Early prediction of circulatory failure in the intensive care unit using machine learning Journal Article
| Authors: | Hyland, S. L.; Faltys, M.; Hüser, M.; Lyu, X.; Gumbsch, T.; Esteban, C.; Bock, C.; Horn, M.; Moor, M.; Rieck, B.; Zimmermann, M.; Bodenham, D.; Borgwardt, K.; Rätsch, G.; Merz, T. M. |
| Article Title: | Early prediction of circulatory failure in the intensive care unit using machine learning |
| Abstract: | Intensive-care clinicians are presented with large quantities of measurements from multiple monitoring systems. The limited ability of humans to process complex information hinders early recognition of patient deterioration, and high numbers of monitoring alarms lead to alarm fatigue. We used machine learning to develop an early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data. It predicts 90% of circulatory-failure events in the test set, with 82% identified more than 2 h in advance, resulting in an area under the receiver operating characteristic curve of 0.94 and an area under the precision-recall curve of 0.63. On average, the system raises 0.05 alarms per patient and hour. The model was externally validated in an independent patient cohort. Our model provides early identification of patients at risk for circulatory failure with a much lower false-alarm rate than conventional threshold-based systems. © 2020, The Author(s), under exclusive licence to Springer Nature America, Inc. |
| Keywords: | adult; controlled study; middle aged; case control study; diagnostic accuracy; sensitivity and specificity; cohort analysis; data base; retrospective study; high risk patient; false negative result; intensive care unit; ischemia; diagnostic value; early diagnosis; intermethod comparison; false positive result; predictive value; critical illness; critically ill patient; external validity; diagnostic test accuracy study; instrument validation; feature extraction; organs at risk; integrated health care system; human; female; priority journal; article; feature selection; supervised machine learning; alarm monitoring; circews algorithm; circews lite algorithm; early warning score |
| Journal Title: | Nature Medicine |
| Volume: | 26 |
| Issue: | 3 |
| ISSN: | 1078-8956 |
| Publisher: | Nature Publishing Group |
| Date Published: | 2020-03-01 |
| Start Page: | 364 |
| End Page: | 373 |
| Language: | English |
| DOI: | 10.1038/s41591-020-0789-4 |
| PUBMED: | 32152583 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Article -- Export Date: 1 April 2020 -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work