Prediction of successful weight reduction after bariatric surgery by data mining technologies

Yi Chih Lee, Wei Jei Lee, Tian Shyug Lee, Yang Chu Lin, Weu Wang, Phui Ly Liew, Ming Te Huang, Ching Wen Chien

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Background: Surgery is the only long-lasting effective treatment for morbid obesity. Prediction on successful weight loss after surgery by data mining technologies is lacking. We analyze the available information during the initial evaluation of patients referred to bariatric surgery by data mining methods for predictors of successful weight loss. Methods: 249 patients undergoing laparoscopic mini-gastric bypass (LMGB) or adjustable gastric banding (LAGB) were enrolled. Logistic Regression and Artificial Neural Network (ANN) technologies were used to predict weight loss. Overall classification capability of the designed diagnostic models was evaluated by the misclassification costs. Results: We studied 249 patients consisting of 72 men and 177 women over 2 years. Mean age was 33±9 years. 208 (83.5%) patients had successful weight reduction while 41 (16.5%) did not. Logistic Regression revealed that the type of operation had a significant prediction effect (P=0.000). Patients receiving LMGB had a better weight loss than those receiving LAGB (78.54%±26.87 vs 43.65%±26.08). ANN provided the same predicted factor on the type of operation but it further proposed that HbA1c and triglyceride were associated with success. HbA1c is lower in the successful than failed group (5.81±1.06 vs 6.05±1.49; P=NS), and triglyceride in the successful group is higher than in the failed group (171.29±112.62 vs 144.07±89.90; P=NS). Conclusion: Artificial neural network is a better modeling technique and the overall predictive accuracy is higher on the basis of multiple variables related to laboratory tests. LMGB, high preoperative triglyceride level, and low HbA1c level can predict successful weight reduction at 2 years.

Original languageEnglish
Pages (from-to)1235-1241
Number of pages7
JournalObesity Surgery
Volume17
Issue number9
DOIs
Publication statusPublished - Sep 2007

Fingerprint

Data Mining
Bariatric Surgery
Weight Loss
Technology
Gastric Bypass
Triglycerides
Stomach
Logistic Models
Morbid Obesity
Costs and Cost Analysis

Keywords

  • Artificial neural network
  • Bariatric surgery
  • Glycosylated hemoglobin A
  • Morbid obesity
  • Triglyceride
  • Weight reduction

ASJC Scopus subject areas

  • Surgery

Cite this

Lee, Y. C., Lee, W. J., Lee, T. S., Lin, Y. C., Wang, W., Liew, P. L., ... Chien, C. W. (2007). Prediction of successful weight reduction after bariatric surgery by data mining technologies. Obesity Surgery, 17(9), 1235-1241. https://doi.org/10.1007/s11695-007-9322-9

Prediction of successful weight reduction after bariatric surgery by data mining technologies. / Lee, Yi Chih; Lee, Wei Jei; Lee, Tian Shyug; Lin, Yang Chu; Wang, Weu; Liew, Phui Ly; Huang, Ming Te; Chien, Ching Wen.

In: Obesity Surgery, Vol. 17, No. 9, 09.2007, p. 1235-1241.

Research output: Contribution to journalArticle

Lee, Yi Chih ; Lee, Wei Jei ; Lee, Tian Shyug ; Lin, Yang Chu ; Wang, Weu ; Liew, Phui Ly ; Huang, Ming Te ; Chien, Ching Wen. / Prediction of successful weight reduction after bariatric surgery by data mining technologies. In: Obesity Surgery. 2007 ; Vol. 17, No. 9. pp. 1235-1241.
@article{513529ce39bb4e539eb3f8aa5b71d58c,
title = "Prediction of successful weight reduction after bariatric surgery by data mining technologies",
abstract = "Background: Surgery is the only long-lasting effective treatment for morbid obesity. Prediction on successful weight loss after surgery by data mining technologies is lacking. We analyze the available information during the initial evaluation of patients referred to bariatric surgery by data mining methods for predictors of successful weight loss. Methods: 249 patients undergoing laparoscopic mini-gastric bypass (LMGB) or adjustable gastric banding (LAGB) were enrolled. Logistic Regression and Artificial Neural Network (ANN) technologies were used to predict weight loss. Overall classification capability of the designed diagnostic models was evaluated by the misclassification costs. Results: We studied 249 patients consisting of 72 men and 177 women over 2 years. Mean age was 33±9 years. 208 (83.5{\%}) patients had successful weight reduction while 41 (16.5{\%}) did not. Logistic Regression revealed that the type of operation had a significant prediction effect (P=0.000). Patients receiving LMGB had a better weight loss than those receiving LAGB (78.54{\%}±26.87 vs 43.65{\%}±26.08). ANN provided the same predicted factor on the type of operation but it further proposed that HbA1c and triglyceride were associated with success. HbA1c is lower in the successful than failed group (5.81±1.06 vs 6.05±1.49; P=NS), and triglyceride in the successful group is higher than in the failed group (171.29±112.62 vs 144.07±89.90; P=NS). Conclusion: Artificial neural network is a better modeling technique and the overall predictive accuracy is higher on the basis of multiple variables related to laboratory tests. LMGB, high preoperative triglyceride level, and low HbA1c level can predict successful weight reduction at 2 years.",
keywords = "Artificial neural network, Bariatric surgery, Glycosylated hemoglobin A, Morbid obesity, Triglyceride, Weight reduction",
author = "Lee, {Yi Chih} and Lee, {Wei Jei} and Lee, {Tian Shyug} and Lin, {Yang Chu} and Weu Wang and Liew, {Phui Ly} and Huang, {Ming Te} and Chien, {Ching Wen}",
year = "2007",
month = "9",
doi = "10.1007/s11695-007-9322-9",
language = "English",
volume = "17",
pages = "1235--1241",
journal = "Obesity Surgery",
issn = "0960-8923",
publisher = "Springer New York LLC",
number = "9",

}

TY - JOUR

T1 - Prediction of successful weight reduction after bariatric surgery by data mining technologies

AU - Lee, Yi Chih

AU - Lee, Wei Jei

AU - Lee, Tian Shyug

AU - Lin, Yang Chu

AU - Wang, Weu

AU - Liew, Phui Ly

AU - Huang, Ming Te

AU - Chien, Ching Wen

PY - 2007/9

Y1 - 2007/9

N2 - Background: Surgery is the only long-lasting effective treatment for morbid obesity. Prediction on successful weight loss after surgery by data mining technologies is lacking. We analyze the available information during the initial evaluation of patients referred to bariatric surgery by data mining methods for predictors of successful weight loss. Methods: 249 patients undergoing laparoscopic mini-gastric bypass (LMGB) or adjustable gastric banding (LAGB) were enrolled. Logistic Regression and Artificial Neural Network (ANN) technologies were used to predict weight loss. Overall classification capability of the designed diagnostic models was evaluated by the misclassification costs. Results: We studied 249 patients consisting of 72 men and 177 women over 2 years. Mean age was 33±9 years. 208 (83.5%) patients had successful weight reduction while 41 (16.5%) did not. Logistic Regression revealed that the type of operation had a significant prediction effect (P=0.000). Patients receiving LMGB had a better weight loss than those receiving LAGB (78.54%±26.87 vs 43.65%±26.08). ANN provided the same predicted factor on the type of operation but it further proposed that HbA1c and triglyceride were associated with success. HbA1c is lower in the successful than failed group (5.81±1.06 vs 6.05±1.49; P=NS), and triglyceride in the successful group is higher than in the failed group (171.29±112.62 vs 144.07±89.90; P=NS). Conclusion: Artificial neural network is a better modeling technique and the overall predictive accuracy is higher on the basis of multiple variables related to laboratory tests. LMGB, high preoperative triglyceride level, and low HbA1c level can predict successful weight reduction at 2 years.

AB - Background: Surgery is the only long-lasting effective treatment for morbid obesity. Prediction on successful weight loss after surgery by data mining technologies is lacking. We analyze the available information during the initial evaluation of patients referred to bariatric surgery by data mining methods for predictors of successful weight loss. Methods: 249 patients undergoing laparoscopic mini-gastric bypass (LMGB) or adjustable gastric banding (LAGB) were enrolled. Logistic Regression and Artificial Neural Network (ANN) technologies were used to predict weight loss. Overall classification capability of the designed diagnostic models was evaluated by the misclassification costs. Results: We studied 249 patients consisting of 72 men and 177 women over 2 years. Mean age was 33±9 years. 208 (83.5%) patients had successful weight reduction while 41 (16.5%) did not. Logistic Regression revealed that the type of operation had a significant prediction effect (P=0.000). Patients receiving LMGB had a better weight loss than those receiving LAGB (78.54%±26.87 vs 43.65%±26.08). ANN provided the same predicted factor on the type of operation but it further proposed that HbA1c and triglyceride were associated with success. HbA1c is lower in the successful than failed group (5.81±1.06 vs 6.05±1.49; P=NS), and triglyceride in the successful group is higher than in the failed group (171.29±112.62 vs 144.07±89.90; P=NS). Conclusion: Artificial neural network is a better modeling technique and the overall predictive accuracy is higher on the basis of multiple variables related to laboratory tests. LMGB, high preoperative triglyceride level, and low HbA1c level can predict successful weight reduction at 2 years.

KW - Artificial neural network

KW - Bariatric surgery

KW - Glycosylated hemoglobin A

KW - Morbid obesity

KW - Triglyceride

KW - Weight reduction

UR - http://www.scopus.com/inward/record.url?scp=38549113987&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549113987&partnerID=8YFLogxK

U2 - 10.1007/s11695-007-9322-9

DO - 10.1007/s11695-007-9322-9

M3 - Article

C2 - 18074500

AN - SCOPUS:38549113987

VL - 17

SP - 1235

EP - 1241

JO - Obesity Surgery

JF - Obesity Surgery

SN - 0960-8923

IS - 9

ER -