A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF)
Gracjan Iwanek, Mateusz Guzik, Amadeusz Oleszczak, Iga Karbowiak, Dominik Marciniak, Matteo Pagnesi, Julio Nuñez, Robert Zymliński, Piotr Ponikowski, Jan Biegus · 2026
Read A machine-learning model for accurate diuresis prediction in acute heart failure (DRC-AHF) by Gracjan Iwanek, Mateusz Guzik, Amadeusz Oleszczak, Iga Karbowiak, Dominik Marciniak, Matteo Pagnesi, Julio Nuñez, Robert Zymliński, Piotr Ponikowski, Jan Biegus (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/PMC13585464.txt.
Description
Iwanek and colleagues built a machine learning tool in 2026 to forecast how much urine a patient with acute heart failure will make after a water pill. That output is a key sign of whether treatment is working. The prospective study enrolled 296 patients at one center to build the model, then tested it in a separate group of 50. Just three inputs feed the model: kidney function and two urine measures taken two hours after the intravenous drug.
In the test group, forecast and actual six-hour urine output tracked each other closely. The model sorted 88 percent of patients into the right output band, against 58 percent for a standard formula. Error shrank steadily as more training patients were added, by roughly 200 milliliters per hundred patients. The calculator is freely available online. The authors present it as a practical aid for early, personal adjustment of diuretic therapy.
Catalog record
| CREATOR | Gracjan Iwanek, Mateusz Guzik, Amadeusz Oleszczak, Iga Karbowiak, Dominik Marciniak, Matteo Pagnesi, Julio Nuñez, Robert Zymliński, Piotr Ponikowski, Jan Biegus |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 37 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |