Cooperations between engineers and physicians are crucial for studying and solving complex medical-biological problems. The study of obesity - unanimously regarded as a multi-factorial disease - is a typical example where specialists from various areas of medical research may be supported by engineers expert in system theory and software development. The effectiveness and the risk-benefit profile of medical intervention in this field (i.e., bariatric surgery and gastric banding) may require advanced data analysis to classify patient typologies and to predict the effects of therapies. In this paper the experience gained by a team of engineers joining a team of physicians is described: as a first step a specific software for data analysis was developed in the case of obese patients. The software toolbox implemented standard statistical models for classification of subjects according to their psychological profile. Afterwards, the analysis was extended using artificial neural networks for modeling and predicting the outcome of gastric banding in term of excess weight loss after 2 years, based on the preliminary knowledge of the psychological profile of patients involved. Obtained results demonstrate that the cooperation led to the development of a reliable tool for physicians, as an aid to forecasting the outcome of the therapy and to predict the patients candidate to get better benefits from a gastric banding treatment.

Statistical Toolbox in Medicine for Predicting Effects of Therapies in Obesity

LANDI, ALBERTO;PIAGGI, PAOLO;LIPPI, CHITA;SANTINI, FERRUCCIO;PINCHERA, ALDO
2010-01-01

Abstract

Cooperations between engineers and physicians are crucial for studying and solving complex medical-biological problems. The study of obesity - unanimously regarded as a multi-factorial disease - is a typical example where specialists from various areas of medical research may be supported by engineers expert in system theory and software development. The effectiveness and the risk-benefit profile of medical intervention in this field (i.e., bariatric surgery and gastric banding) may require advanced data analysis to classify patient typologies and to predict the effects of therapies. In this paper the experience gained by a team of engineers joining a team of physicians is described: as a first step a specific software for data analysis was developed in the case of obese patients. The software toolbox implemented standard statistical models for classification of subjects according to their psychological profile. Afterwards, the analysis was extended using artificial neural networks for modeling and predicting the outcome of gastric banding in term of excess weight loss after 2 years, based on the preliminary knowledge of the psychological profile of patients involved. Obtained results demonstrate that the cooperation led to the development of a reliable tool for physicians, as an aid to forecasting the outcome of the therapy and to predict the patients candidate to get better benefits from a gastric banding treatment.
2010
9781424449989
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/137017
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact