| Summary: | 博士 === 臺北醫學大學 === 醫學科學研究所 === 99 === 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 and spinal anesthesia.
In part I, Anesthesia records for the period of March through November 2007 were reviewed, and 1017 records were analyzed. Eleven patient-related, two surgical, and five anesthetic variables were used to develop the ANN and logistic regression (LR) models. The quality of the models was evaluated by an external validation dataset. Three clinicians were asked to make predictions of the same validation dataset on a case-by-case basis.
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 (ROC) curves for the ANN and LR models were 0.893 and 0.840. The clinicians had the lowest predictive accuracy and sensitivity compared to the ANN and LR models.
In part II, from Sep 2004 to Dec 2006, the anesthesia records of 1501 patients receiving surgery under spinal anesthesia were used to develop the ANN and LR models. 75% of data were used for training and the last 25% of data were used as test set for validation. Five anesthesiologists were asked to review the data of test set and to make predictions of hypotensive event during spinal anesthesia by clinical experience.
The ANN model had a sensitivity of 75.9% and specificity of 76.0%. The LR model had a sensitivity of 68.1% and specificity of 73.5%. The area under ROC curves were 0.796 and 0.748. The ANN model performed significantly better than the LR model. The prediction of clinicians had the lowest sensitivity of 28.7%, 22.2%, 21.3%, 16.1%, and 36.1%.
The ANN model for general anesthesia was applied to clinical practice to verify its feasibility. Randomly selected 34 patients were enrolled into the study group and 37 patients into the control group. In the study group the ANN model was used to predict whether patients had postinduction hypotension and informed the clinician. It depended on the clinician to choose some strategies to prevent the occurrence of hypotension. In the control group the clinician was not informed about the predictive result of the ANN model. The incidence of hypotension in study group was less than that in the control group (11.8% vs. 29.7%). Application of the ANN model significantly reduced the incidence of postinduction hypotension.
The ANN models developed in this study had good discrimination and calibration and would be helpful in providing decision support to clinicians and in increasing vigilance in those patients at high risk of postinduction hypotension during general and spinal anesthesia.
|
|---|
