Name
Title | ||
|---|---|---|
Tell me something interesting: Clinical utility of machine learning prediction models in the ICU |
Abstract | ||
|---|---|---|
•Characterize ICU clinicians’ needs from machine learning-based prediction systems.•We identify multiple aspects in which these needs deviate from most current practice.•Desired prediction targets include patient trajectory and care prioritization.•Important aspects of trajectory prediction are clinical norm, trend and trend deviation .We obtained quantitative estimates of clinical utility of vital signs prediction. Derived utilities can be used to derive model evaluation metrics and loss functions.•We obtained quantitative estimates of clinical utility of vital signs prediction.•Derived utilities can be used to derive model evaluation metrics and loss functions. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1016/j.jbi.2022.104107 | Journal of Biomedical Informatics |
Keywords | DocType | Volume |
ICU,Machine learning,Decision-support,Vital signs | Journal | 132 |
ISSN | Citations | PageRank |
1532-0464 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bar Eini-Porat | 1 | 0 | 0.34 |
| Ofra Amir | 2 | 0 | 0.34 |
| Danny Eytan | 3 | 0 | 0.34 |
| Uri Shalit | 4 | 11 | 5.26 |