Integrating NACC UDS with RDW EHR data for MCI prediction and identification of MCI related features
Gefei Wang, Baijia Xu, Wanwan Xu, Hiroko H Dodge, Yize Zhao · 2025
Read Integrating NACC UDS with RDW EHR data for MCI prediction and identification of MCI related features by Gefei Wang, Baijia Xu, Wanwan Xu, Hiroko H Dodge, Yize Zhao (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11714250.txt.
Description
Gefei Wang and four co-authors wrote this 2025 study on predicting mild cognitive impairment by fusing two medical data worlds. A national Alzheimer's research data set holds deep, standardized assessments, while hospital records hold messy but rich histories of diagnoses and medicines. The team linked both for 143 patients, of whom eighty-five later developed impairment, and trained the same random forest model on each source and on the union.
The union won clearly: its discrimination score beat either source alone, with the hospital-only model weakest. Features from the health records, especially histories of other mental disorders, sleep problems, pain, and low blood pressure, added real signal beyond the research battery. The authors argue prediction improves when curated research data marry everyday clinical exhaust. The sample is small, so they frame the study as a proof of concept for data integration in early detection.
Catalog record
| CREATOR | Gefei Wang, Baijia Xu, Wanwan Xu, Hiroko H Dodge, Yize Zhao |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |