Machine learning-based early detection of abnormal heart rate in critically ill patients: a real-world clinical dataset study with automated alert system integration
Joao C. Ferreira, Luis B. Elvas · 2026
Read Machine learning-based early detection of abnormal heart rate in critically ill patients: a real-world clinical dataset study with automated alert system integration by Joao C. Ferreira, Luis B. Elvas (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-13593851.txt.
Description
Joao Ferreira and Luis Elvas build an early warning system for abnormal heart rates in a 2026 study of intensive care patients. A heart that beats too fast or too slow is a risk that early, automated detection can blunt. The team worked with real records from a Lisbon hospital covering more than twenty-three thousand patients.
Four standard classifiers were compared under a patient-specific definition of abnormal, then the winner was retested against standard clinical cutoffs. Logistic regression came out on top under both definitions, catching most events while keeping false alarms in check. Training respected time order and kept each patient's data apart to stop leakage. A prototype email alert system was then shown to two heart specialists as a proof of concept. The authors warn that scores alone do not prove clinical worth.
Catalog record
| CREATOR | Joao C. Ferreira, Luis B. Elvas |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |