Predicting hypotensive episodes during spinal anesthesia with the application of artificial neural networks

Chao Shun Lin, Jainn Shiun Chiu, Ming Hui Hsieh, Martin S. Mok, Yu Chuan Li, Hung Wen Chiu

研究成果: 雜誌貢獻文章

23 引文 (Scopus)

摘要

Hypotension is one of the most frequent adverse effects of spinal anesthesia. Several factors might be related to the occurrence of hypotension. Predictions of the hypotensive event, however, had been addressed by only a few authors using logistic regression (LR) models. Artificial neural networks (ANN) are pattern-recognition tools that can be used to detect complex patterns within data sets. The purpose of this study was to develop the ANN-based predictive model to identify patients with high risk of hypotension during spinal anesthesia. From September 2004 to December 2006, the anesthesia records of 1501 patients receiving surgery under spinal anesthesia were used to develop the ANN and LR models. By random selection 75% of data were used for training and the remaining 25% of data were used as test set for validating the predictive performance. Five senior 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 receiver operating characteristic 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%, and specificity of 76.8%, 84.3%, 83.1%, 87.0%, and 64.0%. The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for hypotension during spinal anesthesia, in allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of anesthesia.
原文英語
頁(從 - 到)193-197
頁數5
期刊Computer Methods and Programs in Biomedicine
92
發行號2
DOIs
出版狀態已發佈 - 十一月 2008

指紋

Spinal Anesthesia
Logistic Models
Neural networks
Hypotension
Logistics
Neural Networks (Computer)
Anesthesia
Sensitivity and Specificity
ROC Curve
Surgery
Pattern recognition

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics

引用此文

Predicting hypotensive episodes during spinal anesthesia with the application of artificial neural networks. / Lin, Chao Shun; Chiu, Jainn Shiun; Hsieh, Ming Hui; Mok, Martin S.; Li, Yu Chuan; Chiu, Hung Wen.

於: Computer Methods and Programs in Biomedicine, 卷 92, 編號 2, 11.2008, p. 193-197.

研究成果: 雜誌貢獻文章

@article{1402d032e0814f09a7544c11aaaf5999,
title = "Predicting hypotensive episodes during spinal anesthesia with the application of artificial neural networks",
abstract = "Hypotension is one of the most frequent adverse effects of spinal anesthesia. Several factors might be related to the occurrence of hypotension. Predictions of the hypotensive event, however, had been addressed by only a few authors using logistic regression (LR) models. Artificial neural networks (ANN) are pattern-recognition tools that can be used to detect complex patterns within data sets. The purpose of this study was to develop the ANN-based predictive model to identify patients with high risk of hypotension during spinal anesthesia. From September 2004 to December 2006, the anesthesia records of 1501 patients receiving surgery under spinal anesthesia were used to develop the ANN and LR models. By random selection 75{\%} of data were used for training and the remaining 25{\%} of data were used as test set for validating the predictive performance. Five senior 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 receiver operating characteristic 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{\%}, and specificity of 76.8{\%}, 84.3{\%}, 83.1{\%}, 87.0{\%}, and 64.0{\%}. The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for hypotension during spinal anesthesia, in allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of anesthesia.",
keywords = "Artificial neural networks, Hypotension, Logistic regression, Spinal anesthesia",
author = "Lin, {Chao Shun} and Chiu, {Jainn Shiun} and Hsieh, {Ming Hui} and Mok, {Martin S.} and Li, {Yu Chuan} and Chiu, {Hung Wen}",
year = "2008",
month = "11",
doi = "10.1016/j.cmpb.2008.06.013",
language = "English",
volume = "92",
pages = "193--197",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",
number = "2",

}

TY - JOUR

T1 - Predicting hypotensive episodes during spinal anesthesia with the application of artificial neural networks

AU - Lin, Chao Shun

AU - Chiu, Jainn Shiun

AU - Hsieh, Ming Hui

AU - Mok, Martin S.

AU - Li, Yu Chuan

AU - Chiu, Hung Wen

PY - 2008/11

Y1 - 2008/11

N2 - Hypotension is one of the most frequent adverse effects of spinal anesthesia. Several factors might be related to the occurrence of hypotension. Predictions of the hypotensive event, however, had been addressed by only a few authors using logistic regression (LR) models. Artificial neural networks (ANN) are pattern-recognition tools that can be used to detect complex patterns within data sets. The purpose of this study was to develop the ANN-based predictive model to identify patients with high risk of hypotension during spinal anesthesia. From September 2004 to December 2006, the anesthesia records of 1501 patients receiving surgery under spinal anesthesia were used to develop the ANN and LR models. By random selection 75% of data were used for training and the remaining 25% of data were used as test set for validating the predictive performance. Five senior 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 receiver operating characteristic 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%, and specificity of 76.8%, 84.3%, 83.1%, 87.0%, and 64.0%. The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for hypotension during spinal anesthesia, in allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of anesthesia.

AB - Hypotension is one of the most frequent adverse effects of spinal anesthesia. Several factors might be related to the occurrence of hypotension. Predictions of the hypotensive event, however, had been addressed by only a few authors using logistic regression (LR) models. Artificial neural networks (ANN) are pattern-recognition tools that can be used to detect complex patterns within data sets. The purpose of this study was to develop the ANN-based predictive model to identify patients with high risk of hypotension during spinal anesthesia. From September 2004 to December 2006, the anesthesia records of 1501 patients receiving surgery under spinal anesthesia were used to develop the ANN and LR models. By random selection 75% of data were used for training and the remaining 25% of data were used as test set for validating the predictive performance. Five senior 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 receiver operating characteristic 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%, and specificity of 76.8%, 84.3%, 83.1%, 87.0%, and 64.0%. The computer-based predictive model should be useful in increasing vigilance in those patients most at risk for hypotension during spinal anesthesia, in allowing for patient-specific therapeutic intervention, or even in suggesting the use of alternative methods of anesthesia.

KW - Artificial neural networks

KW - Hypotension

KW - Logistic regression

KW - Spinal anesthesia

UR - http://www.scopus.com/inward/record.url?scp=52949083181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52949083181&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2008.06.013

DO - 10.1016/j.cmpb.2008.06.013

M3 - Article

C2 - 18760495

AN - SCOPUS:52949083181

VL - 92

SP - 193

EP - 197

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 2

ER -