useful insights to facilitate better treatment plans. With time, this progressive neurodegenerative syndrome could progress from mild cognitive impairment to dementia. A pattern of health conditions can be characterized in unsupervised manner to help predict this progress. As a significant extension to our previous work with streaming clustering model, we consider additional information for predicting dementia onset. With empirical observations, we discover the importance of examining sex and age to predict dementia onset. To this end, we propose a sex-specific model with age-constraint for predicting dementia onset and validate the effectiveness of our models using data from Mayo Clinic Study of Aging (MCSA). The proposed sex-specific models for older adult populations (>=65 years of age) outperformed the previous models with F-score of 77% and 78% for male-specific and female-specific models, respectively. Our experiments of sex-specific temporal clustering of features in older adults demonstrate the potential of more personalized models for early alerts of dementia.