Name
Title | ||
|---|---|---|
Machine learning predicts mortality in septic patients using only routinely available ABG variables: a multi-centre evaluation |
Abstract | ||
|---|---|---|
•The best predictive performance was achieved by the long short-term memory -based model with AUC of 0.88 in the multi-centre study and AUC of 0.85 in the single centre study.•An LSTM-based model could help physicians with the “re-triage” and the decision to restrict treatment in patients with a poor prognosis.•Machine learning based models could help physicians in the decision process evaluating therapy targets after an initial ICU-trial. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.ijmedinf.2020.104312 | International Journal of Medical Informatics |
Keywords | DocType | Volume |
critically ill,artificial intelligence,machine learning,deep learning,LSTM,ICU,risk stratification,intensive care unit,critical care,sepsis | Journal | 145 |
ISSN | Citations | PageRank |
1386-5056 | 1 | 0.63 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bernhard Wernly | 1 | 1 | 0.63 |
| Behrooz Mamandipoor | 2 | 1 | 0.63 |
| Philipp Baldia | 3 | 1 | 0.63 |
| Christian Jung | 4 | 1 | 0.63 |
| Venet Osmani | 5 | 363 | 32.41 |