Name
Abstract | ||
|---|---|---|
•The LightGBM model with refined feature engineering demonstrated high discrimination among high-risk ED patients.•The vital signs and laboratory tests were sufficiently informative to predict ED mortality.•Machine learning models have significant potential as a clinical decision support tool in assisting physicians in their clinical routine. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.ijmedinf.2021.104570 | International Journal of Medical Informatics |
Keywords | DocType | Volume |
Machine learning,Emergency department,Mortality prediction,Feature engineering,Electronic health records | Journal | 155 |
ISSN | Citations | PageRank |
1386-5056 | 0 | 0.34 |
References | Authors | |
0 | 8 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Cong Li | 1 | 0 | 0.34 |
| Zhuo Zhang | 2 | 0 | 0.34 |
| Ya-Zhou Ren | 3 | 101 | 13.51 |
| Hu Nie | 4 | 0 | 0.34 |
| Yuqing Lei | 5 | 0 | 0.34 |
| Hang Qiu | 6 | 6 | 1.94 |
| Zenglin Xu | 7 | 923 | 66.28 |
| Xiaorong Pu | 8 | 85 | 11.17 |