Background: Machine learning (ML) can identify and integrate connections among data and has the potential to predict events. Heart failure is primarily caused by cardiomyopathy, and different etiologies require different treatments. The present study examined the diagnostic value of a ML algorithm that combines echocardiographic data to automatically differentiate ischemic cardiomyopathy (ICM) from dilated cardiomyopathy (DCM). Methods: We retrospectively collected the echocardiographic data of 200 DCM patients and 199 ICM patients treated in the First Affiliated Hospital of Guangxi Medical University between July 2016 and March 2022. All patients underwent invasive coronary angiography for diagnosis of ICM or DCM. The data were randomly divided into a training set and a test set via 10-fold cross-validation. Four ML algorithms (random forest, logistic regression, neural network, and XGBoost [ML algorithm under gradient boosting framework]) were used to generate a training model for the optimal subset, and the parameters were optimized. Finally, model performance was independently evaluated on the test set, and external validation was performed on 79 patients from another center. Results: Compared with the logistic regression model (area under the curve [AUC] = 0.925), neural network model (AUC = 0.893), and random forest model (AUC = 0.900), the XGBoost model had the best identification rate, with an average sensitivity of 72% and average specificity of 78%. The average accuracy was 75%, and the AUC of the optimal subset was 0.934. External validation produced an AUC of 0.804, accuracy of 78%, sensitivity of 64% and specificity of 93%. Conclusions: We demonstrate that utilizing advanced ML algorithms can help to differentiate ICM from DCM and provide appreciable precision for etiological diagnosis and individualized treatment of heart failure patients.

The aim of the present study was to investigate the effects of microRNA (miR)-128 inhibition on the targeted activation of peroxisome proliferator-activated receptor gamma (PPARG) and on cardiomyocyte apoptosis induced by myocardial ischemia/reperfusion (I/R) injury. In vitro, the expression of PPARG was detected by reverse transcription-quantitative polymerase chain reaction and western blotting in neonatal rat ventricular myocytes (NRVMs) and HEK293 cells transfected with the mimics or inhibitors of miR‑128 or control RNA. Luciferase reporter assays were used to identify whether PPARG is a direct target of miR‑128. In vivo, miR‑128 was knocked down via ear vein injection of antagomir‑128 in a rabbit myocardial I/R injury model. Western blotting investigated the activation of Akt [phosphorylated (p)‑Akt] and the expression of total‑Akt, PPARG and myeloid leukemia cell differentiation protein‑1 (Mcl‑1) in the myocardium. Cardiomyocyte apoptosis was examined with transmission electron microscropy and terminal deoxynucleotidyl transferase dUTP nick end labeling staining. PPARG mRNA and protein were downregulated in NRVMs transfected with miR‑128 mimics, but upregulated by antagomir‑128 compared with control. This indicates that PPARG is a direct miR‑128 target. Activation of Akt (p‑Akt), Mcl‑1 and PPARG expression in the myocardium were increased by miR‑128 inhibition. Furthermore, miR‑128 antagomirs significantly reduced apoptosis in hearts subjected to I/R injury, which was blocked by the PPARG inhibitor GW9662. In conclusion, miR‑128 inhibition attenuated I/R injury‑induced cardiomyocyte apoptosis by the targeted activation of PPARG signaling.

Background: The machine learning algorithm (MLA) was implemented to establish an optimal model to predict the no reflow (NR) process and in-hospital death that occurred in ST-elevation myocardial infarction (STEMI) patients who underwent primary percutaneous coronary intervention (pPCI). Methods: The data were obtained retrospectively from 854 STEMI patients who underwent pPCI. MLA was applied to predict the potential NR phenomenon and confirm the in-hospital mortality. A random sampling method was used to split the data into the training (66.7%) and testing (33.3%) sets. The final results were an average of 10 repeated procedures. The area under the curve (AUC) and the associated 95% confidence intervals (CIs) of the receiver operator characteristic were measured. Results: A random forest algorithm (RAN) had optimal discrimination for the NR phenomenon with an AUC of 0.7891 (95% CI: 0.7093–0.8688) compared with 0.6437 (95% CI: 0.5506–0.7368) for the decision tree (CTREE), 0.7488 (95% CI: 0.6613–0.8363) for the support vector machine (SVM), and 0.681 (95% CI: 0.5767–0.7854) for the neural network algorithm (NNET). The optimal RAN AUC for in-hospital mortality was 0.9273 (95% CI: 0.8819–0.9728), for SVM, 0.8935 (95% CI: 0.826–0.9611); NNET, 0.7756 (95% CI: 0.6559–0.8952); and CTREE, 0.7885 (95% CI: 0.6738–0.9033). Conclusions: The MLA had a relatively higher performance when evaluating the NR risk and in-hospital mortality in patients with STEMI who underwent pPCI and could be utilized in clinical decision making.

Background: We investigated the potential of telmisartan to improve microvascular dysfunction induced by myocardial ischemia/reperfusion (I/R) injury by activating the peroxisome proliferator-activated receptor gamma (PPARG) pathway. Methods: Forty-eight male rabbits were randomly allocated into sham-operated, I/R, GW9662, telmisartan, telmisartan–GW9662, or candesartan groups. Rabbits were anesthetized, and the left anterior descending coronary artery (LAD) was ligated for 60 minutes. Following reperfusion for 6 hours, angiotensin II content of the heart was determined using radioimmunoassay. Myocardial neutrophil accumulation and microvessel cross-sectional area were examined histologically. Myocardial capillaries were examined with transmission electron microscopy. Intercellular adhesion molecule-1 (ICAM-1) and vascular cell adhesion molecule-1 (VCAM-1) in the myocardium were measured using enzyme-linked immunosorbent assay. Western blot was utilized for investigating the expression of nuclear factor kappa-light-chain-enhancer of activated B cells (NF- κ B) and PPARG. Results: Angiotensin II concentration was significantly increased in all treatment groups compared with the sham-operated group (P < 0.05, all). Accumulation of polymorphonuclear neutrophils was significantly lower, while microvessel cross-sectional area was significantly higher in the telmisartan, telmisartan-GW9662, and candesartan groups compared with the I/R group (P < 0.05). ICAM-1 and VCAM-1 levels were also significantly lower, and correlated with lower NF- κ B expression in these groups. The effects were the most significant in the telmisartan group compared with the telmisartan–GW9662 and candesartan groups. Telmisartan significantly increased PPARG protein expression compared with all other groups (P < 0.05, all). Conclusions: Except for the typical effects of angiotensin II-receptor blocker, telmisartan improved microvascular dysfunction during myocardial I/R injury via the PPARG pathway.

Purpose: miR-190a-5p expression alters dynamically in response to hypoxia. However, the role of miR-190a-5p expression in hypoxia-induced pulmonary hypertension (PH) remains unclear. We sought to correlate the miR-190a-5p expression levels with the severity, diagnosis, and prognosis of PH in relation to chronic obstructive pulmonary disease (COPD-PH). Additionally, we evaluated the effect of miR-190a-5p through in vitro experiments on human pulmonary endothelial cells (HPECs) that were exposed to hypoxia and in vivo experiments using an animal model of hypoxia-induced PH. Methods: Circulating miR-190a-5p levels were measured from 73 patients with PH and 32 healthy controls through quantitative real-time PCR. The levels of miR-190a-5p and the expression of Krüppel-like factor 15 (KLF15) were analyzed in HPECs that were exposed to hypoxia, and the effects of antagomir-190a-5p in mice with chronic hypoxia-induced PH were tested. Target gene analysis was performed by Western blot and luciferase assay. Results: The miR-190a-5p level was significantly higher in patients with COPD-PH than in the healthy controls. Higher miR-190a-5p levels were associated with a greater severity of COPD-PH. In vitro experiments on HPECs showed that exposure to hypoxia increased the miR-190a-5p levels significantly. KLF15 was validated as a target of miR-190a-5p. Transfection with miR-190a-5p mimicked inhibition of KLF15 expression in HPECs. In the mouse model of PH, antagomir-190a-5p reduced right ventricular systolic pressure and enhanced the KLF15 expression levels in lung tissue. Conclusion: miR-190a-5p regulates hypoxia-induced PH by targeting KLF15. The circulating levels of miR-190a-5p correlate with the severity of COPD-PH, thereby confirming the diagnostic and prognostic value of this parameter in COPD-PH.

Activating transcription factor 3 (ATF3) has been confirmed to be responsive to oxidative stress and to negatively regulate the activity of Toll-like receptor 4 (TLR4). However, the effect of ATF3 on cardiac microvascular ischemia/reperfusion (I/R) injury remains unknown. The GEO2R online tool was employed to obtain differentially expressed genes GSE4105 and GSE122020, in two rat I/R injury microarray datasets. We established a rat myocardial I/R model in vivo, and also generated an in vitro hypoxia/reoxygenation (H/R) model of cardiomyoblast H9c2 cells. Overexpression of ATF3 was achieved by adenoviral-mediated gene transfer (Ad-ATF3). Rats were randomly divided into four groups: sham, I/R, I/R + Ad-Lacz (as a control), and I/R + Ad-ATF3. ELISA, CCK-8, DCFH-DA probe, qRT-PCR and Western blotting were used to determine the expression of ATF3, oxidative indices, cellular injury and TLR4/NF-κB pathway-associated proteins. Transmission electron microscopy, immunohistochemistry and immunofluorescence were used to detect the leukocyte infiltration and the alteration of microvascular morphology and function in vivo. Echocardiographic and hemodynamic data were also obtained. Bioinformatics analysis revealed that ATF3 was upregulated in I/R myocardia in two independent rat myocardial I/R models. Cardiac microvascular I/R injury included leukocyte infiltration, microvascular integrity disruption, and microvascular perfusion defect, which eventually resulted in the deterioration of hemodynamic parameters and heart function. Ad-ATF3 significantly restored microvascular function, increased cardiac microvascular perfusion, and improved hemodynamic parameters and heart function. Mechanistically, Ad-ATF3 ameliorated oxidative stress, inhibited TLR4/NF-κB pathway activation and down-regulated the expression of downstream proinflammatory cytokines in I/R myocardium in vivo and in H/R H9c2 cells in vitro. ATF3 overexpression protects against cardiac microvascular I/R injury in part by inhibiting the TLR4/NF-κB pathway and oxidative stress.