Comparative evaluation of LDL-cholesterol estimation using machine learning algorithms and conventional equations in a large middle eastern cohort
Fayha Salah Ahmed, Mohammad Imteyaz Ahmad, Mohamedi Begum, Deepa Rao, Sheifa Joan · 2026
Read Comparative evaluation of LDL-cholesterol estimation using machine learning algorithms and conventional equations in a large middle eastern cohort by Fayha Salah Ahmed, Mohammad Imteyaz Ahmad, Mohamedi Begum, Deepa Rao, Sheifa Joan (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/pmc-13573710.txt.
Description
Fayha Salah Ahmed, Mohammad Imteyaz Ahmad, Mohamedi Begum, Deepa Rao, and Sheifa Joan wrote a study in 2026 on LDL cholesterol and machine learning. LDL is the bad form that guides heart risk care. The old Friedewald equation can miss the true mark, most of all when triglycerides run high. The team used more than 96,000 lipid profiles from Dubai Health to test new ways to get the mark.
Five learning models took in just three inputs: total cholesterol, HDL, and triglycerides. In the normal range for triglycerides, the models matched direct lab tests more closely than three standard equations. Past that range, all ways lost ground, the models and the old math alike. The team had no external validation of the work. So they frame the models as aids to the old math, not as swaps for it. That weak spot is the next task.
Catalog record
| CREATOR | Fayha Salah Ahmed, Mohammad Imteyaz Ahmad, Mohamedi Begum, Deepa Rao, Sheifa Joan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |