Send to

Choose Destination
See comment in PubMed Commons below
Oncology. 2005;68(1):79-86. Epub 2005 Apr 8.

Prediction of pancreatic cancer by serum biomarkers using surface-enhanced laser desorption/ionization-based decision tree classification.

Author information

Department of Pathophysiology, Shanghai Terry Fox Cancer Center and Institute of Hematology, Rui-Jin Hospital, Shanghai Second Medical University, Shanghai 200025, China.



In order to improve the prognosis of pancreatic cancer patients, it is crucial to explore novel tools for its early diagnosis. Here, we attempted to screen serum biomarkers to distinguish pancreatic cancer from non-cancer individuals.


47 serum samples from pancreatic cancer patients, 39 of whom had small surgically resectable cancers, were collected before surgery, and an additional 53 serum samples from age- and sex-matched individuals without cancer were used as controls. The surface-enhanced laser desorption/ionization (SELDI) ProteinChip was applied to analyze serum protein profiling. 54 samples (27 with pancreatic cancer and 27 controls) were analyzed in the training set by a decision tree algorithm to be able to separate pancreatic cancer from controls. A double-blind test was used to determine the sensitivity and specificity of the classification model.


A panel of six biomarkers was selected to set up a decision tree as the classification model. The model separated effectively pancreatic cancer from control samples, achieving a sensitivity of 88.9% and a specificity of 74.1%. The double-blind test challenged the model with a sensitivity of 80% and a specificity of 84.6%.


The SELDI ProteinChip combined with an artificial intelligence classification algorithm shows great potential for the diagnosis of pancreatic cancer.

[Indexed for MEDLINE]
PubMed Commons home

PubMed Commons

How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for S. Karger AG, Basel, Switzerland
    Loading ...
    Support Center