Phase 1 of the PREPARE: Pioneering Research for Early Prediction of Alzheimer's and Related Dementias EUREKA Challenge
Alzheimer's disease and Alzheimer's disease related dementias (AD/ADRD) impact over 6 million Americans, causing progressive cognitive, functional, and behavioral impairments. Early detection is crucial, especially with emerging treatment options, but current clinical tools are not sensitive enough for early prediction.
In the PREPARE Challenge (Pioneering Research for Early Prediction of Alzheimer's and Related Dementias EUREKA Challenge) to advance solutions for accurate, innovative, and representative early prediction of AD/ADRD. To achieve this goal, the challenge will feature three phases that successively build on each other.
In Phase 1 (completed), solvers found, curated, or contributed representative and open datasets that could be used for early prediction of AD/ADRD.
In Phases 2 and 3 (current/upcoming), solvers will develop models for early prediction of AD/ADRD, with an emphasis on explainability of predictions, and then refine and demonstrate their approaches.
This repository contains code from winning competitors in the PREPARE Challenge DrivenData challenge. Code for all winning solutions are open source under the MIT License.
Winning code for other DrivenData competitions is available in the competition-winners repository.
| Place | Team or User | Data Summary |
|---|---|---|
| 1 | VBM_CSE_UB | Audio recordings, acoustic features, demographic information, and clinical data from 2,086 participants in the DementiaBank dataset. |
| 2 | zedlab | 2 million synthetic patient records with 9 variables, generated using AI models trained on EHR data from the Truven Marketscan national database and University of Chicago (2012-2021). |
| 3 | IGCPHARMA | Winner of the Disproportionate Impact Bonus Survey data from 26,839 adults over 50 in the Mexican Health and Aging Study (MHAS) and the Mexican Cognitive Aging Ancillary Study (Mex-Cog), which uses the Harmonized Cognitive Assessment Protocol (HCAP) to assess cognitive function. |
| 4 | gaganwig | Pre-processed resting-state fMRI data from a diverse cohort of 1,491 AD patients and healthy subjects, sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Data enable multi-modal prediction analyses by integrating brain function with structural, pathological, and genetic measures. |
| 5 | EngrDynamics | Survey data from approximately 1 million participants in the National Health Interview Survey (NHIS), with self-reported information about cognitive decline. |
| Data Idea | korinreidellisonlabs | This proposal addresses the AD misdiagnosis rate in the African American population. It describes a community-driven, patient-centric method for creating a representative, de-identified repository of data for early prediction of AD by combining EHR and claim data with data that captures biologically based biomarkers (e.g., ADNI data including genomics data, MRI, PET, CSF, blood-based biomarkers). |
| Data Idea | msundman | Obstructive sleep apnea (OSA) is a modifiable potential risk factor for AD. This proposal outlines a method of collecting data to explore whether radiographs routinely acquired at dental screenings capture an early, scalable AD risk signal. |
| Data Idea | stephanieruth.young | This proposal describes a method of creating an open, shareable dataset of cognitive screening data through mobile data collection with the MyCog App and traditional neuropsychological assessments for diagnosing AD/ADRD. |
Additional solution details can be found inside the directory for each submission.
Winners Blog Post: Meet the winners for Phase 1 of the PREPARE Challenge