Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ran Xin has a total of 85 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CaLiNet-E: Reconstructing 12-lead ECG from three leads with brief patient-specific calibration

    by Xinyu Zhang, Ran Xin, Hailing Cai, Junjie Yang, Yundai Chen, Huilong Duan, Xudong Lu

    Background and Objective: Brief paired 12-lead calibration may supply patient-specific information unavailable to population models for missing-lead reconstruction. We quantified its contribution relative to nonlinear architecture and tested transfer across recordings from the same patient.,Methods: From I, II and V2, we reconstructed V1 and V3-V6. We compared a population linear mapping (GL), a patient-calibrated linear mapping (PCM), four uncalibrated neural architectures, and CaLiNet-E, which combines a quality-gated patient-calibrated anchor with a FiLM-conditioned residual U-Net. Evaluation used patient-disjoint PTB-XL development and locked test folds plus CPSC2018 and CODE-test. Cross-record transfer used 189 patients with multiple PTB-XL recordings.,Results: On development, calibration increased Eq. (6) by 0.155 within linear models (GL 0.441; PCM 0.596) and by 0.167 within matched nonlinear models (forced rho=0 0.513; CaLiNet-E 0.680); corresponding nonlinear contributions were 0.072 and 0.084. On locked fold 10, CaLiNet-E achieved PCC 0.969 and nRMSE 0.213 versus 0.944 and 0.295 for PCM; diagnostic macro F1 was 0.664 versus 0.675 for the original signal. CPSC2018 agreed; on CODE-test, PCM had higher PCC but CaLiNet-E lower nRMSE. Cross-record coefficients without shrinkage did not improve on GL (-0.001; 95% CI -0.019 to 0.018) but exceeded mismatched-patient coefficients by 0.124 (0.105 to 0.144). Half-weight shrinkage toward GL recovered 0.033 (0.015 to 0.051), while cross-record CaLiNet-E exceeded its matched forced-rho=0 control by 0.064 (0.044 to 0.090). On a common GL reference, it retained 21.4% (16.8% to 26.1%) of fresh-calibration gain. Same-patient coefficient pairs were closer than different-patient pairs in 81.5% of comparisons; nearest-neighbour identification was 18.5% versus 0.53% chance.,Conclusions: Calibration contributed more than the architectural differences examined. The coefficients carry a detectable patient-specific ECG signature, but most within-record benefit is recording-specific. Shrinkage improves transfer; recalibration remains preferable after measurement-geometry changes.

  • Open Access

    Development and Validation of a Coronary Computed Tomography Angiography‐Based Radiomics‐Integrated Model for Noninvasive Detection of Left Atrial Appendage Thrombus in Atrial Fibrillation

    by Ran Xin, Guanhua Dou, Yipu Ding, Mingrui Ma, Shuo Wang, Zinuan Liu, Xi Wang, Dongkai Shan, Yang Mu, Jing Jing, et al.

    Background: Timely detection of left atrial appendage thrombus (LAAT) is critical for stroke prevention in atrial fibrillation. Current diagnostic approaches such as traditional models and physician visual analysis face challenges in comprehensive capturing image information. The study aimed to develop and validate a multimodal model integrating coronary computed tomography angiography‐based radiomics features with clinical parameters for noninvasive LAAT detection in patients with atrial fibrillation. Methods: The diagnostic study retrospectively enrolled 670 patients with nonvalvular atrial fibrillation undergoing coronary computed tomography angiography and transesophageal echocardiography from May 2015 to May 2023 and stratified into training and internal validation sets. An independent prospective cohort (n=114) from May 2023 to May 2025 served for external validation. Semiautomated LAA segmentation extracted 1231 radiomics features, with 25 features selected by random forest. A multimodal LAAT detection model was developed and evaluated using receiver operating characteristic, calibration curve, and decision curve analysis and compared against traditional models and physician visual analysis. Results: The Radiomics‐LAAT model achieved significantly superior discrimination in both internal validation (area under the curve, 0.963 [95% CI, 0.945–0.980], accuracy: 0.929) and external validation (areas under the curve, 0.920 [95% CI, 0.886–0.953], accuracy: 0.807), outperforming traditional models and physician visual analysis, with optimal calibration (Brier score: 0.067) and clinical net benefit. The Radiomics‐LAAT model achieved high sensitivity (0.953), specificity (0.905), negative predictive value (0.950), and positive predictive value (0.910). Conclusions: The Radiomics‐LAAT model significantly enhances noninvasive LAAT detection performance compared with traditional models and physician visual analysis, demonstrating its potential for stroke risk stratification in patients with atrial fibrillation.

  • Open Access

    Revisiting Globalized CAD Risk Assessment in the Era of Artificial Intelligence

    by Junjie Yang, Ran Xin

  • Open Access

    Narciclasine Alleviates Endothelial Inflammation and Atherosclerosis Initiation by Inhibiting Histone Lactylation-Mediated NF-κB Activation

    by Ziqian Wang, Zhengbin Zhang, Ran Xin, Mingrui Ma, Zeyu Sun, Zhongxuan Li, Chen Zhang, Liangliang Liu, Zhengfeng Wu, Yingqian Zhang, et al.

    Glycolysis-derived lactate serves as a substrate for lysine lactylation, an epigenetic modification playing critical transcriptional regulatory roles in inflammatory diseases. Endothelial inflammation, characterized by upregulated glycolysis, initiates atherosclerosis, yet the contribution of histone lactylation remains undefined. Although narciclasine exhibits anti-inflammatory and antioxidant properties, its impact on endothelial inflammation in atherosclerosis is unknown. Connectivity Map (CMap) analysis predicted narciclasine as an inhibitor of oscillatory shear stress and TNF-α-induced endothelial inflammation. In vitro, treatment of human umbilical vein endothelial cells (HUVECs) with 20 nM narciclasine significantly suppressed ox-LDL-induced expression of VCAM1, ICAM1, SELE, and CCL2, reduced reactive oxygen species (ROS) production, and inhibited monocyte adhesion and migration. In vivo, administration of narciclasine (0.02 mg/kg) attenuated carotid artery endothelial inflammation and macrophage infiltration, consequently reducing early atherogenesis in partial carotid ligation model in ApoE−/− mice. Mechanistically, ox-LDL upregulated GLUT1 and PFKFB3 expression, enhancing endothelial glycolysis and lactate production. Increased lactate accumulation promoted histone H3 lysine 18 lactylation (H3K18la). Both pharmacological (2-DG, DCA) suppression of lactate production or genetic (LDHA, P300 silencing) suppression reduced H3K18la levels and inhibited ox-LDL-induced endothelial inflammation. Reanalysis of public CUT&Tag data (GEO: GSE267661) and chromatin immunoprecipitation (ChIP) validation revealed ox-LDL-induced enrichment of H3K18la at key promoters of NF-κB pathway genes (TRAF2, TRAF6, RIP1, cIAP1, RELA). Narciclasine treatment suppressed GLUT1 and PFKFB3 expression, thereby reducing H3K18la enrichment and inhibiting NF-κB pathway activation. Our findings provide novel insights into the functional role of lactylation-mediated epigenetic regulation in glycolysis-driven endothelial inflammation. Collectively, this study identifies narciclasine as a potential therapeutic candidate, which mitigates endothelial inflammation and early atherosclerosis by targeting a glycolysis-H3K18la network linked to NF-κB activation.


  • Incremental Prognostic Value of Perivascular Fat Attenuation Index in Patients with Diabetes with Coronary Artery Disease

    by Yipu Ding, Dongkai Shan, Tianwen Han, Zinuan Liu, Xi Wang, Guanhua Dou, Ran Xin, Ziqiang Guo, Guanxi Chen, Jing Jing, et al.

    The addition of pericoronary adipose tissue attenuation to conventional and advanced coronary CT angiography findings improved the prediction of major adverse cardiovascular and cerebrovascular events in individuals with diabetes mellitus.


  • Open Access

    Young Patients With Colorectal Cancer Have Higher Early Mortality but Better Long-Term Survival

    by Shuyuan Wang, Zhen Yuan, Kemin Ni, Yixiang Zhan, Xuanzhu Zhao, Zhaoce Liu, Yanfei Liu, Ben Yi, Sizhen Lai, Xin Yin, et al.

    INTRODUCTION: To define the prognosis of colorectal cancer (CRC) in young patients and to compare their postoperative treatment with that of older patients. METHODS: This multicenter study enrolled 5,457 patients with primary CRC who underwent surgical resection. The overall survival (OS), clinicopathologic characteristics, and postoperative treatment of 253 young patients aged 18–44 years and 5,204 older patients aged 44–80 years were analyzed. RESULTS: The OS rate was 77.1% for young and 74.2% for older patients (P = 0.348). Landmark analysis showed a significant difference in survival between young and older patients, with 63.8% of deaths among young patients being within 25 months of surgery compared with 42.4% among older patients (P = 0.002). Among those who survived more than 25 months, young patients had significantly better survival than older patients (P = 0.009). Multivariable analysis of young patients revealed that the tumor location, perineural invasion, and stage were associated with poor survival within 25 months; after this period, stage was the only prognostic marker. Young patients were more likely to receive chemotherapy, particularly multiagent regimens. For young patients, no significant difference in OS was found based on the chemotherapy regimen, regardless of disease stage (II, III, or IV, all P > 0.05). In addition, unlike in older patients, no difference in OS was found in young patients regardless of the drug regimen administered (all P > 0.05). DISCUSSION: Young-onset CRC may have a unique disease biology that warrants further research and therapy development.


  • Open Access

    Circulating Methylated SEPT9 DNA Analyses to Predict Recurrence Risk and Adjuvant Chemotherapy Benefit in Stage II to III Colorectal Cancer

    by Zhen Yuan, Shuyuan Wang, Kemin Ni, Yixiang Zhan, Hong Ma, Xinyu Liu, Ran Xin, Xingyu Zhou, Zhaoce Liu, Xuanzhu Zhao, et al.

    We aimed to evaluate the ability of circulating cell-free methylated SETP9 DNA (mSEPT9) to identify recurrence and to determine its clinical utility in adjuvant chemotherapy (ACT) regimen decisions. This study enrolled 426 patients with stage II–III CRC who received radical resection between January 8, 2018, and November 30, 2020. The median follow-up duration was 15.8 months (range, 8.1–43.4 months). The primary endpoint was recurrence-free survival (RFS). A propensity score matching model was used to minimize potential confounding covariates and to confirm our findings. In stage II–III CRC patients, postoperative (within 1 month after surgery) mSEPT9 positivity was significantly correlated with worse RFS (HR=6.21, P<0.001), and it remained the strongest independent predictor in multivariate Cox regression analysis (HR=5.83, P<0.001), which was significantly superior to CEA, CA19-9, and CA242. During disease surveillance, mSEPT9 positivity preceded radiographic recurrence by a median of 5.0 months. The postoperative mSEPT9-positive patients benefited more from CAPEOX compared to FOLFOX (HR=3.97, P=0.017), while for mSEPT9-negative patients, CAPEOX and FOLFOX resulted in similar RFS (HR=1.70, P=0.322). Furthermore, 3 months of CAPEOX was more effective than 3 and 6 months of FOLFOX (HR=4.40, P=0.065; HR=1.56, P=0.073, respectively). Our results revealed that mSEPT9 detection after radical resection could identify minimal residual disease (MRD) and could predict a high risk of recurrence in patients with stage II–III CRC. Furthermore, we show pioneering work that mSEPT9 detection could be used to guide the selection of an adjuvant chemotherapy regimen to improve RFS.


  • Open Access

    Incremental Value of Noncontrast Chest Computed Tomography-derived Parameters in Predicting Subclinical Carotid Atherosclerosis

    by Xi Wang, Ran Mm Xin, Dongkai Shan, Guanhua Mm Dou, Wei Zhang, Jing Mm Jing, Bai Mbbs He, Yundai Chen, Junjie Yang

    Purpose: To investigate the incremental value of noncontrast chest computed tomography (CT)-derived parameters, such as coronary artery calcium score (CACS) and epicardial adipose tissue volume (EATv), in predicting subclinical carotid atherosclerosis above traditional risk factors in community-based asymptomatic populations of northern China. Materials and Methods: A total of 2195 community-based asymptomatic individuals were enrolled from Jidong Oilfield in accordance with the PERSUADE study. CACS and EATv were measured on noncontrast chest CT. Demographics and ideal cardiovascular health score (ICHS) were collected through questionnaires. We recalculated the ideal cardiovascular health risk score (ICHRS) (ICHRS=14−ICHS) and standardized the parameters as log-CACS and body mass index adjusted EATv (i-EATv). Subclinical carotid atherosclerosis was assessed by Doppler sonography and defined as any prevalence of average carotid intima-media thickness ≥1.00 mm, appearance of carotid plaque, and carotid arterial stenosis in the areas of extracranial carotid arteries on both sides. Results: A total of 451 (20.55%) individuals presented subclinical carotid atherosclerosis. CACS and EATv were significantly greater in the subclinical group, while ICHS was lower. In multivariate logistic regression, ICHRS (odds ratio [OR]=1.143, 95% confidence interval [CI]: 1.080-1.210, PPPPP<0.0001). Conclusion: Noncontrast chest CT-derived parameters, including CACS and EATv, could provide significant incremental improvement for predicting subclinical carotid atherosclerosis beyond the conventional risk assessment model based on ICHRS.


  • Open Access

    Machine Learning Model-Based Simple Clinical Information to Predict Decreased Left Atrial Appendage Flow Velocity

    by Chao Li, Guanhua Dou, Yipu Ding, Ran Xin, Jing Wang, Jun Guo, Yundai Chen, Junjie Yang

    Background: Transesophageal echocardiography (TEE) is the first technique of choice for evaluating the left atrial appendage flow velocity (LAAV) in clinical practice, which may cause some complications. Therefore, clinicians require a simple applicable method to screen patients with decreased LAAV. Therefore, we investigated the feasibility and accuracy of a machine learning (ML) model to predict LAAV. Method: The analysis included patients with atrial fibrillation who visited the general hospital of PLA and underwent transesophageal echocardiography (TEE) between January 2017 and December 2020. Three machine learning algorithms were used to predict LAAV. The area under the receiver operating characteristic curve (AUC) was measured to evaluate diagnostic accuracy. Results: Of the 1039 subjects, 125 patients (12%) were determined as having decreased LAAV (LAAV < 25 cm/s). Patients with decreased LAAV were fatter and showed a higher prevalence of persistent AF, heart failure, hypertension, diabetes and stroke, and the decreased LAAV group had a larger left atrium diameter and a higher serum level of NT-pro BNP than the control group (p < 0.05). Three machine-learning models (SVM model, RF model, and KNN model) were developed to predict LAAV. In the test data, the RF model performs best (R = 0.608, AUC = 0.89) among the three models. A fivefold cross-validation scheme further verified the predictive ability of the RF model. In the RF model, NT-proBNP was the factor with the strongest impact. Conclusions: A machine learning model (Random Forest model)-based simple clinical information showed good performance in predicting LAAV. The tool for the screening of decreased LAAV patients may be very helpful in the risk classification of patients with a high risk of LAA thrombosis.