Machine learning can accurately predict pre-admission baseline hemoglobin and creatinine in intensive care patients
| Autor: | Ke-Chun Huang, Daniele Ramazzotti, Carolina Donado, Antonin Dauvin, Molly Douglas, Matteo Bonvini, Patrik Bachtiger, Christopher Martin Sauer, Leo Anthony Celi |
|---|---|
| Přispěvatelé: | Dauvin, A, Donado, C, Bachtiger, P, Huang, K, Sauer, C, Ramazzotti, D, Bonvini, M, Celi, L, Douglas, M |
| Rok vydání: | 2019 |
| Předmět: |
Anemia
Medicine (miscellaneous) Health Informatics Anaemia 030204 cardiovascular system & hematology Machine learning computer.software_genre lcsh:Computer applications to medicine. Medical informatics Article law.invention 03 medical and health sciences chemistry.chemical_compound 0302 clinical medicine Health Information Management law Intensive care Chronic kidney disease medicine Computational models 030212 general & internal medicine Baseline (configuration management) Creatinine business.industry Computational model Acute kidney injury medicine.disease Intensive care unit Computer Science Applications Icu admission chemistry lcsh:R858-859.7 Data integration Hemoglobin Artificial intelligence business computer |
| Zdroj: | NPJ Digital Medicine npj Digital Medicine, Vol 2, Iss 1, Pp 1-10 (2019) |
| ISSN: | 2398-6352 |
| Popis: | Patients admitted to the intensive care unit frequently have anemia and impaired renal function, but often lack historical blood results to contextualize the acuteness of these findings. Using data available within two hours of ICU admission, we developed machine learning models that accurately (AUC 0.86–0.89) classify an individual patient’s baseline hemoglobin and creatinine levels. Compared to assuming the baseline to be the same as the admission lab value, machine learning performed significantly better at classifying acute kidney injury regardless of initial creatinine value, and significantly better at predicting baseline hemoglobin value in patients with admission hemoglobin of |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|