# The influence of midlife morbidity clusters on dementia risk: The ARIC study

## TL;DR

This study shows that midlife health conditions grouped together increase dementia risk, suggesting early interventions could help.

## Contribution

The study introduces a novel use of cluster analysis to identify midlife morbidity patterns linked to dementia risk.

## Key findings

- Midlife clusters like smoking, obesity, and heart conditions are linked to higher dementia risk.
- Cluster analysis reveals distinct morbidity profiles that influence dementia risk.
- The healthiest cluster had the lowest dementia risk compared to other clusters.

## Abstract

Understanding comorbidities’ combined impacts on dementia risk may offer a more comprehensive understanding of individuals’ risk. Using machine‐learning, we grouped individuals with similar midlife risk profiles into clusters and explored associations with dementia risk.

Participants without dementia at baseline (1987–1989) from the prospective Atherosclerosis Risk in Communities (ARIC) study were included (ages 45–64 years; N = 15,250). Using unsupervised hierarchical cluster analysis, nine clusters were created and defined based on 14 midlife morbidities. The associations with incident dementia (N = 3272 cases, median follow‐up 25 years) and deaths (N = 9099) were evaluated using time‐to‐event regression models.

Compared with the healthiest cluster (Cluster 1), Clusters 2 (smoking) (hazard ratio [HR](95% confidence interval [CI]) = 1.62 (1.08, 2.43)), 5 (obesity, diabetes, hypertension, and hypertriglyceridemia) (HR(95%CI) = 1.91 (1.35,2.70)), and 7/8 (atrial fibrillation/heart failure) (HR(95%CI) = 2.69 (1.59,4.57)) were associated with dementia. Accounting for competing risk of death in the Fine‐Gray subdistribution model negated the cluster‐dementia association.

Midlife morbidity clusters are important for dementia and mortality risk.

Cluster analysis is a useful approach to capture complex morbidity patterns in the population.An unsupervised machine learning method yielded nine distinct clusters of morbidities in participants without dementia in the Atherosclerosis Risk in Communities (ARIC) Study cohort.Individuals in clusters defined by current smoking (Cluster 2), obesity, diabetes, hypertension, and hypertriglyceridemia (Cluster 5), or heart failure/atrial fibrillation (Cluster 7/8) in midlife, had a significantly increased risk of dementia compared to those in the healthiest cluster.These findings emphasize the importance of midlife morbidity on dementia risk in older adults, highlighting the potential for targeted early interventions based on clustered morbidity profiles.

Cluster analysis is a useful approach to capture complex morbidity patterns in the population.

An unsupervised machine learning method yielded nine distinct clusters of morbidities in participants without dementia in the Atherosclerosis Risk in Communities (ARIC) Study cohort.

Individuals in clusters defined by current smoking (Cluster 2), obesity, diabetes, hypertension, and hypertriglyceridemia (Cluster 5), or heart failure/atrial fibrillation (Cluster 7/8) in midlife, had a significantly increased risk of dementia compared to those in the healthiest cluster.

These findings emphasize the importance of midlife morbidity on dementia risk in older adults, highlighting the potential for targeted early interventions based on clustered morbidity profiles.