AI-driven neuroimaging for Alzheimer’s disease: Addressing genetic and ethnic bias in diagnostic modeling
Hamna binte Iqbal, Ayesha Janjua, Raghabendra kumar Mahato · 2026
Read AI-driven neuroimaging for Alzheimer’s disease: Addressing genetic and ethnic bias in diagnostic modeling by Hamna binte Iqbal, Ayesha Janjua, Raghabendra kumar Mahato (2026) 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/PMC13459678.txt.
Description
Iqbal and colleagues wrote a letter to the editor in 2026 about bias in artificial intelligence tools for Alzheimer's disease. These tools read brain scans and mix them with gene data, blood markers, and behaviour scores. The authors warn that training data lean heavily toward people of European ancestry.
In one cohort of 1,730 people, the models missed more true cases among Hispanic patients than among non-Hispanic patients. Gaps also appeared for Black and Asian patients when set against White patients. Tools that scored very well inside the main data set scored lower on outside hospital data. The authors call for training sets that include more regions and ethnic groups. They also want routine fairness checks before such tools guide real diagnosis in clinics.
Catalog record
| CREATOR | Hamna binte Iqbal, Ayesha Janjua, Raghabendra kumar Mahato |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 4 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |