A Prediction Model of Alzheimer's Disease Progression in the Community

Eileen Gamagami, PhD, for Medscape

July 14, 2022

The study covered in this summary was published on medRxiv.org as a preprint and has not yet been peer reviewed.

Key Takeaway

  • Longitudinal Grade of Membership (L-GoM) model is a valid measure of clinical progression of AD and mild cognitive impairment (MCI) in both non-Hispanic White patients with high socioeconomic status and community-dwelling, multiethnic older adults.

Why This Matters

  • L-GoM model as a predictive tool for individuals with AD is valid for community-dwelling older adults of different ethnic, linguistic, and socioeconomic backgrounds, and the algorithm extends to include MCI.

Study Design

  • Participants (150 individuals with AD, 123 individuals with MCI) were recruited from a random sample of elderly Medicare recipients from the Washington Heights and Inwood areas of Manhattan, New York City.

  • Participants were excluded if they did not speak English or Spanish.

  • The diagnoses of AD dementia and MCI were based on the National Institute on Aging–Alzheimer's Association 2011 criteria, and dementia severity was measured by the Clinical Dementia Rating Scale (CDR).

  • Two outcomes were used for validation of the L-GoM model predictions: time of death and need for full-time care.

  • Participants were followed annually for up to 7 years.

 Key Results

  • Observed rates of survival and need for full time care in a community-dwelling multiethnic cohort supported the predicted results of the L-GoM model.

  • Average L-GoM scores differed significantly between AD and MCI groups and differed by sex, ethnicity, and ApoE status.


  • This study utilized a small population sample.

  • Validation did not include all minority groups in the US.

  • Misdiagnosis of AD and MCI could potentially yield incorrect predictions.

  • Subsequent application of the L-GoM model to other longitudinal studies may require modification to accommodate differences in instrumentation.


  • This study was funded by the National Institute on Aging of the National Institutes of Health under Award Number R01AG007370.

  • Co-author Yaakov Stern, PhD, consults for Eisai, Lilly, and Arcadia. Columbia University licenses the Dependence Scale, and in accordance with university policy, Stern is entitled to royalties through this license. The remaining authors report no conflicts of interest.

This is a summary of a preprint research study, "Validation of a multivariate prediction model of the clinical progression of Alzheimer's disease in a community-dwelling multiethnic cohort," written by Eric Stallard, Duke University, Durham, North Carolina, and colleagues on medRxiv.org, provided to you by Medscape. This study has not yet been peer reviewed. The full text of the study can be found medRxiv.org.

For more Medscape Neurology news, join us on Facebook and Twitter


Comments on Medscape are moderated and should be professional in tone and on topic. You must declare any conflicts of interest related to your comments and responses. Please see our Commenting Guide for further information. We reserve the right to remove posts at our sole discretion.