Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system

Tetsuro Takayama, Kozo Takayama, Nagamu Inoue, Shinsuke Funakoshi, Hiroshi Serizawa, Noriaki Watanabe, Naoki Kumagai, Kanji Tsuchimoto, Toshifumi Hibi

研究成果: Article

10 引用 (Scopus)

抄録

BACKGROUND: The demand for percutaneous endoscopic gastrostomy (PEG) has increased because it is safe and a technically easy method, but it has risks of severe complications including death and a high mortality rate within 30 days. At present, we cannot predict survival or the incidence of complications before tube placement in an individual. Earlier studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. AIMS: We predicted the survival and complications before PEG placement in an individual by using artificial neural network (ANN) system, which can assess the nonlinear relationship. METHODS: We studied 100 patients who underwent PEG at the Kitasato Medical Institute Hospital from 1997 to 2005. Clinical data and laboratory data were used as input data. Complications related to PEG placement and survival dates were historically and prospectively measured. From the clinical data and laboratory data, we examined the prediction of outcome in individual patients using multiple logistic regression analysis and an ANN. RESULTS: The correct answer rate of survival by multiple logistic regression analysis was 67.9%. In contrast, using the ANN, we correctly predicted the survival date and aspiration pneumonia in 75 and 89% of patients, respectively. There was a nonlinear relationship among input factors and survival and complications. CONCLUSION: We correctly predicted the outcome and complications of individual patients with PEG with a high correct answer rate. Our data show the potential of an ANN as a powerful tool in daily clinical use to individualize treatment ('tailor-made medicine') for PEG and reduce costs.

元の言語English
ページ(範囲)1279-1285
ページ数7
ジャーナルEuropean Journal of Gastroenterology and Hepatology
21
発行部数11
DOI
出版物ステータスPublished - 2009 11

Fingerprint

Gastrostomy
Survival
Logistic Models
Regression Analysis
Aspiration Pneumonia
Survival Rate
Medicine
Costs and Cost Analysis
Mortality
Incidence

ASJC Scopus subject areas

  • Gastroenterology
  • Hepatology

これを引用

Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system. / Takayama, Tetsuro; Takayama, Kozo; Inoue, Nagamu; Funakoshi, Shinsuke; Serizawa, Hiroshi; Watanabe, Noriaki; Kumagai, Naoki; Tsuchimoto, Kanji; Hibi, Toshifumi.

:: European Journal of Gastroenterology and Hepatology, 巻 21, 番号 11, 11.2009, p. 1279-1285.

研究成果: Article

Takayama, Tetsuro ; Takayama, Kozo ; Inoue, Nagamu ; Funakoshi, Shinsuke ; Serizawa, Hiroshi ; Watanabe, Noriaki ; Kumagai, Naoki ; Tsuchimoto, Kanji ; Hibi, Toshifumi. / Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system. :: European Journal of Gastroenterology and Hepatology. 2009 ; 巻 21, 番号 11. pp. 1279-1285.
@article{15da5163b9b74dd597de83f9d3e02413,
title = "Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system",
abstract = "BACKGROUND: The demand for percutaneous endoscopic gastrostomy (PEG) has increased because it is safe and a technically easy method, but it has risks of severe complications including death and a high mortality rate within 30 days. At present, we cannot predict survival or the incidence of complications before tube placement in an individual. Earlier studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. AIMS: We predicted the survival and complications before PEG placement in an individual by using artificial neural network (ANN) system, which can assess the nonlinear relationship. METHODS: We studied 100 patients who underwent PEG at the Kitasato Medical Institute Hospital from 1997 to 2005. Clinical data and laboratory data were used as input data. Complications related to PEG placement and survival dates were historically and prospectively measured. From the clinical data and laboratory data, we examined the prediction of outcome in individual patients using multiple logistic regression analysis and an ANN. RESULTS: The correct answer rate of survival by multiple logistic regression analysis was 67.9{\%}. In contrast, using the ANN, we correctly predicted the survival date and aspiration pneumonia in 75 and 89{\%} of patients, respectively. There was a nonlinear relationship among input factors and survival and complications. CONCLUSION: We correctly predicted the outcome and complications of individual patients with PEG with a high correct answer rate. Our data show the potential of an ANN as a powerful tool in daily clinical use to individualize treatment ('tailor-made medicine') for PEG and reduce costs.",
keywords = "Artificial neural network, Percutaneous endoscopic gastrostomy, Prediction, Survival",
author = "Tetsuro Takayama and Kozo Takayama and Nagamu Inoue and Shinsuke Funakoshi and Hiroshi Serizawa and Noriaki Watanabe and Naoki Kumagai and Kanji Tsuchimoto and Toshifumi Hibi",
year = "2009",
month = "11",
doi = "10.1097/MEG.0b013e32832a4eae",
language = "English",
volume = "21",
pages = "1279--1285",
journal = "European Journal of Gastroenterology and Hepatology",
issn = "0954-691X",
publisher = "Lippincott Williams and Wilkins",
number = "11",

}

TY - JOUR

T1 - Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system

AU - Takayama, Tetsuro

AU - Takayama, Kozo

AU - Inoue, Nagamu

AU - Funakoshi, Shinsuke

AU - Serizawa, Hiroshi

AU - Watanabe, Noriaki

AU - Kumagai, Naoki

AU - Tsuchimoto, Kanji

AU - Hibi, Toshifumi

PY - 2009/11

Y1 - 2009/11

N2 - BACKGROUND: The demand for percutaneous endoscopic gastrostomy (PEG) has increased because it is safe and a technically easy method, but it has risks of severe complications including death and a high mortality rate within 30 days. At present, we cannot predict survival or the incidence of complications before tube placement in an individual. Earlier studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. AIMS: We predicted the survival and complications before PEG placement in an individual by using artificial neural network (ANN) system, which can assess the nonlinear relationship. METHODS: We studied 100 patients who underwent PEG at the Kitasato Medical Institute Hospital from 1997 to 2005. Clinical data and laboratory data were used as input data. Complications related to PEG placement and survival dates were historically and prospectively measured. From the clinical data and laboratory data, we examined the prediction of outcome in individual patients using multiple logistic regression analysis and an ANN. RESULTS: The correct answer rate of survival by multiple logistic regression analysis was 67.9%. In contrast, using the ANN, we correctly predicted the survival date and aspiration pneumonia in 75 and 89% of patients, respectively. There was a nonlinear relationship among input factors and survival and complications. CONCLUSION: We correctly predicted the outcome and complications of individual patients with PEG with a high correct answer rate. Our data show the potential of an ANN as a powerful tool in daily clinical use to individualize treatment ('tailor-made medicine') for PEG and reduce costs.

AB - BACKGROUND: The demand for percutaneous endoscopic gastrostomy (PEG) has increased because it is safe and a technically easy method, but it has risks of severe complications including death and a high mortality rate within 30 days. At present, we cannot predict survival or the incidence of complications before tube placement in an individual. Earlier studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. AIMS: We predicted the survival and complications before PEG placement in an individual by using artificial neural network (ANN) system, which can assess the nonlinear relationship. METHODS: We studied 100 patients who underwent PEG at the Kitasato Medical Institute Hospital from 1997 to 2005. Clinical data and laboratory data were used as input data. Complications related to PEG placement and survival dates were historically and prospectively measured. From the clinical data and laboratory data, we examined the prediction of outcome in individual patients using multiple logistic regression analysis and an ANN. RESULTS: The correct answer rate of survival by multiple logistic regression analysis was 67.9%. In contrast, using the ANN, we correctly predicted the survival date and aspiration pneumonia in 75 and 89% of patients, respectively. There was a nonlinear relationship among input factors and survival and complications. CONCLUSION: We correctly predicted the outcome and complications of individual patients with PEG with a high correct answer rate. Our data show the potential of an ANN as a powerful tool in daily clinical use to individualize treatment ('tailor-made medicine') for PEG and reduce costs.

KW - Artificial neural network

KW - Percutaneous endoscopic gastrostomy

KW - Prediction

KW - Survival

UR - http://www.scopus.com/inward/record.url?scp=70350166178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350166178&partnerID=8YFLogxK

U2 - 10.1097/MEG.0b013e32832a4eae

DO - 10.1097/MEG.0b013e32832a4eae

M3 - Article

C2 - 19478677

AN - SCOPUS:70350166178

VL - 21

SP - 1279

EP - 1285

JO - European Journal of Gastroenterology and Hepatology

JF - European Journal of Gastroenterology and Hepatology

SN - 0954-691X

IS - 11

ER -