Liver Cancer Risk Quantification Through An Artificial Neural Network Based On Personal Health Data
A Ataei1*, J Deng2, W Muhammad3, (1) Florida Atlantic University, Boca Raton, FL, (2) Yale University School of Medicine, New Haven, CT, (3) Florida Atlantic University, Boca Raton, FL
Presentations
PO-GePV-M-20 (Sunday, 7/25/2021) [Eastern Time (GMT-4)]
Purpose: Liver cancer is the sixth most common type of cancer worldwide and is the third leading cause of cancer related mortality. Several types of cancer can form in the liver. Hepatocellular carcinoma (HCC) makes up 75%-85% of all primary liver cancers and it is a malignant disease with limited therapeutic options due to its aggressive progression. While the exact cause of liver cancer may not be known, this study models a reduction in liver cancer risk of an individual using an artificial neural network (ANN) in response to change habits/lifestyle.
Methods: To address this challenge, an artificial neural network (ANN) was developed, trained, and tested using the health data captured in the National Health Interview Survey (NHIS) and Pancreatic, Lung, Colorectal, and Ovarian cancer (PLCO) datasets to predict liver cancer risk. The ANN was trained on 70% (training dataset) of the data using 10-fold cross-validation, while the remaining 30% was withheld for further testing (testing dataset). The testing population was also stratified into low, medium, and high risk.
Results: The best performance of the model was observed with an area under the curve (AUC) of 0.80 and 0.81 for training and testing dataset, respectively.
Conclusion: Our results indicate that our ANN can be used to predict liver cancer risk with changes with lifestyle. This model may provide a novel approach to identify patients at higher risk who may benefited from early diagnosis and intervention.
Keywords
Not Applicable / None Entered.
Taxonomy
Not Applicable / None Entered.
Contact Email