Background: The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. Methods: The data in this paper were selected from patients with chronic heart failure who were hospitalized at the First Affiliated Hospital of Kunming Medical University, from 2017 to 2019 with cardiac function class III-IV. The dataset was explored using six different machine learning models, including logistic regression, naive Bayes, random forest classifier, extreme gradient boost, K-nearest neighbor, and decision tree. Finally, interpretable methods based on machine learning, such as SHAP value, permutation importance, and partial dependence plots, were used to estimate the 3-year all-cause mortality risk and produce individual interpretations of the model's conclusions. Result: In this paper, random forest was identified as the optimal aools lgorithm for this dataset. We also incorporated relevant machine learning interpretable tand techniques to improve disease prognosis, including permutation importance, PDP plots and SHAP values for analysis. From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. Conclusion: The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. Machine learning in combination with permutation importance, PDP plots, and the SHAP value could offer a clear explanation of individual risk prediction and give doctors an intuitive knowledge of the functions of important model components.

Purpose: Luteolin is a promising candidate for diabetic nephropathy due to its potential anti-inflammatory and anti-fibrotic properties. This study explored the molecular mechanisms through which luteolin combats fibrosis in DN. Methods: Potential targets affected by luteolin and genes associated with DN were collected from databases. Overlapping targets between luteolin and diabetic nephropathy were identified through Venn analysis. A protein-protein interaction network was constructed using these common targets, and critical pathways and targets were elucidated through GO and KEGG analysis. These pathways and targets were confirmed using a streptozotocin-induced mouse model. Luteolin was administered at 45 mg/kg and 90 mg/kg. Various parameters were evaluated, including body weight, blood glucose levels, and histopathological examinations. Protein levels related to energy metabolism, inflammation, and fibrosis were quantified. Results: Fifty-three targets associated with luteolin and 36 genes related to diabetic nephropathy were extracted. The AGE-RAGE signaling pathway was the key pathway impacted by luteolin in diabetic nephropathy. Key molecular targets include TGF-β, IL-1β, and PPARG. Luteolin reduced body weight and blood glucose levels, lowered the left kidney index, and improved insulin and glucose tolerance. Furthermore, luteolin mitigated inflammatory cell infiltration, basement membrane thickening, and collagen deposition in the kidney. Luteolin up-regulated the protein expression of p-AMPKα (Th172) while simultaneously down-regulated the protein expression of p-NF-ĸB (p65), NLRP3, TGF-β 1, α-SMA, and Collagen I. Conclusion: Luteolin mitigated renal fibrosis by alleviating energy metabolism disruptions and inflammation by modulating the AMPK/NLRP3/TGF-β signaling pathway.

(1) Background: Job burnout may affect the prognosis of patients with acute coronary syndrome (ACS) through mechanisms involving heart rate variability (HRV). However, no study has yet examined those potential associations. Hence, we conducted the present study to investigate this issue. (2) Method: Participants included patients who presented with a first episode of ACS and who were employed. The Copenhagen Burnout Inventory (CBI) was used to assess job burnout. Twenty-four-hour ambulatory electrocardiography recorded HRV on four occasions, i.e., during the hospitalization and follow-ups at one, six, and 12 months, respectively. (3) Results: A total of 120 participants who at least completed three Holter examinations throughout the study were enrolled in the final analysis. Job burnout scores at baseline were inversely associated with LnSDNN, LnTP, LnHF, LnLF, LnULF, and LnVLF during the consequent one-year follow-up. Each 1 SD increase in job burnout scores predicted a decline ranging from 0.10 to 0.47 in the parameters described above (all p < 0.05), and all relationships were independent of numerous confounders, including anxiety and depression. (4) Conclusion: High job burnout predicted reduced HRV parameters during the one-year period post-ACS in the working population.

Background: Due to the lack of evidence and inconsistency of sex differences in Heart failure (HF) in the Chinese population, this study aimed to compare sex differences in functional capacity and quality of life (QoL) between women and men after standard HF medications therapies, and analyze whether sex differences were associated with the composite endpoints of all-cause mortality or HF-related hospitalization and cardiac event-free survival rate in Chinese patients with HF. Methods: This was a 1-year longitudinal study. Participants included patients with HF from March 2017 to December 2018. At baseline and followed up at 1, 6, and 12 months later, functional capacity was assessed by 6-minute walk testing (6MWT), QoL was measured with the Kansas City Cardiomyopathy Questionnaire (KCCQ) and EuroQoL five dimensions (EQ-5D). The Cox proportional hazards model and Kaplan-Meier curves were used to determine sex differences in subsequent outcomes. The Cox proportional hazards model was used to identify the risk factors for composite endpoints. Kaplan-Meier curves were used to compare survival. Results: All patients were assigned to either men group (n = 94) or women group (n = 60). Longitudinal follow-ups showed a continuously increasing in 6MWT, Kansas City Cardiomyopathy Questionnaire overall score, EQ-5D visual analogue scale, and EQ-5D Index score in both groups (all P < 0.001); however, women reported a lower level of all parameters at the 1, 6, and 12 months follow-ups (all P < 0.05). In addition, women had a higher risk of all-cause mortality or HF-related hospitalization and a lower cardiac event-free survival rate than men (log-rank test, P = 0.027). Conclusion: Women reported worse functional capacity, QoL, and prognosis than men in a sample of Chinese patients with HF. Our findings highlight the importance of paying attention to sex differences in HF.

ShenGui capsule (SGC), as a herbal compound, has significant effects on the treatment of heart failure (HF), but its mechanism of action is unclear. In this study, we aimed to explore the potential pharmacological targets and mechanisms of SGC in the treatment of HF using network pharmacology and molecular docking approaches. Potential active ingredients of SGC were obtained from the traditional Chinese medicine systems pharmacology database and analysis platform database and screened by pharmacokinetic parameters. Target genes of HF were identified by comparing the toxicogenomics database, GeneCards, and DisGeNET databases. Protein interaction networks and gene-disorder-target networks were constructed using Cytoscape for visual analysis. Gene ontology and Kyoto Encyclopedia of Genes and Genomes were also performed to identify protein functional annotations and potential target signaling pathways through the DAVID database. CB-DOCK was used for molecular docking to explore the role of IL-1β with SGC compounds. Sixteen active ingredients in SGC were screened from the traditional Chinese medicine systems pharmacology database and analysis platform, of which 36 target genes intersected with HF target genes. Protein-protein interactions suggested that each target gene was closely related, and interleukin-1β (IL-1β) was identified as Hub gene. The network pharmacology analysis suggested that these active ingredients were well correlated with HF. Kyoto Encyclopedia of Genes and Genomes enrichment analysis suggested that target genes were highly enriched in pathways such as inflammation. Molecular docking results showed that IL-1β binds tightly to SGC active components. This experiment provides an important research basis for the mechanism of action of SGC in the treatment of HF. In this study, the active compounds of SGC were found to bind IL-1β for the treatment of heart failure.