Machine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B.

Hepatic fibrosis is a common middle stage of the pathological processes of chronic liver diseases. Clinical intervention during the early stages of hepatic fibrosis can slow the development of liver cirrhosis and reduce the risk of developing liver cancer. Performing a liver biopsy, the gold standard for viral liver disease management, has drawbacks such as invasiveness and a relatively high sampling error rate. Real-time tissue elastography (RTE), one of the most recently developed technologies, might be promising imaging technology because it is both noninvasive and provides accurate assessments of hepatic fibrosis. However, determining the stage of liver fibrosis from RTE images in a clinic is a challenging task. In this study, in contrast to the previous liver fibrosis index (LFI) method, which predicts the stage of diagnosis using RTE images and multiple regression analysis, we employed four classical classifiers (i.e., Support Vector Machine, Naïve Bayes, Random Forest and K-Nearest Neighbor) to build a decision-support system to improve the hepatitis B stage diagnosis performance. Eleven RTE image features were obtained from 513 subjects who underwent liver biopsies in this multicenter collaborative research. The experimental results showed that the adopted classifiers significantly outperformed the LFI method and that the Random Forest(RF) classifier provided the highest average accuracy among the four machine algorithms. This result suggests that sophisticated machine-learning methods can be powerful tools for evaluating the stage of hepatic fibrosis and show promise for clinical applications.

Machine Learning Algorithms for Risk Prediction of Severe Hand-Foot-Mouth Disease in Children.

The identification of indicators for severe HFMD is critical for early prevention and control of the disease. With this goal in mind, 185 severe and 345 mild HFMD cases were assessed. Patient demographics, clinical features, MRI findings, and laboratory test results were collected. Gradient boosting tree (GBT) was then used to determine the relative importance (RI) and interaction effects of the variables. Results indicated that elevated white blood cell (WBC) count > 15 × 109/L (RI: 49.47, p < 0.001) was the top predictor of severe HFMD, followed by spinal cord involvement (RI: 26.62, p < 0.001), spinal nerve roots involvement (RI: 10.34, p < 0.001), hyperglycemia (RI: 3.40, p < 0.001), and brain or spinal meninges involvement (RI: 2.45, p = 0.003). Interactions between elevated WBC count and hyperglycemia (H statistic: 0.231, 95% CI: 0-0.262, p = 0.031), between spinal cord involvement and duration of fever ≥3 days (H statistic: 0.291, 95% CI: 0.035-0.326, p = 0.035), and between brainstem involvement and body temperature (H statistic: 0.313, 95% CI: 0-0.273, p = 0.017) were observed. Therefore, GBT is capable to identify the predictors for severe HFMD and their interaction effects, outperforming conventional regression methods.

Accuracy of real-time tissue elastography for the evaluation of hepatic fibrosis in patients with chronic hepatitis B: a prospective multicenter study.

BACKGROUND: The prognosis and management of hepatic fibrosis are closely related to the stage of the disease. The limitations of liver biopsy, which is the gold standard for treatment, include its invasiveness and sampling error. Ultrasound elasticity might be the most promising imaging technology for the noninvasive and accurate assessment of hepatic fibrosis. Real-time tissue elastography (RTE) measures the relative stiffness of the tissue in the region of interest caused by the heartbeat. Many studies have verified that RTE is useful for the diagnosis of hepatic fibrosis in patients with chronic hepatitis C (CHC). PURPOSE: To determine the formula of the liver fibrosis index for chronic hepatitis B (BLFI) and to validate the diagnostic accuracy of the BLFI for hepatic fibrosis compared with the liver fibrosis index (LFI). MATERIALS AND METHODS: RTE was performed in 747 prospectively enrolled patients with chronic hepatitis B (CHB) or cirrhosis from 8 centers in China; 375 patients were analyzed as the training set, and 372 patients were evaluated as the validation set. The fibrosis stage was diagnosed from pathological specimens obtained by ultrasound-guided liver biopsy. Nine image features were measured from strain images, and the new formula for the BLFI was obtained by combining the nine imaging features of the RTE images using multiple regression analysis of the training set. The BLFI and LFI were compared with the pathological fibrosis stage at diagnosis, and the diagnostic performances of the indexes were compared. RESULTS: The Spearman correlation coefficient between the BLFI and hepatic fibrosis stages was significantly positive (r = 0.711, p < 0.001), and significant differences were present between all disease stages. The areas under the receiver-operating characteristic (AUROC) curves of the BLFI and LFI for predicting significant fibrosis (S0-S1 vs. S2-S4) were 0.858 and 0.858, respectively. For cirrhosis (S0-S3 vs. S4), the AUROC curves of the BLFI and LFI were 0.868 and 0.862, respectively. CONCLUSION: The results of this large, multicenter study confirmed that RTE is valuable for the diagnosis of hepatic fibrosis in patients with CHB. However, the diagnostic efficiencies of the new BLFI and the original LFI, which were based on CHC, for the assessment of CHB hepatic fibrosis were similar; thus, the LFI has the potential to be used to directly evaluate the extent of hepatic fibrosis in patients with CHB.