Combining PubMed knowledge and EHR data to develop a weighted bayesian network for pancreatic cancer prediction

Abstract

In this paper, we propose a novel method that combines PubMed knowledge and Electronic Health Records to develop a weighted Bayesian Network Inference (BNI) model for pancreatic cancer prediction. We selected 20 common risk factors associated with pancreatic cancer and used PubMed knowledge to weigh the risk factors. A keyword-based algorithm was developed to extract and classify PubMed abstracts into three categories that represented positive, negative, or neutral associations between each risk factor and pancreatic cancer. Then we designed a weighted BNI model by adding the normalized weights into a conventional BNI model. We used this model to extract the EHR values for patients with or without pancreatic cancer, which then enabled us to calculate the prior probabilities for the 20 risk factors in the BNI. The software iDiagnosis was designed to use this weighted BNI model for predicting pancreatic cancer. In an evaluation using a case-control dataset, the weighted BNI model significantly outperformed the conventional BNI and two other classifiers (k-Nearest Neighbor and Support Vector Machine). We conclude that the weighted BNI using PubMed knowledge and EHR data shows remarkable accuracy improvement over existing representative methods for pancreatic cancer prediction.

Figure 1

Steps to construct a node-weighted BNI

Figure 2

Class hierarchy of pancreatic cancer variables

Figure 3

The topology of the Bayesian Network for predicting pancreatic cancer

Figure 4

A simplified Bayesian Network for pancreatic cancer prediction: (a) two-node Bayesian Network (b) three-node Bayesian Network, where V_up is the set of all parent nodes of PC and V_down is the set of all child nodes of pancreatic cancer.

Figure 5

The interfaces of iDiagnosis for (a) the Bayesian function and (b) the eUtils function.

Figure 6

Comparison of ROC curves of the weighted BNI, the conventional BNI, KNN and SVM: the weighted BNI model is more accurate than the conventional BNI, KNN and SVM for pancreatic cancer prediction.