Neural network modeling for surgical decisions on traumatic brain injury patients

Yu Chuan Li, Li Liu, Wen Ta Chiu, Wen Shan Jian

研究成果: 雜誌貢獻文章

52 引文 (Scopus)

摘要

Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial- basis-function (RBF) neural network. From the 12 640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P

原文英語
頁(從 - 到)1-9
頁數9
期刊International Journal of Medical Informatics
57
發行號1
DOIs
出版狀態已發佈 - 一月 2000

指紋

Decision Support Techniques
Logistic Models
Neural Networks (Computer)
Skull
Sensitivity and Specificity
ROC Curve
Theoretical Models
Databases
Skull Fractures
Glasgow Coma Scale
Calibration
Seizures
Software
Traumatic Brain Injury
Physicians
Research

ASJC Scopus subject areas

  • Medicine(all)

引用此文

Neural network modeling for surgical decisions on traumatic brain injury patients. / Li, Yu Chuan; Liu, Li; Chiu, Wen Ta; Jian, Wen Shan.

於: International Journal of Medical Informatics, 卷 57, 編號 1, 01.2000, p. 1-9.

研究成果: 雜誌貢獻文章

@article{7382dbfdd585402f9fa4238e45a44161,
title = "Neural network modeling for surgical decisions on traumatic brain injury patients",
abstract = "Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial- basis-function (RBF) neural network. From the 12 640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73{\%}, 68{\%}), compared to (80{\%}, 80{\%}) from the RBF model and (88{\%}, 80{\%}) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P",
keywords = "Computer-assisted medical decision, Decision theory, Intracranial hematoma, Logistic regression, Medical decision support system, Neural networks, Traumatic brain injury",
author = "Li, {Yu Chuan} and Li Liu and Chiu, {Wen Ta} and Jian, {Wen Shan}",
year = "2000",
month = "1",
doi = "10.1016/S1386-5056(99)00054-4",
language = "English",
volume = "57",
pages = "1--9",
journal = "International Journal of Medical Informatics",
issn = "1386-5056",
publisher = "Elsevier Ireland Ltd",
number = "1",

}

TY - JOUR

T1 - Neural network modeling for surgical decisions on traumatic brain injury patients

AU - Li, Yu Chuan

AU - Liu, Li

AU - Chiu, Wen Ta

AU - Jian, Wen Shan

PY - 2000/1

Y1 - 2000/1

N2 - Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial- basis-function (RBF) neural network. From the 12 640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P

AB - Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial- basis-function (RBF) neural network. From the 12 640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P

KW - Computer-assisted medical decision

KW - Decision theory

KW - Intracranial hematoma

KW - Logistic regression

KW - Medical decision support system

KW - Neural networks

KW - Traumatic brain injury

UR - http://www.scopus.com/inward/record.url?scp=0033969016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033969016&partnerID=8YFLogxK

U2 - 10.1016/S1386-5056(99)00054-4

DO - 10.1016/S1386-5056(99)00054-4

M3 - Article

C2 - 10708251

AN - SCOPUS:0033969016

VL - 57

SP - 1

EP - 9

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

SN - 1386-5056

IS - 1

ER -