Alzheimer's Counterfactual Twin Cohort

FREE SAMPLE INCLUDED. This project holds the full technical documentation and a free evaluation sample (500 people, all 27 scenarios, all tables, hidden truth included). It is not the full dataset. Full dataset: https://sentineldata.com.ua/dataset/alzheimers-counterfactual-twin-cohort Zenodo record (same package): https://doi.org/10.5281/zenodo.24227228 About the dataset: ten thousand synthetic people aged 50 to 75 are followed for up to 25 years through Alzheimer's disease, and each person is lived 27 times: once untreated and 26 times under different medical strategies, with the same body and the same random numbers. The untreated course of every person is known exactly, so the effect of any strategy on that person is a subtraction of two of their own trajectories. Next to the noisy clinical record (MMSE, CDR-SB, plasma p-tau217, amyloid PET) the data carry the hidden truth behind it: true amyloid, tau, inflammation, clearance and damage every quarter. The full description, with the disease model, validation, benchmarks and limitations, is on the project wiki. Sample license: CC BY-NC 4.0. All data are synthetic and describe no real person. Version 1.0.

Authors

Publication Details

Journal
Open Science Framework
Published
2026-11-14
DOI
https://doi.org/10.17605/osf.io/epk8q
Primary Topic
Alzheimer's disease research and treatments
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Alzheimer's Counterfactual Twin Cohort

Chekerskyi Maksym
Open Science Framework
Alzheimer's disease research and treatments
article

Alzheimer's Counterfactual Twin Cohort

Chekerskyi Maksym
article en

Abstract

FREE SAMPLE INCLUDED. This project holds the full technical documentation and a free evaluation sample (500 people, all 27 scenarios, all tables, hidden truth included). It is not the full dataset. Full dataset: https://sentineldata.com.ua/dataset/alzheimers-counterfactual-twin-cohort Zenodo record (same package): https://doi.org/10.5281/zenodo.24227228 About the dataset: ten thousand synthetic people aged 50 to 75 are followed for up to 25 years through Alzheimer's disease, and each person is lived 27 times: once untreated and 26 times under different medical strategies, with the same body and the same random numbers. The untreated course of every person is known exactly, so the effect of any strategy on that person is a subtraction of two of their own trajectories. Next to the noisy clinical record (MMSE, CDR-SB, plasma p-tau217, amyloid PET) the data carry the hidden truth behind it: true amyloid, tau, inflammation, clearance and damage every quarter. The full description, with the disease model, validation, benchmarks and limitations, is on the project wiki. Sample license: CC BY-NC 4.0. All data are synthetic and describe no real person. Version 1.0.

Open Science Framework
Alzheimer's disease research and treatments
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon