Intelligent clinical decision supports for interferon treatment in chronic hepatitis C and B based on i-biopsy™

In chronic hepatitis C and B, which can progress to cirrhosis and liver cancer, Interferon is the only effective treatment, for carefully selected patients, but it is very expensive. Some of the selection criteria are based on liver biopsy, an invasive, costly and painful medical procedure. Developing an efficient selection system, based on non-invasive medical procedures, could be in the patients benefit and also save money. We investigated the capability of a knowledge discovery in data approach, using computational intelligence tools, to integrate information from various non-invasive data sources - imaging, clinical, and laboratory data - to assist the interferon therapeutical decision, mainly by predicting with acceptable accuracy the results of the biopsy. The resulted intelligent systems, tested on 700 patients with chronic hepatitis C and 500 patients with chronic hepatitis B, based on C5.0 decision trees and boosting, predict with 100% accuracy the results of the liver biopsy. Also, by integrating other patients selection criteria, they offer a non-invasive support for the correct Interferon therapeutic decision. To our best knowledge, these decision systems outperformed all similar systems published in the literature and offer a realistic opportunity to replace liver biopsy in this medical context.

[1]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[2]  Taghi M. Khoshgoftaar,et al.  Experimental perspectives on learning from imbalanced data , 2007, ICML '07.

[3]  Masoud Nikravesh,et al.  Feature Extraction: Foundations and Applications (Studies in Fuzziness and Soft Computing) , 2006 .

[4]  Masoud Nikravesh,et al.  Feature Extraction - Foundations and Applications , 2006, Feature Extraction.

[5]  Radu Badea,et al.  Intelligent virtual biopsy can predict fibrosis stage in chronic hepatitis C, combining ultrasonographic and laboratory parameters, with 100% accuracy , 2008 .

[6]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[7]  Patrice Cacoub,et al.  Meta-analyses of FibroTest diagnostic value in chronic liver disease , 2007, BMC gastroenterology.

[8]  J Rakela,et al.  The role of ultrasonography and automatic‐needle biopsy in outpatient percutaneous liver biopsy , 1996, Hepatology.

[9]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[10]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Researchers , 2007 .

[11]  A. Tobkes,et al.  Liver biopsy: review of methodology and complications. , 1995, Digestive diseases.

[12]  Radu Badea,et al.  732 TOWARD INTELLIGENT VIRTUAL BIOPSY: USING ARTIFICIAL INTELLIGENCE TO PREDICT FIBROSIS STAGE IN CHRONIC HEPATITIS C PATIENTS WITHOUT BIOPSY , 2008 .

[13]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[14]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.