6 引文 (Scopus)

摘要

Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful "second opinion" to assist neurosurgeon to predict outcome after traumatic brain injury.
原文英語
主出版物標題Studies in Health Technology and Informatics
頁面241-245
頁數5
116
出版狀態已發佈 - 2005
事件19th International Congress of the European Federation for Medical Informatics, MIE 2005 - Geneva, 瑞士
持續時間: 八月 28 2005九月 1 2005

其他

其他19th International Congress of the European Federation for Medical Informatics, MIE 2005
國家瑞士
城市Geneva
期間8/28/059/1/05

指紋

Craniocerebral Trauma
Glasgow Outcome Scale
Persistent Vegetative State
Neural networks
Brain
Databases
Neural Networks (Computer)
Taiwan
Recovery
Epidemiologic Studies
Referral and Consultation
Logistic Models
Neurons
Logistics
Traumatic Brain Injury

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

引用此文

Hsu, M-H., Li, Y. C., Chiu, W. T., & Yen, J. C. (2005). Outcome prediction after moderate and severe head injury using an artificial neural network. 於 Studies in Health Technology and Informatics (卷 116, 頁 241-245)

Outcome prediction after moderate and severe head injury using an artificial neural network. / Hsu, Min-Huei; Li, Yu Chuan; Chiu, Wen Ta; Yen, Ju Chuan.

Studies in Health Technology and Informatics. 卷 116 2005. p. 241-245.

研究成果: 書貢獻/報告類型會議貢獻

Hsu, M-H, Li, YC, Chiu, WT & Yen, JC 2005, Outcome prediction after moderate and severe head injury using an artificial neural network. 於 Studies in Health Technology and Informatics. 卷 116, 頁 241-245, 19th International Congress of the European Federation for Medical Informatics, MIE 2005, Geneva, 瑞士, 8/28/05.
Hsu M-H, Li YC, Chiu WT, Yen JC. Outcome prediction after moderate and severe head injury using an artificial neural network. 於 Studies in Health Technology and Informatics. 卷 116. 2005. p. 241-245
Hsu, Min-Huei ; Li, Yu Chuan ; Chiu, Wen Ta ; Yen, Ju Chuan. / Outcome prediction after moderate and severe head injury using an artificial neural network. Studies in Health Technology and Informatics. 卷 116 2005. 頁 241-245
@inproceedings{deea80ec0c734cb99cbc19fb424f9338,
title = "Outcome prediction after moderate and severe head injury using an artificial neural network",
abstract = "Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8{\%} of predictions of this model were correct, 14.6{\%} were pessimistic, and 9.6{\%} optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful {"}second opinion{"} to assist neurosurgeon to predict outcome after traumatic brain injury.",
keywords = "Artificial neural network, Head injury, Outcome prediction",
author = "Min-Huei Hsu and Li, {Yu Chuan} and Chiu, {Wen Ta} and Yen, {Ju Chuan}",
year = "2005",
language = "English",
isbn = "1586035495",
volume = "116",
pages = "241--245",
booktitle = "Studies in Health Technology and Informatics",

}

TY - GEN

T1 - Outcome prediction after moderate and severe head injury using an artificial neural network

AU - Hsu, Min-Huei

AU - Li, Yu Chuan

AU - Chiu, Wen Ta

AU - Yen, Ju Chuan

PY - 2005

Y1 - 2005

N2 - Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful "second opinion" to assist neurosurgeon to predict outcome after traumatic brain injury.

AB - Many studies have constructed predictive models for outcome after traumatic brain injury. Most of these attempts focused on dichotomous result, such as alive vs dead or good outcome vs poor outcome. If we want to predict more specific levels of outcome, we need more sophisticated models. We conducted this study to determine if artificial neural network modeling would predict outcome in five levels of Glasgow Outcome Scale (death, persistent vegetative state, severe disability, moderate disability, and good recovery) after moderate to severe head injury. The database was collected from a nation-wide epidemiological study of traumatic brain injury in Taiwan from July 1, 1995 to June 30, 1998. There were total 18583 records in this database and each record had thirty-two parameters. After pruning the records with minor cases (GCS 13) and missing data in the 132 variables, the number of cases decreased from 18583 to 4460. A step-wise logistic regression was applied to the remaining data set and 10 variables were selected as being statically significant in predicting outcome. These 10 variables were used as the input neurons for constructing neural network. Overall, 75.8% of predictions of this model were correct, 14.6% were pessimistic, and 9.6% optimistic. This neural network model demonstrated a significant difference of performance between different levels of Glasgow Outcome Scale. The prediction performance of dead or good recovery is best and the prediction of vegetative state is worst. An artificial neural network may provide a useful "second opinion" to assist neurosurgeon to predict outcome after traumatic brain injury.

KW - Artificial neural network

KW - Head injury

KW - Outcome prediction

UR - http://www.scopus.com/inward/record.url?scp=77956932961&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956932961&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1586035495

SN - 9781586035495

VL - 116

SP - 241

EP - 245

BT - Studies in Health Technology and Informatics

ER -