Background Predicting hospital mortality risk is essential for the care of heart failure patients, especially for those in intensive care units. Methods Using a novel machine learning algorithm, we constructed a risk stratification tool that correlated patients’ clinical features and in-hospital mortality. We used the extreme gradient boosting algorithm to generate a model predicting the mortality risk of heart failure patients in the intensive care unit in the derivation dataset of 5676 patients from the Medical Information Mart for Intensive Care III database. The logistic regression model and a common risk score for mortality were used for comparison. The eICU Collaborative Research Database dataset was used for external validation. Results The performance of the machine learning model was superior to that of conventional risk predictive methods, with the area under curve 0.831 (95% CI 0.820–0.843) and acceptable calibration. In external validation, the model had an area under the curve of 0.809 (95% CI 0.805–0.814). Risk stratification through the model was specific when the hospital mortality was very low, low, moderate, high, and very high (2.0%, 10.2%, 11.5%, 21.2% and 56.2%, respectively). The decision curve analysis verified that the machine learning model is the best clinically valuable in predicting mortality risk. Conclusion Using readily available clinical data in the intensive care unit, we built a machine learning-based mortality risk tool with prediction accuracy superior to that of linear regression model and common risk scores. The risk tool may support clinicians in assessing individual patients and making individualized treatment.

The gut microbiome is associated with hepatitis B virus (HBV)-induced liver disease, which progresses from chronic hepatitis B, to liver cirrhosis, and eventually to hepatocellular carcinoma. Studies have analyzed the gut microbiome at each stage of HBV-induced liver diseases, but a consensus has not been reached on the microbial signatures across these stages. Here, we conducted by a systematic meta-analysis of 486 fecal samples from publicly available 16S rRNA gene datasets across all disease stages, and validated the results by a gut microbiome characterization on an independent cohort of 15 controls, 23 chronic hepatitis B, 20 liver cirrhosis, and 22 hepatocellular carcinoma patients. The integrative analyses revealed 13 genera consistently altered at each of the disease stages both in public and validation datasets, suggesting highly robust microbiome signatures. Specifically, Colidextribacter and Monoglobus were enriched in healthy controls. An unclassified Lachnospiraceae genus was specifically elevated in chronic hepatitis B, whereas Bilophia was depleted. Prevotella and Oscillibacter were depleted in liver cirrhosis. And Coprococcus and Faecalibacterium were depleted in hepatocellular carcinoma. Classifiers established using these 13 genera showed diagnostic power across all disease stages in a cross-validation between public and validation datasets (AUC = 0.65–0.832). The identified microbial taxonomy serves as non-invasive biomarkers for monitoring the progression of HBV-induced liver disease, and may contribute to microbiome-based therapies.