Dementia Risk Prediction Project logo

DRPP at AHA Epi Lifestyle 2025

March 2025

The DRPP was well represented at the AHA Epi Lifestyle conference in New Orleans, Louisiana, this spring.

Dr. Sanaz Sedeghat gave an excellent oral presentation on the associations of cardiovascular risk factors across young adulthood, midlife, and late life with dementia incidence. Ash Saravanan, a student investigator on the Early Onset Dementia Ancillary Study, presented her work titled “Traumatic Brain Injury and Risk of Early Onset Dementia: A Population-Based Cohort Study and Meta-analysis” at a poster session. 

psHarmonize package in CRAN

January 2025

The psHarmonize package has been published by CRAN.

To read more about the psHarmonize R package, follow the link to the cran.r-project website: psHarmonize

psHarmonize Paper Published

June 2024

Our team has developed an R package ‘psHarmonize’ to streamline data harmonization and support both reproducibility and accuracy. The primary function, ‘harmonization’, uses a harmonization sheet imported from .xlsx format as input into an R function. The structured file catalogs variable names and domains in a source data set, provides R code instructions for the systematic mapping or conversion of source variables to harmonized variables, specifies the variable name to be used in the harmonized data set, and tracks notes. This function completes all harmonization according to the instructions provided and is accomplished through concise R code. The approach results in a human readable .xlsx file of harmonization instructions that can be reproducibly executed in R.

The full paper can be found here: psHarmonize Paper

AHA Epi Lifestyle Conference 2024

March 2024

The Dementia Risk Prediction Pooling Project was well presented at the AHA Epi Lifestyle conference this Spring. Several team members presented their work using DRPP data. Katherine Giorgio gave a moderated poster presentation on the patterns of early-onset and late-onset dementia incidence within the DRPP,  Natalia Lakomski had a poster presentation on the association between APOE genotype and dementia risk, and Joanne Li gave an oral presentation on the midlife and late-life population attributable fractions of risk factors for dementia in the United States. 

We are excited to share more of the work the DRPP team is doing in the future!

Cohort Profile Published

February 2024

The DRPP team is excited to announce that our first manuscript has been published in the International Journal of Epidemiology! The DRPP Cohort Profile paper details the variables that have been measured, number of participants, person years of follow-up time, and location of each of the 16 cohorts involved in DRPP. In addition, this paper touches on findings such as mean total cholesterol trends by age and cohort, patterns of disease over time, and dementia rate per 1,000 person-years, by age and cohort. 

Interested in reading more? Cohort Profile Paper

Early Onset Ancillary Study & Addition of UK Biobank

September 2023

The Dementia Risk Prediction Project is growing.

Early onset Alzheimer’s Disease and Related Dementias (ADRD), defined as an ADRD diagnosis before age 65, is a particularly devastating disease that is widely understudied. Using the infrastructure of DRPP, our team will soon be conducting a prospective study on early onset ADRD, which will include four eligible participating studies (ARIC, MESA, FHS and Whitehall II) as well as data from UK Biobank (total participants n~550,000). Findings of this study will shed light on the magnitude of early onset ADRD disease burden and identify risk factors for this disease which may lead to development of more effective preventive strategies to delay the onset of early onset ADRD.

Alzheimer's Association International Conference 2023

July 2023

Kevin Yu, a doctoral student on the DRPP team, presented his research on the use of Machine Learning (ML) to model dementia risk prediction at the 2023 AAIC. The purpose of Kevin’s research is that “Although ML models have been used to create accurate prediction models for dementia, many suffer from overfitting and external validation that often results in decreased performance. Pooling data from various sources for model training can improve the generalizability of prediction models.” These models were developed using pooled data from the Dementia Risk Prediction Pooling (DRPP) Consortium.