TY - JOUR
T1 - Application of an artificial neural network to predict postinduction hypotension during general anesthesia
AU - Lin, Chao-Shun
AU - Chang, Chuen-Chau
AU - Chiu, Jainn Shiun
AU - Lee, Yuan-Wen
AU - Lin, Jui-An
AU - Mok, Martin S.
AU - Chiu, Hung-Wen
AU - Li, Yu-Chuan
N1 - Funding Information:
This work was supported by the National Science Council of Taiwan (grant NSC 98–2221-E-038–011, NSC 98–2218-E-038–001).
PY - 2011/3
Y1 - 2011/3
N2 - Background. Perioperative hypotension is associated with adverse outcomes in patients undergoing surgery. A computer-based model that integrates related factors and predicts the risk of hypotension would be helpful in clinical anesthesia. The purpose of this study was to develop artificial neural network (ANN) models to identify patients at high risk for postinduction hypotension during general anesthesia. Methods. Anesthesia records for March through November 2007 were reviewed, and 1017 records were analyzed. Eleven patient-related, 2 surgical, and 5 anesthetic variables were used to develop the ANN and logistic regression (LR) models. The quality of the models was evaluated by an external validation data set. Three clinicians were asked to make predictions of the same validation data set on a case-by-case basis. Results. The ANN model had an accuracy of 82.3%, sensitivity of 76.4%, and specificity of 85.6%. The accuracy of the LR model was 76.5%, the sensitivity was 74.5%, and specificity was 77.7%. The area under the receiver operating characteristic curve for the ANN and LR models was 0.893 and 0.840. The clinicians had the lowest predictive accuracy and sensitivity compared with the ANN and LR models. Conclusions. The ANN model developed in this study had good discrimination and calibration and would provide decision support to clinicians and increase vigilance for patients at high risk of postinduction hypotension during general anesthesia.
AB - Background. Perioperative hypotension is associated with adverse outcomes in patients undergoing surgery. A computer-based model that integrates related factors and predicts the risk of hypotension would be helpful in clinical anesthesia. The purpose of this study was to develop artificial neural network (ANN) models to identify patients at high risk for postinduction hypotension during general anesthesia. Methods. Anesthesia records for March through November 2007 were reviewed, and 1017 records were analyzed. Eleven patient-related, 2 surgical, and 5 anesthetic variables were used to develop the ANN and logistic regression (LR) models. The quality of the models was evaluated by an external validation data set. Three clinicians were asked to make predictions of the same validation data set on a case-by-case basis. Results. The ANN model had an accuracy of 82.3%, sensitivity of 76.4%, and specificity of 85.6%. The accuracy of the LR model was 76.5%, the sensitivity was 74.5%, and specificity was 77.7%. The area under the receiver operating characteristic curve for the ANN and LR models was 0.893 and 0.840. The clinicians had the lowest predictive accuracy and sensitivity compared with the ANN and LR models. Conclusions. The ANN model developed in this study had good discrimination and calibration and would provide decision support to clinicians and increase vigilance for patients at high risk of postinduction hypotension during general anesthesia.
KW - Anesthesiology
KW - Artificial neural networks
KW - Logistic regression models
KW - ROC curve analysis
UR - http://www.scopus.com/inward/record.url?scp=79953836782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79953836782&partnerID=8YFLogxK
U2 - 10.1177/0272989X10379648
DO - 10.1177/0272989X10379648
M3 - Article
C2 - 20876347
AN - SCOPUS:79953836782
SN - 0272-989X
VL - 31
SP - 308
EP - 314
JO - Medical Decision Making
JF - Medical Decision Making
IS - 2
ER -
