FibroTest attributes to generate decision trees in hepatitis C

Jun 15, 2009

In recent years the use of non-invasive biomarkers to assess liver fibrosis has become widely accepted. Although the combination of surrogate markers, such as those employed by the FibroTest, have a high predictive value for the assessment of significant fibrosis, it is important to find tools that can improve its accuracy, particularly in intermediate stages and to reinforce its reliability by ensuring that the classification results are independent of contingent features of the classification technique.

A research article to be published in the World Journal of Gastroenterology explored the automatic generation of decision trees to simplify a classification process and to provide additional information to support the classification rational. The research group, led by Dr. Kershenobich from México´s National University (UNAM), used the C4.5 classification algorithm to construct decision trees with data from 261 patients with chronic hepatitis C without a liver biopsy. The FibroTest attributes (age, gender, bilirubin, apolipoprotein, haptoglobin, 2 macroglobulin, and glutamyl transpeptidase) were used as predictors, and the FibroTest score as the target.

The construction of decision trees using the FibroTest attributes provided explicit rules to relate the range of values of the with scores, and they might help in gaining a better grasp of the importance and significance of the test.

Analysis, such as the one performed in the present work, could help to further classify preclinical subgroups and identify subclasses of rapid or slower fibrosers. This classification should enhance our ability to assess differences in fibrosis scores in clinical studies and improve our understanding of fibrosis progression.

The present work is the result of a group effort between members of the Department of Experimental Medicine of the Faculty of Medicine and the Institute of Applied Mathematics at the Universidad Nacional Autonoma of Mexico (UNAM), which provided a grant to support the investigation.

Source: World Journal of Gastroenterology (news : web)

Explore further: Obama to announce major Ebola effort

add to favorites email to friend print save as pdf

Related Stories

MRI predicts liver fibrosis, study says

Oct 23, 2007

Moderate to severe chronic liver disease can be predicted with the use of diffusion-weighted MRI (DWI), according to a recent study conducted by researchers at New York University Medical Center in New York, NY.

Noninvasive ways to assess liver disease

Feb 02, 2008

Two new studies examine non-invasive ways to determine liver fibrosis and cirrhosis. An enhanced version of the Original European Liver Fibrosis panel was found to have good diagnostic accuracy for fibrosis in patients with ...

Noninvasive tests for cirrhosis may help to avoid liver biopsy

Oct 01, 2007

Newer ultrasound and magnetic resonance (MR) imaging tests yield encouraging initial results in diagnosing fibrosis (scarring) and cirrhosis of the liver, according to three studies in the October issue of the journal Clinical Ga ...

Recommended for you

Tracing the rise of Ebola in West Africa

1 hour ago

Since the Ebola outbreak first emerged in West Africa, The Associated Press has been reporting on it. A timeline compiled from AP dispatches since March shows the dreaded disease being identified in a remote ...

Spinal manipulation helps relieve back-related leg pain

2 hours ago

(HealthDay)—Adding spinal manipulative therapy (SMT) to home exercise and advice (HEA) may improve short-term outcomes in patients with subacute and chronic back-related leg pain (BRLP), according to research ...

User comments : 0