An ethnic-sensitive hybrid framework for T2D prediction with explainable AI and weighted ensembles

Karlo Abnoosian, Rahman Farnoosh, Hamidreza Noushkaran, Danial Javaheri, Hasnat Azeez Shimal, Abdullah Abdulamer Abdulkarem · 2025

Read An ethnic-sensitive hybrid framework for T2D prediction with explainable AI and weighted ensembles by Karlo Abnoosian, Rahman Farnoosh, Hamidreza Noushkaran, Danial Javaheri, Hasnat Azeez Shimal, Abdullah Abdulamer Abdulkarem (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-12800193.txt.

Description

Karlo Abnoosian and co-authors build a diabetes prediction framework that respects ethnic differences in a 2025 paper. Type 2 diabetes is a global crisis, and early prediction is hardest where data are missing and classes are lopsided. Risk factors also differ across populations.

Their four-stage system cleans weak variables, fills gaps with a class-aware generative model, and then combines fifteen learning algorithms with weights from their performance. A method that explains the model then shows which risks matter most in each group. Three benchmark datasets test the design. Fitting the tool to the group at hand is the paper's central argument, since risk is not the same from one group to the next.

Catalog record

CREATORKarlo Abnoosian, Rahman Farnoosh, Hamidreza Noushkaran, Danial Javaheri, Hasnat Azeez Shimal, Abdullah Abdulamer Abdulkarem
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE139 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12800193

Browse the full library · About the Tower of Babel