Premium
SU‐E‐T‐131: Artificial Neural Networks Applied to Overall Survival Prediction for Patients with Periampullary Carcinoma
Author(s) -
Gong Y,
Yu J,
Yeung V,
Palmer J,
Yu Y,
Lu B,
Babinsky L,
Burkhart R,
Leiby B,
Siow V,
Lavu H,
Rosato E,
Winter J,
Lewis N,
Sama A,
Mitchell E,
Anne P,
Hurwitz M,
Yeo C,
BarAd V,
Xiao Y
Publication year - 2015
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.4924492
Subject(s) - medicine , artificial neural network , censoring (clinical trials) , survival analysis , concordance , artificial intelligence , computer science , pathology
Purpose: Artificial neural networks (ANN) can be used to discover complex relations within datasets to help with medical decision making. This study aimed to develop an ANN method to predict two‐year overall survival of patients with peri‐ampullary cancer (PAC) following resection. Methods: Data were collected from 334 patients with PAC following resection treated in our institutional pancreatic tumor registry between 2006 and 2012. The dataset contains 14 variables including age, gender, T‐stage, tumor differentiation, positive‐lymph‐node ratio, positive resection margins, chemotherapy, radiation therapy, and tumor histology.After censoring for two‐year survival analysis, 309 patients were left, of which 44 patients (∼15%) were randomly selected to form testing set. The remaining 265 cases were randomly divided into training set (211 cases, ∼80% of 265) and validation set (54 cases, ∼20% of 265) for 20 times to build 20 ANN models. Each ANN has one hidden layer with 5 units. The 20 ANN models were ranked according to their concordance index (c‐index) of prediction on validation sets. To further improve prediction, the top 10% of ANN models were selected, and their outputs averaged for prediction on testing set. Results: By random division, 44 cases in testing set and the remaining 265 cases have approximately equal two‐year survival rates, 36.4% and 35.5% respectively. The 20 ANN models, which were trained and validated on the 265 cases, yielded mean c‐indexes as 0.59 and 0.63 on validation sets and the testing set, respectively. C‐index was 0.72 when the two best ANN models (top 10%) were used in prediction on testing set. The c‐index of Cox regression analysis was 0.63. Conclusion: ANN improved survival prediction for patients with PAC. More patient data and further analysis of additional factors may be needed for a more robust model, which will help guide physicians in providing optimal post‐operative care. This project was supported by PA CURE Grant.