Identification of novel hypertension biomarkers using explainable AI and metabolomics
Karthik Sekaran, Hatem Zayed · 2024
Read Identification of novel hypertension biomarkers using explainable AI and metabolomics by Karthik Sekaran, Hatem Zayed (2024) 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-11532322.txt.
Description
High blood pressure affects about a third of adults in Qatar, and its roots in body chemistry are still being mapped. Karthik Sekaran and Hatem Zayed profiled small molecules in blood samples from 224 Qatari patients with early-stage hypertension and 554 healthy controls. They then used explainable AI methods to find which molecules best separate the groups.
One molecule, vanillylmandelic acid, stood clearly higher in the patient group. Three others, a fat-carrier molecule, a sphingolipid, and the amino acid glycine, carried much of the predictive weight. Their best model sorted patients from controls with about 78 percent accuracy, and explanation tools showed how each marker pushed the decision. The authors present the markers as candidates for earlier detection and for understanding the disease in this population, while noting the work covers one country's patients at one disease stage.
Catalog record
| CREATOR | Karthik Sekaran, Hatem Zayed |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |