Pulmonary hypertension (PH) is a chronic and life-threatening disease characterized by pulmonary vascular remodeling (PVR), which involves the abnormal proliferation of pulmonary artery smooth muscle cells (PASMCs). These cells exhibit metabolic characteristics akin to cancer cells, particularly in their shift toward glycolysis. The Lon protease 1 (LONP1) has been shown to promote glycolytic reprogramming of tumor cells, conferring a malignant proliferative phenotype. However, the precise role of LONP1 in PH remains unclear. In the present study, Su5416/hypoxia-induced and monocrotaline (MCT)-induced PH rodent models and platelet-derived growth factor BB (PDGF-BB)-induced PASMCs were used to investigate the role and mechanism of LONP1 in PH. The results revealed an up-regulation of LONP1 expression in lung tissues from two PH rodent models, as well as in PDGF-BB-induced PASMCs. In vivo knockdown of LONP1 significantly alleviated PASMC mitochondrial dysfunction, reduced glycolytic enzyme expression, and decreased lactate accumulation, thereby mitigating PVR. Additionally, in vitro experiments demonstrated that knockdown or inhibition of LONP1 attenuated glycolytic reprogramming, proliferation, and migration of PASMCs, whereas overexpression of LONP1 had converse effects. Mechanistic studies confirmed that mitochondrial pyruvate carrier 1 (MPC1) was a direct substrate for LONP1-mediated degradation. Functional experiments with MPC1 knockdown and overexpression further elucidated its role in the proliferation and migration of PASMCs. Rescue experiments indicated that MPC1 knockdown abrogated the suppressive effects of LONP1 knockdown on glycolytic reprogramming, proliferation, and migration in PASMCs. Therapeutically, knockdown or pharmacological inhibition of LONP1 significantly reversed MCT-induced PH in rats. Thus, targeting LONP1 may represent a promising therapeutic strategy for PH.

Acute kidney injury (AKI) is a common and serious complication in patients with acute myocardial infarction (AMI) and diabetes mellitus (DM), often leading to poor outcomes. Timely and accurate risk stratification of AKI severity is essential for early intervention and improved prognosis. This study aimed to develop and externally validate machine learning (ML) models for early risk stratification of AKI severity in AMI patients with DM. In this multicenter retrospective study, data were collected from the MIMIC-III/IV, eICU-CRD, and Zhongda Hospital databases. Feature selection was performed via Boruta and LASSO algorithms. A total of 30 predictive models were built using 10 ML algorithms. Model performance was assessed via metrics of discrimination, calibration, and clinical utility. The top-performing models were interpreted using SHapley Additive exPlanations (SHAP) and deployed as an interactive web application. Among the 4,908 AMI patients with DM, 1,930 (39.3%) developed AKI. The LightGBM model achieved the highest area under the curve (AUC) in predicting stage I or higher AKI (AUC = 0.851, 95% CI: 0.822–0.879) and stage II or higher AKI (AUC = 0.874, 95% CI: 0.849–0.897) in the external Zhongda Hospital cohort. For stage III AKI, the XGBoost model performed best, with an AUC of 0.875 (95% CI: 0.846–0.901). We developed and validated ML models for early risk stratification of AKI severity in AMI patients with DM. These models demonstrated robust performance and clinical utility and were integrated into a user-friendly web tool to facilitate individualized risk stratification and early intervention, potentially improving clinical outcomes.