Search

Background:. The basis of individualized treatment should be individualized mortality risk predictive information. The present study aimed to develop an online individual mortality risk predictive tool for acute-on-chronic liver failure (ACLF) patients based on a random survival forest (RSF) algorithm. Methods:. The current study retrospectively enrolled ACLF patients from the Department of Infectious Diseases of The First People's Hospital of Foshan, Shunde Hospital of Southern Medical University, and Jiangmen Central Hospital. Two hundred seventy-six consecutive ACLF patients were included in the present study as a model cohort (n = 276). Then the current study constructed a validation cohort by drawing patients from the model dataset based on the resampling method (n = 276). The RSF algorithm was used to develop an individual prognostic model for ACLF patients. The Brier score was used to evaluate the diagnostic accuracy of prognostic models. The weighted mean rank estimation method was used to compare the differences between the areas under the time-dependent ROC curves (AUROCs) of prognostic models. Results:. Multivariate Cox regression identified hepatic encephalopathy (HE), age, serum sodium level, acute kidney injury (AKI), red cell distribution width (RDW), and international normalization index (INR) as independent risk factors for ACLF patients. A simplified RSF model was developed based on these previous risk factors. The AUROCs for predicting 3-, 6-, and 12-month mortality were 0.916, 0.916, and 0.905 for the RSF model and 0.872, 0.866, and 0.848 for the Cox model in the model cohort, respectively. The Brier scores were 0.119, 0.119, and 0.128 for the RSF model and 0.138, 0.146, and 0.156 for the Cox model, respectively. The nonparametric comparison suggested that the RSF model was superior to the Cox model for predicting the prognosis of ACLF patients. Conclusions:. The current study developed a novel online individual mortality risk predictive tool that could predict individual mortality risk predictive curves for individual patients. Additionally, the current online individual mortality risk predictive tool could further provide predicted mortality percentages and 95% confidence intervals at user-defined time points.

Background: Patients with liver cirrhosis are at higher risk of developing hepatocellular carcinoma (HCC). Due to the low accuracy of current methods, new non-invasive strategies for early HCC diagnosis in cirrhotic patients are needed. Methods: A case-control study recruited a total of 2,250 patients with liver cirrhosis (LC), 508 with HCC, and 476 healthy controls (CTRL), from 13 hospitals in 11 provinces of China. Four genomic features of cell-free DNA (cfDNA), including nucleosome footprint, fragmentation, base mismatch and 5-hydroxymethylcytosines were profiled. Training and validation cohorts helped develop the integrated diagnostic model, and a test cohort was used to evaluate its performance. Findings: We established a classifier of each feature for HCC against non-HCC (cirrhosis & healthy control). By integrating these four genomic features, we developed a novel diagnostic model (HIFI, 5-Hydroxymethylcytosines/base mIsmatch/Fragmentation/nucleosome footprInt), and achieved a higher accuracy in differentiating HCCs from liver cirrhosis (AUC=0.997 [0.994-0.999], sensitivity 95.42%, specificity 97.67% in test set) than AFP or PIVKA-II, irrespective of the following demographics and clinical features, age, HBV status, Child-Pugh score, BCLC stage, tumor size, and AFP status. In AFP positive (AFP>20ug/L) liver cirrhosis patients and AFP/PIVKA-II negative (AFP 400μg/L: 100% in liver cirrhosis patients; AFP

Background. We aimed to determine a discriminant function for prognosis in chronic severe hepatitis B (CSHB), by discriminant analysis of prognostic indexes and probability of death. Methods. In 205 patients with chronic severe hepatitis B (101 patients in the survival group and 104 patients in the death group), we carried out discriminant analysis of serum total bilirubin, prothrombin activity, white blood cells, creatinine, maximum depth of ascites, hepatic encephalopathy, singultus, and digestive tract hemorrhage. Results. The discriminant function was V = 0.00043 × total bilirubin (µM) − 0.025 × prothrombin activity (%) + 0.056 × white blood cells (109/l) + 0.00284 × creatinine (µM) + 0.0014 × maximum depth of ascites (mm) + 0.724 × hepatic encephalopathy score + 0.078 × singultus score + 0.457 × digestive tract hemorrhage score − 2.488. The correctness of the function for predicting death in the death group was 92.3%, and that for predicting survival in the survival group was 96.0%. When the V values were −∞, −4.595, −2.197, −1.386, −0.405, 0.405, 1.386, 2.197, 2.944, 4.595, and ∞, a posterior probabilities of death were 0%, 5%, 10%, 20%, 40%, 60%, 80%, 90%, 95%, 99%, and 100%, respectively. Conclusions. The discriminant function is an objective, convenient, and practical method to assess the prognosis of chronic severe hepatitis B.