Steven Walczak1, Vic Velanovich2. 1. School of Information and Florida Center for Cybersecurity, University of South Florida, 4202 E. Fowler Ave., CIS 1040, Tampa, FL, 33620, USA. swalczak@usf.edu. 2. Division of General Surgery, Morsani College of Medicine, University of South Florida, Tampa, FL, USA.
Abstract
OBJECTIVE: This study aims to evaluate the development of an artificial neural network (ANN) method for predicting the survival likelihood of pancreatic adenocarcinoma patients. The ANN predictive model should produce results with a 90% sensitivity. METHODS: A prospective examination of the records for 283 consecutive pancreatic adenocarcinoma patients is used to identify 219 records with complete data. These records are then used to create two unique samples which are then used to train and validate an ANN predictive model. Numerous network architectures are evaluated, following recommended ANN development protocols. RESULTS: Several backpropagation-trained ANNs were produced that satisfied the 90% sensitivity requirement. An ANN model with over a 91% sensitivity is selected because even though it did not have the highest sensitivity, it was able to achieve over 38% specificity. CONCLUSIONS: ANN models can accurately predict the 7-month survival of pancreatic adenocarcinoma patients, both with and without resection, at a 91% sensitivity and 38% specificity. This implies that ANN models may be useful objective decision tools in complex treatment decisions. This information may be used by patients and surgeons in determining optimal treatment plans that minimize regret and improve the quality of life for these patients.
OBJECTIVE: This study aims to evaluate the development of an artificial neural network (ANN) method for predicting the survival likelihood of pancreatic adenocarcinomapatients. The ANN predictive model should produce results with a 90% sensitivity. METHODS: A prospective examination of the records for 283 consecutive pancreatic adenocarcinomapatients is used to identify 219 records with complete data. These records are then used to create two unique samples which are then used to train and validate an ANN predictive model. Numerous network architectures are evaluated, following recommended ANN development protocols. RESULTS: Several backpropagation-trained ANNs were produced that satisfied the 90% sensitivity requirement. An ANN model with over a 91% sensitivity is selected because even though it did not have the highest sensitivity, it was able to achieve over 38% specificity. CONCLUSIONS: ANN models can accurately predict the 7-month survival of pancreatic adenocarcinomapatients, both with and without resection, at a 91% sensitivity and 38% specificity. This implies that ANN models may be useful objective decision tools in complex treatment decisions. This information may be used by patients and surgeons in determining optimal treatment plans that minimize regret and improve the quality of life for these patients.
Authors: Zeeshan Syed; Ilan Rubinfeld; Joe H Patton; Jennifer Ritz; Jack Jordan; Andrea Doud; Vic Velanovich Journal: J Am Coll Surg Date: 2011-04-13 Impact factor: 6.113
Authors: Jeffrey M Sutton; Gregory C Wilson; Ian M Paquette; Koffi Wima; Dennis J Hanseman; R Cutler Quillin; Jeffrey J Sussman; Michael J Edwards; Syed A Ahmad; Shimul A Shah; Daniel E Abbott Journal: HPB (Oxford) Date: 2014-07-16 Impact factor: 3.647
Authors: Elfriede H Bollschweiler; Stefan P Mönig; Karin Hensler; Stephan E Baldus; Keiichi Maruyama; Arnulf H Hölscher Journal: Ann Surg Oncol Date: 2004-05 Impact factor: 5.344