Diagnostic performance of discriminant formulas and machine learning models for detecting β-thalassemia trait in Bangladesh
Rumana Mahtarin, Kasrina Azad, Rakib Bin Mahbub Talukder, Rynak Rahmat, Suzana Chowdhury Nitu, Arif Mahmud Howlader, Mohabbat Hossain, Mst. Sharmin Aktar Mukta, Mohammad Tanbir Habib, Abu Bakar Siddik, Nishat Sultana, Zannat Kawser, Umme Kulsum, Faisal Zainal Abedin, Nusrat Sultana, Md. Ahashan Habib, A. K. M. Ekramul Hossain, Farjana Akther Noor, Ahmad Zubair Mahdi, Muhammad Asaduzzaman, Emran Kabir Chowdhury, Md Rofiqur Rahman, Firdausi Qadri, Mst. Noorjahan Begum, A. H. M. Nurun Nabi · 2026
Read Diagnostic performance of discriminant formulas and machine learning models for detecting β-thalassemia trait in Bangladesh by Rumana Mahtarin, Kasrina Azad, Rakib Bin Mahbub Talukder, Rynak Rahmat, Suzana Chowdhury Nitu, Arif Mahmud Howlader, Mohabbat Hossain, Mst. Sharmin Aktar Mukta, Mohammad Tanbir Habib, Abu Bakar Siddik, Nishat Sultana, Zannat Kawser, Umme Kulsum, Faisal Zainal Abedin, Nusrat Sultana, Md. Ahashan Habib, A. K. M. Ekramul Hossain, Farjana Akther Noor, Ahmad Zubair Mahdi, Muhammad Asaduzzaman, Emran Kabir Chowdhury, Md Rofiqur Rahman, Firdausi Qadri, Mst. Noorjahan Begum, A. H. M. Nurun Nabi (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/PMC13271480.txt.
Description
Rumana Mahtarin is lead author of a 2026 cross-sectional study comparing ways to detect beta-thalassemia trait, a carrier state for a serious inherited blood disease, in Bangladesh. Telling the trait apart from iron-deficiency anaemia matters for genetic counselling and prevention, and many simple blood-count formulas claim to do it, but they had not been compared head-to-head locally.
The team tested 47 existing formulas and twelve machine learning models on 467 people, 143 with the trait and 324 with anaemia, drawn from a larger cohort of 2,514. They also built two new formulas by merging the strongest performers. A multi-criteria ranking method gave the final ordering, and clustering grouped methods with similar diagnostic behaviour.
Catalog record
| CREATOR | Rumana Mahtarin, Kasrina Azad, Rakib Bin Mahbub Talukder, Rynak Rahmat, Suzana Chowdhury Nitu, Arif Mahmud Howlader, Mohabbat Hossain, Mst. Sharmin Aktar Mukta, Mohammad Tanbir Habib, Abu Bakar Siddik, Nishat Sultana, Zannat Kawser, Umme Kulsum, Faisal Zainal Abedin, Nusrat Sultana, Md. Ahashan Habib, A. K. M. Ekramul Hossain, Farjana Akther Noor, Ahmad Zubair Mahdi, Muhammad Asaduzzaman, Emran Kabir Chowdhury, Md Rofiqur Rahman, Firdausi Qadri, Mst. Noorjahan Begum, A. H. M. Nurun Nabi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50219 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |