Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.
Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.
复制标题
DOI:
10.1136/bmjopen-2017-017833
复制
发表时间:
2018-01-26
期刊:
影响因子:
2.9
通讯作者:
Das R
中科院分区:
文献类型:
--
作者:
Mao Q;Jay M;Hoffman JL;Calvert J;Barton C;Shimabukuro D;Shieh L;Chettipally U;Fletcher G;Kerem Y;Zhou Y;Das R
We validate a machine learning-based sepsis-prediction algorithm (InSight) for the detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings. A machine-learning algorithm with gradient tree boosting. Features for prediction were created from combinations of six vital sign measurements and their changes over time. A mixed-ward retrospective dataset from the University of California, San Francisco (UCSF) Medical Center (San Francisco, California, USA) as the primary source, an intensive care unit dataset from the Beth Israel Deaconess Medical Center (Boston, Massachusetts, USA) as a transfer-learning source and four additional institutions’ datasets to evaluate generalisability. 684 443 total encounters, with 90 353 encounters from June 2011 to March 2016 at UCSF. None. Area under the receiver operating characteristic (AUROC) curve for detection and prediction of sepsis, severe sepsis and septic shock. For detection of sepsis and severe sepsis, InSight achieves an AUROC curve of 0.92 (95% CI 0.90 to 0.93) and 0.87 (95% CI 0.86 to 0.88), respectively. Four hours before onset, InSight predicts septic shock with an AUROC of 0.96 (95% CI 0.94 to 0.98) and severe sepsis with an AUROC of 0.85 (95% CI 0.79 to 0.91). InSight outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis and septic shock. This is the first sepsis screening system to exceed an AUROC of 0.90 using only vital sign inputs. InSight is robust to missing data, can be customised to novel hospital data using a small fraction of site data and retains strong discrimination across all institutions.
登录
查看更多内容
影响因子:
3.7
作者:
Horng S;Sontag DA;Halpern Y;Jernite Y;Shapiro NI;Nathanson LA
通讯作者:
Nathanson LA
影响因子:
8.8
作者:
Stevenson EK;Rubenstein AR;Radin GT;Wiener RS;Walkey AJ
通讯作者:
Walkey AJ
影响因子:
3.2
作者:
Desautels T;Calvert J;Hoffman J;Jay M;Kerem Y;Shieh L;Shimabukuro D;Chettipally U;Feldman MD;Barton C;Wales DJ;Das R
通讯作者:
Das R
影响因子:
17.1
作者:
Henry, Katharine E.;Hager, David N.;Saria, Suchi
通讯作者:
Saria, Suchi
影响因子:
158.5
作者:
Rivers, E;Nguyen, B;Tomlanovich, M
通讯作者:
Tomlanovich, M