Justified granulation aided noninvasive liver fibrosis classification system

Abstract

Background: According to the World Health Organization 130-150 million (according to WHO) of people globally are chronically infected with hepatitis C virus. The virus is responsible for chronic hepatitis that ultimately may cause liver cirrhosis and death. The disease is progressive, however antiviral treatment may slow down or stop its development. Therefore, it is important to estimate the severity of liver fibrosis for diagnostic, therapeutic and prognostic purposes. Liver biopsy provides a high accuracy diagnosis, however it is painful and invasive procedure. Recently, we witness an outburst of non-invasive tests (biological and physical ones) aiming to define severity of liver fibrosis, but commonly used FibroTest®, according to an independent research, in some cases may have accuracy lower than 50 %. In this paper a data mining and classification technique is proposed to determine the stage of liver fibrosis using easily accessible laboratory data.

Methods: Research was carried out on archival records of routine laboratory blood tests (morphology, coagulation, biochemistry, protein electrophoresis) and histopathology records of liver biopsy as a reference value. As a result, the granular model was proposed, that contains a series of intervals representing influence of separate blood attributes on liver fibrosis stage. The model determines final diagnosis for a patient using aggregation method and voting procedure. The proposed solution is robust to missing or corrupted data.

Results: The results were obtained on data from 290 patients with hepatitis C virus collected over 6 years. The model has been validated using training and test data. The overall accuracy of the solution is equal to 67.9 %. The intermediate liver fibrosis stages are hard to distinguish, due to effectiveness of biopsy itself. Additionally, the method was verified against dataset obtained from 365 patients with liver disease of various etiologies. The model proved to be robust to new data. What is worth mentioning, the error rate in misclassification of the first stage and the last stage is below 6.5 % for all analyzed datasets.

Conclusions: The proposed system supports the physician and defines the stage of liver fibrosis in chronic hepatitis C. The biggest advantage of the solution is a human-centric approach using intervals, which can be verified by a specialist, before giving the final decision. Moreover, it is robust to missing data. The system can be used as a powerful support tool for diagnosis in real treatment.

Fig. 1

The illustration of X_k,n set for a given k and n in a value domain

Fig. 2

Data representation during classification process: clouds of black points (elements of X_k,n sets), series of intervals and fuzzy sets. The intuitive classification algorithm merges the obtained results using voting procedure

Fig. 3

The illustration of X_k,n set for given α in value domain. The functions V_l and V_r assume maximal values in proximity of local concentration of groups of elements of the set

Fig. 4

The example of normalized V_l function for various α value. The maximal value of V_l function, for given α, allows to find a local concentration of elements within X_k,n set

Fig. 5

The RBC attribute interval representation for class 0, 1 and 2 respectively: (a) histogram (b) generated interval granules for z = 3

Fig. 6

$\tilde{g}$ membership function for a given αj and changing d parameter: (a) example, (b) real estimated data for Age attribute

Fig. 7

Classification example illustrated on two attributes: Age (a) and RBC (b). The values of attributes of classified patient are compared against the fuzzy representation of classes. Then, using averaging (c) and weighted voting d, the patient’s fibrosis class is found

Fig. 8

Calibration of proposed method using number of cuts (z - discrete parameter) and generalization parameter (g)

Fig. 9

Tuning of proposed method of attributes reduction vs. overall accuracy. The classification is performed only on selected set of attributes (K' ⊂K) with the smallest overlap between all fibrosis classes