Development and early feasibility testing of machine-learning algorithms to non-invasively assess hemoglobin levels
Simon Hefner, Philipp Stoffers, Benedikt Langenberger, Alix Holstein, Miha Garafolj, Christina Klötzer, Carmen Herling, Vladan Vucinic, Reinhard Henschler, Ariel Dora Stern, Uwe Platzbecker, Anne Sophie Platzbecker · 2026
Read Development and early feasibility testing of machine-learning algorithms to non-invasively assess hemoglobin levels by Simon Hefner, Philipp Stoffers, Benedikt Langenberger, Alix Holstein, Miha Garafolj, Christina Klötzer, Carmen Herling, Vladan Vucinic, Reinhard Henschler, Ariel Dora Stern, Uwe Platzbecker, Anne Sophie Platzbecker (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-13230506.txt.
Description
Simon Hefner and colleagues test in 2026 whether photos of fingernails and eyelids can estimate hemoglobin without a blood draw. Their HeMonitor study enrolled three hundred sixty-seven patients with blood cancers plus healthy donors for comparison. Machine learning models learned to predict lab hemoglobin values from the images alone.
The best model landed close to lab values, with spread near one unit on the reported scale. A second exploratory layer combined each estimate with patient reports of overall health and fatigue. Lower estimates generally matched worse quality of life, which fits the known burden of anemia. Agreement with clinician judgment looked encouraging in borderline ranges. Home monitoring built this way still needs testing in planned follow-up studies.
Catalog record
| CREATOR | Simon Hefner, Philipp Stoffers, Benedikt Langenberger, Alix Holstein, Miha Garafolj, Christina Klötzer, Carmen Herling, Vladan Vucinic, Reinhard Henschler, Ariel Dora Stern, Uwe Platzbecker, Anne Sophie Platzbecker |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |