Background::Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.Methods::This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Na?ve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.Results::The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. Conclusions::Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Objective To assess the predictive value of computed tomography pulmonary angiography(CTPA)cardiovascular parame-ters for chronic thromboembolic pulmonary hypertension(CTEPH)under the 2022 European Society of Cardiology/European Respiratory Society(ESC/ERS)guidelines,and to compare with the 2021 Chinese guidelines.Methods A total of 201 suspected CTEPH patients were retrospectively selected.All patients underwent right heart catheterization(RHC)and CTPA evaluation.According to the Euro-pean guidelines,they were divided into three groups:mean pulmonary artery pressure(mPAP)≤20 mmHg control group(63 cases)(1 mmHg=0.133 kPa),mPAP＞20 mmHg CTEPH group(138 cases),and mPAP≥25 mmHg CTEPH group(123 cases).Inter-group comparison of CTPA cardiovascular parameters was performed,and receiver operating characteristic(ROC)curve analysis was performed for each parameter.Results Under the 2022 European guidelines,the diagnostic efficacy of the diameter of the main pulmonary artery trunk(MPAd)was the highest[area under the curne(AUC)was 0.933].The binary logistic regression analysis revealed that the MP Ad,right ventricular free wall thickness(RVWT),and interventricular septal angle(IVSA)were inde-pendent risk factors for the diagnosis of CTEPH(P＜0.05).Under both the Chinese and European guidelines,the MPAd,the transverse diameter and area of the right atrium,the transverse diameter and area of the bi-ventricle,the RVWT,and the IVSA showed significant statistical differences in CTEPH and control groups(P＜0.05).Conclusion Under both the Chinese and European guidelines,the MP Ad measured by CTPA has the highest diagnostic efficacy for CTEPH,while the IVSA has the strongest correlation with clinical prognostic indicators.The right atrium structure also has evaluation value.

Objective:To explore the clinical characteristics and establish a corresponding prognostic scoring model in patients with early-stage clinical features of hepatitis B-induced acute-on-chronic liver failure (HBV-ACLF).Methods:Clinical characteristics of 725 cases with hepatitis B-related acute-on-chronic hepatic dysfunction (HBV-ACHD) were retrospectively analyzed using Chinese group on the study of severe hepatitis B (COSSH). The independent risk factors associated with 90-day prognosis to establish a prognostic scoring model was analyzed by multivariate Cox regression, and was validated by 500 internal and 390 external HBV-ACHD patients.Results:Among 725 cases with HBV-ACHD, 76.8% were male, 96.8% had cirrhosis base,66.5% had complications of ascites, 4.1% had coagulation failure in respect to organ failure, and 9.2% had 90-day mortality rate. Multivariate Cox regression analysis showed that TBil, WBC and ALP were the best predictors of 90-day mortality rate in HBV-ACHD patients. The established scoring model was COSS-HACHADs = 0.75 × ln(WBC) + 0.57 × ln(TBil)-0.94 × ln(ALP) +10. The area under the receiver operating characteristic curve (AUROC) of subjects was significantly higher than MELD, MELD-Na, CTP and CLIF-C ADs( P < 0.05). An analysis of 500 and 390 cases of internal random selection group and external group had similar verified results. Conclusion:HBV-ACHD patients are a group of people with decompensated cirrhosis combined with small number of organ failure, and the 90-day mortality rate is 9.2%. COSSH-ACHDs have a higher predictive effect on HBV-ACHD patients' 90-day prognosis, and thus provide evidence-based medicine for early clinical diagnosis and treatment.

Nowadays potential preclinical drugs for the treatment of nonalcoholic steatohepatitis (NASH) have failed to achieve expected therapeutic efficacy because the pathogenic mechanisms are underestimated. Inactive rhomboid protein 2 (IRHOM2), a promising target for treatment of inflammation-related diseases, contributes to deregulated hepatocyte metabolism-associated nonalcoholic steatohepatitis (NASH) progression. However, the molecular mechanism underlying Irhom2 regulation is still not completely understood. In this work, we identify the ubiquitin-specific protease 13 (USP13) as a critical and novel endogenous blocker of IRHOM2, and we also indicate that USP13 is an IRHOM2-interacting protein that catalyzes deubiquitination of Irhom2 in hepatocytes. Hepatocyte-specific loss of the Usp13 disrupts liver metabolic homeostasis, followed by glycometabolic disorder, lipid deposition, increased inflammation, and markedly promotes NASH development. Conversely, transgenic mice with Usp13 overexpression, lentivirus (LV)- or adeno-associated virus (AAV)-driven Usp13 gene therapeutics mitigates NASH in 3 models of rodent. Mechanistically, in response to metabolic stresses, USP13 directly interacts with IRHOM2 and removes its K63-linked ubiquitination induced by ubiquitin-conjugating enzyme E2N (UBC13), a ubiquitin E2 conjugating enzyme, and thus prevents its activation of downstream cascade pathway. USP13 is a potential treatment target for NASH therapy by targeting the Irhom2 signaling pathway.