ФП Тест / version 2.0

Aim. The purpose of the work was the development of a machine learning model for diagnosing the stage of liver fibrosis in patients with chronic viral hepatitis C according to the data of routine clinical examination.

Materials and methods. A total of 1240 patients with chronic viral hepatitis C was examined. A set of data obtained from 689 patients balancing by the stage of liver fibrosis was used for developing and testing machine learning models. 9 routine clinical parameters were selected as the most important predictors for determining the likelihood of liver fibrosis the 3–4 stages presence: age, height, weight and body mass index of the patient, the number of platelets in the clinical blood test, levels of alanine transaminase, aspartate transaminase, gamma-glutamyltransferase, and total bilirubin in a biochemical blood test.

Results. The accuracy of the developed method for determining the 3–4 stages of liver fibrosis in patients with chronic viral hepatitis C in comparison with the «gold standard» of diagnosis (liver biopsy) was 80.56% (95% CI: 69.53–88.94%), sensitivity — 66.67%, specificity — 94.44%.

Conclusion. The developed method is an alternative to more expensive and geographically inaccessible studies. The method does not require the purchase of additional equipment or software, as well as additional laboratory tests, when used in real clinical practice. The introduction of the method into clinical practice can help to solve the problem of low material and territorial availability of diagnostic tests and allow determining the stage of liver fibrosis in patients with chronic viral hepatitis C.

Aim. To evaluate the informative value of the new diagnostic method «ФП Тест» version 1.0 to determine the 3-4 stage of liver fibrosis in patients with chronic viral hepatitis C.

Materials and methods. A new diagnostic method «ФП Тест» is developed on the basis of an artificial neural network using deep learning technologies. To form the training and test samples, 809 patients with chronic viral hepatitis C were included in the study. 291 patients were randomly selected in the training sample and 76 patients in the test sample. As a standard method for diagnosing the stage of liver fibrosis according to the Metavir scale, all patients in the test sample underwent a liver biopsy. Liver fibrosis of stage 0–2 was detected in 51.32% of patients in the test sample, liver fibrosis of stage 3-4 was found in 48.68% of patients. To conduct a comparative assessment of the information content of minimally invasive tests, the APRI and FIB – 4 indices were calculated.

Results. The accuracy of the «ФП Тест» version 1.0 method for diagnosing stage 3-4 liver fibrosis was 78.95%, sensitivity - 70.27%, specificity - 87.18%. The informative indices of calculated indices for detecting liver fibrosis of stages 3-4 were: APRI (accuracy - 68.42%, sensitivity - 54.05%, specificity - 82.05%), FIB – 4 (accuracy - 75.00%, sensitivity - 67.58%, specificity - 82.05%). The values ​​of the area under the ROC – curve for the classification of patients depending on the presence or absence of stage 3–4 liver fibrosis were: «ФП Тест» version 1.0 (AUC = 0.77), APRI (AUC = 0.77), FIB – 4 ( AUC = 0.81).

Conclusion. The new diagnostic method «ФП Тест» is a simple, affordable and informative test for determining stage 3-4 liver fibrosis in patients with chronic viral hepatitis C.

Aim. To evaluate the informative value of the new diagnostic method «ФП Тест» version 1.0 to determine moderate / severe hepatitis activity in patients with chronic HCV infection.

Materials and methods. The study included 304 patients with chronic HCV infection. 184 patients were randomly selected into the training sample, 120 patients into the test sample. As a standard method for diagnosing hepatitis activity, a puncture biopsy of the liver was performed in all patients with the calculation of the histological activity index according to the Knodell scale. Minimum / low degree of hepatitis activity (HAI 0–8 points) was detected in 46.38% of patients, moderate / severe hepatitis activity (HAI 9–18 points) in 53.62% of patients.

Results. The accuracy of the «ФП Тест» version 1.0 method for diagnosing moderate / severe hepatitis activity was 79.17%, sensitivity - 78.46%, specificity - 80.00%. The values ​​of the area under the ROC – curve for classifying patients depending on the presence or absence of moderate / severe hepatitis activity were: «ФП Тест» version 1.0 (AUC = 0.84, cut-off value = 0.52), determination of ALT level ( AUC = 0.74, cut-off value = 61.40 U / L), determination of AST level (AUC = 0.76, cut-off value = 39.00 U / L).

Conclusion. The new diagnostic method «ФП Тест» is a simple, affordable and informative test to determine moderate / severe hepatitis activity in patients with chronic HCV infection.