Multimodal data integration using machine learning to predict the risk of clear cell renal cancer metastasis: a retrospective multicentre study.

PURPOSE: To develop and validate a predictive combined model for metastasis in patients with clear cell renal cell carcinoma (ccRCC) by integrating multimodal data. MATERIALS AND METHODS: In this retrospective study, the clinical and imaging data (CT and ultrasound) of patients with ccRCC confirmed by pathology from three tertiary hospitals in different regions were collected from January 2013 to January 2023. We developed three models, including a clinical model, a radiomics model, and a combined model. The performance of the model was determined based on its discriminative power and clinical utility. The evaluation indicators included area under the receiver operating characteristic curve (AUC) value, accuracy, sensitivity, specificity, negative predictive value, positive predictive value and decision curve analysis (DCA) curve. RESULTS: A total of 251 patients were evaluated. Patients (n = 166) from Shandong University Qilu Hospital (Jinan) were divided into the training cohort, of which 50 patients developed metastases; patients (n = 37) from Shandong University Qilu Hospital (Qingdao) were used as internal testing, of which 15 patients developed metastases; patients (n = 48) from Changzhou Second People's Hospital were used as external testing, of which 13 patients developed metastases. In the training set, the combined model showed the highest performance (AUC, 0.924) in predicting lymph node metastasis (LNM), while the clinical and radiomics models both had AUCs of 0.845 and 0.870, respectively. In the internal testing, the combined model had the highest performance (AUC, 0.877) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.726 and 0.836, respectively. In the external testing, the combined model had the highest performance (AUC, 0.849) for predicting LNM, while the AUCs of the clinical and radiomics models were 0.708 and 0.804, respectively. The DCA curve showed that the combined model had a significant prediction probability in predicting the risk of LNM in ccRCC patients compared with the clinical model or the radiomics model. CONCLUSION: The combined model was superior to the clinical and radiomics models in predicting LNM in ccRCC patients.

Predictive value of bilirubin and serum γ-glutamyltranspeptidase levels in type-2 diabetes mellitus patients with acute coronary syndrome.

BACKGROUND: Cardiovascular disease is a major complication of diabetes mellitus (DM). Type-2 DM (T2DM) is associated with an increased risk of cardiovascular events and mortality, while serum biomarkers may facilitate the prediction of these outcomes. Early differential diagnosis of T2DM complicated with acute coronary syndrome (ACS) plays an important role in controlling disease progression and improving safety. AIM: To investigate the correlation of serum bilirubin and γ-glutamyltranspeptidase (γ-GGT) with major adverse cardiovascular events (MACEs) in T2DM patients with ACS. METHODS: The clinical data of inpatients from January 2022 to December 2022 were analyzed retrospectively. According to different conditions, they were divided into the T2DM complicated with ACS group (T2DM + ACS, n = 96), simple T2DM group (T2DM, n = 85), and simple ACS group (ACS, n = 90). The clinical data and laboratory indices were compared among the three groups, and the correlations of serum total bilirubin (TBIL) levels and serum γ-GGT levels with other indices were discussed. T2DM + ACS patients received a 90-day follow-up after discharge and were divided into event (n = 15) and nonevent (n = 81) groups according to the occurrence of MACEs; Univariate and multivariate analyses were further used to screen the independent influencing factors of MACEs in patients. RESULTS: The T2DM + ACS group showed higher γ-GGT, total cholesterol, low-density lipoprotein cholesterol (LDL-C) and glycosylated hemoglobin (HbA1c) and lower TBIL and high-density lipoprotein cholesterol levels than the T2DM and ACS groups (P < 0.05). Based on univariate analysis, the event and nonevent groups were significantly different in age (t = 3.3612, P = 0.0011), TBIL level (t = 3.0742, P = 0.0028), γ-GGT level (t = 2.6887, P = 0.0085), LDL-C level (t = 2.0816, P = 0.0401), HbA1c level (t = 2.7862, P = 0.0065) and left ventricular ejection fraction (LEVF) levels (t=3.2047, P = 0.0018). Multivariate logistic regression analysis further identified that TBIL level and LEVF level were protective factor for MACEs, and age and γ-GGT level were risk factors (P < 0.05). CONCLUSION: Serum TBIL levels are decreased and γ-GGT levels are increased in T2DM + ACS patients, and the two indices are significantly negatively correlated. TBIL and γ-GGT are independent influencing factors for MACEs in such patients.

What we talk about when we talk about spinal cord aging.

Spinal cord-associated disorders are common in the elderly population; however, the mechanisms underlying spinal aging remain elusive. In a recent Nature paper, Sun et al. systemically analyzed aged spines in nonhuman primates and identified a new cluster of CHIT1-positive microglia that drives motor neuron senescence and subsequent spine aging.

Endothelial H2S-AMPK dysfunction upregulates the angiocrine factor PAI-1 and contributes to lung fibrosis.

Dysfunction of the vascular angiocrine system is critically involved in regenerative defects and fibrosis of injured organs. Previous studies have identified various angiocrine factors and found that risk factors such as aging and metabolic disorders can disturb the vascular angiocrine system in fibrotic organs. One existing key gap is what sense the fibrotic risk to modulate the vascular angiocrine system in organ fibrosis. Here, using human and mouse data, we discovered that the metabolic pathway hydrogen sulfide (H2S)-AMP-activated protein kinase (AMPK) is a sensor of fibrotic stress and serves as a key mechanism upregulating the angiocrine factor plasminogen activator inhibitor-1 (PAI-1) in endothelial cells to participate in lung fibrosis. Activation of the metabolic sensor AMPK was inhibited in endothelial cells of fibrotic lungs, and AMPK inactivation was correlated with enriched fibrotic signature and reduced lung functions in humans. The inactivation of endothelial AMPK accelerated lung fibrosis in mice, while the activation of endothelial AMPK with metformin alleviated lung fibrosis. In fibrotic lungs, endothelial AMPK inactivation led to YAP activation and overexpression of the angiocrine factor PAI-1, which was positively correlated with the fibrotic signature in human fibrotic lungs and inhibition of PAI-1 with Tiplaxtinin mitigated lung fibrosis. Further study identified that the deficiency of the antioxidative gas metabolite H2S accounted for the inactivation of AMPK and activation of YAP-PAI-1 signaling in endothelial cells of fibrotic lungs. H2S deficiency was involved in human lung fibrosis and H2S supplement reversed mouse lung fibrosis in an endothelial AMPK-dependent manner. These findings provide new insight into the mechanism underlying the deregulation of the vascular angiocrine system in fibrotic organs.

Hepatic Zbtb18 (Zinc Finger and BTB Domain Containing 18) alleviates hepatic steatohepatitis via FXR (Farnesoid X Receptor).

A lasting imbalance between fatty acid synthesis and consumption leads to non-alcoholic fatty liver disease (NAFLD), coupled with hepatitis and insulin resistance. Yet the details of the underlying mechanisms are not fully understood. Here, we unraveled that the expression of the transcription factor Zbtb18 is markedly decreased in the livers of both patients and murine models of NAFLD. Hepatic Zbtb18 knockout promoted NAFLD features like impaired energy expenditure and fatty acid oxidation (FAO), and induced insulin resistance. Conversely, hepatic Zbtb18 overexpression alleviated hepato-steatosis, insulin resistance, and hyperglycemia in mice fed on a high-fat diet (HFD) or in diabetic mice. Notably, in vitro and in vivo mechanistic studies revealed that Zbtb18 transcriptional activation of Farnesoid X receptor (FXR) mediated FAO and Clathrin Heavy Chain (CLTC) protein hinders NLRP3 inflammasome activity. This key mechanism by which hepatocyte's Zbtb18 expression alleviates NAFLD and consequent liver fibrosis was further verified by FXR's deletion and forced expression in mice and cultured mouse primary hepatocytes (MPHs). Moreover, CLTC deletion significantly abrogated the hepatic Zbtb18 overexpression-driven inhibition of NLRP3 inflammasome activity in macrophages. Altogether, Zbtb18 transcriptionally activates the FXR-mediated FAO and CLTC expression, which inhibits NLRP3 inflammasome's activity alleviating inflammatory stress and insulin resistance, representing an attractive remedy for hepatic steatosis and fibrosis.

Regenerating the heart by metabolically reprogramming the cardiomyocyte epigenome.

In mammal adolescence, cardiomyocytes rapidly exit the cell cycle, and heart regeneration in adults is limited after cardiac injury. Recent work by Li et al. in Nature revealed that inhibition of fatty acid oxidation can rewire cell metabolism and lead to epigenetic reprogramming of cardiomyocytes to an immature state that facilitates cardiomyocyte cell-cycle reentry and heart regeneration in adult animals.

Voltage-dependent anion channel 1 (VDAC1) overexpression alleviates cardiac fibroblast activation in cardiac fibrosis via regulating fatty acid metabolism.

Cardiac fibrosis is characterized by the excessive deposition of extracellular matrix in the myocardium with cardiac fibroblast activation, leading to chronic cardiac remodeling and dysfunction. However, little is known about metabolic alterations in fibroblasts during cardiac fibrosis, and there is a lack of pharmaceutical treatments that target metabolic dysregulation. Here, we provided evidence that fatty acid ß-oxidation (FAO) dysregulation contributes to fibroblast activation and cardiac fibrosis. With transcriptome, metabolome, and functional assays, we demonstrated that FAO was downregulated during fibroblast activation and cardiac fibrosis, and that perturbation of FAO reversely affected the fibroblast-to-myofibroblast transition. The decrease in FAO may be attributed to reduced long-chain fatty acid (LCFA) uptake. Voltage-dependent anion channel 1 (VDAC1), the main gatekeeper of the outer mitochondrial membrane (OMM), serves as the transporter of LCFA into the mitochondria for further utilization and has been shown to be decreased in myofibroblasts. In vitro, the addition of exogenous VDAC1 was shown to ameliorate cardiac fibroblast activation initiated by transforming growth factor beta 1 (TGF-ß1) stimuli, and silencing of VDAC1 displayed the opposite effect. A mechanistic study revealed that VDAC1 exerts a protective effect by regulating LCFA uptake into the mitochondria, which is impaired by an inhibitor of carnitine palmitoyltransferase 1A. In vivo, AAV9-mediated overexpression of VDAC1 in myofibroblasts significantly alleviated transverse aortic constriction (TAC)-induced cardiac fibrosis and rescued cardiac function in mice. Finally, we treated mice with the VDAC1-derived R-Tf-D-LP4 peptide, and the results showed that R-Tf-D-LP4 prevented TAC-induced cardiac fibrosis and dysfunction in mice. In conclusion, this study provides evidence that VDAC1 maintains FAO metabolism in cardiac fibroblasts to repress fibroblast activation and cardiac fibrosis and suggests that the VDAC1 peptide is a promising drug for rescuing fibroblast metabolism and repressing cardiac fibrosis.

Sensing mitochondrial DNA stress in cardiotoxicity.

Cytoplasmic mitochondrial DNA (mtDNA) can trigger the interferon response to promote disease progression, but mtDNA sensing mechanisms remain elusive. Lei et al. have shown that Z-DNA binding protein1 (ZBP1) cooperates with cyclic GMP-AMP synthase (cGAS) to sense Z-form mtDNA and transmit mtDNA stress signals to promote diseases such as cardiotoxicity, providing an important piece of the mtDNA stress landscape.

Artificial Intelligence and Big Data Technologies in the Construction of Surgical Risk Prediction Model for Patients with Coronary Artery Bypass Grafting.

The objective of this work was to predict the risk of mortality rate in patients with coronary artery bypass grafting (CABG) based on the risk prediction model of CABG using artificial intelligence (AI) and big data technologies. The clinical data of 2,364 patients undergoing CABG in our hospital from January 2019 to August 2021 were collected in this work. Based on AI and big data technology, business requirement analysis, system requirement analysis, complication prediction module, big data mining technology, and model building are carried out, respectively; the successful CABG risk prediction system includes case feature analysis service, risk warning service, and case retrieval service. The commonly used precision, recall, and F1-score were adopted to evaluate the quality of the gradient-boosted tree (GBT) model. The analysis proved that the GBT model was the best in terms of precision, F1-score, and area under the receiver operating characteristic curve (ROC). According to the CABG risk prediction model, 1,382 patients had a score of <0, 463 patients had a score of 0 ≤ score ≤ 2, 252 patients had a score of 2 < score ≤ 5, and 267 patients had a score of >5, which were stratified into four groups: A, B, C, and D. The actual number of in-hospital deaths was 25, and the in-hospital mortality rate was 1.05%. The mortality rate predicted by the CABG risk prediction model was 2.67 ± 1.82% (95% confidential interval (CI) (2.87-2.98)), which was higher than the actual value. The CABG risk prediction model showed the credible results only in group B with AUC = 0.763 > 0.7. In group B, 3 patients actually died, the actual mortality rate was 0.33%, and the predicted mortality rate was 0.96 ± 0.78 (95% CI (0.82-0.87)), which overestimated the mortality rate of patients in group B. It successfully constructed a CABG risk prediction model based on the AI and big data technologies, which would overestimate the mortality of patients with intermediate risk, and it is suitable for different types of heart diseases through continuous research and development and innovation, and provides clinical guidance value.

Gut microbiota and microbiota-derived metabolites in cardiovascular diseases.

ABSTRACT: Cardiovascular diseases, including heart failure, coronary artery disease, atherosclerosis, aneurysm, thrombosis, and hypertension, are a great economic burden and threat to human health and are the major cause of death worldwide. Recently, researchers have begun to appreciate the role of microbial ecosystems within the human body in contributing to metabolic and cardiovascular disorders. Accumulating evidence has demonstrated that the gut microbiota is closely associated with the occurrence and development of cardiovascular diseases. The gut microbiota functions as an endocrine organ that secretes bioactive metabolites that participate in the maintenance of cardiovascular homeostasis, and their dysfunction can directly influence the progression of cardiovascular disease. This review summarizes the current literature demonstrating the role of the gut microbiota in the development of cardiovascular diseases. We also highlight the mechanism by which well-documented gut microbiota-derived metabolites, especially trimethylamine N-oxide, short-chain fatty acids, and phenylacetylglutamine, promote or inhibit the pathogenesis of cardiovascular diseases. We also discuss the therapeutic potential of altering the gut microbiota and microbiota-derived metabolites to improve or prevent cardiovascular diseases.

SIRT6 is an epigenetic repressor of thoracic aortic aneurysms via inhibiting inflammation and senescence.

Thoracic aortic aneurysms (TAAs) develop asymptomatically and are characterized by dilatation of the aorta. This is considered a life-threating vascular disease due to the risk of aortic rupture and without effective treatments. The current understanding of the pathogenesis of TAA is still limited, especially for sporadic TAAs without known genetic mutation. Sirtuin 6 (SIRT6) expression was significantly decreased in the tunica media of sporadic human TAA tissues. Genetic knockout of Sirt6 in mouse vascular smooth muscle cells accelerated TAA formation and rupture, reduced survival, and increased vascular inflammation and senescence after angiotensin II infusion. Transcriptome analysis identified interleukin (IL)-1ß as a pivotal target of SIRT6, and increased IL-1ß levels correlated with vascular inflammation and senescence in human and mouse TAA samples. Chromatin immunoprecipitation revealed that SIRT6 bound to the Il1b promoter to repress expression partly by reducing the H3K9 and H3K56 acetylation. Genetic knockout of Il1b or pharmacological inhibition of IL-1ß signaling with the receptor antagonist anakinra rescued Sirt6 deficiency mediated aggravation of vascular inflammation, senescence, TAA formation and survival in mice. The findings reveal that SIRT6 protects against TAA by epigenetically inhibiting vascular inflammation and senescence, providing insight into potential epigenetic strategies for TAA treatment.

Sirtuin 2 deficiency aggravates ageing-induced vascular remodelling in humans and mice.

AIMS: The mechanisms underlying ageing-induced vascular remodelling remain unclear. This study investigates the role and underlying mechanisms of the cytoplasmic deacetylase sirtuin 2 (SIRT2) in ageing-induced vascular remodelling. METHODS AND RESULTS: Transcriptome and quantitative real-time PCR data were used to analyse sirtuin expression. Young and old wild-type and Sirt2 knockout mice were used to explore vascular function and pathological remodelling. RNA-seq, histochemical staining, and biochemical assays were used to evaluate the effects of Sirt2 knockout on the vascular transcriptome and pathological remodelling and explore the underlying biochemical mechanisms. Among the sirtuins, SIRT2 had the highest levels in human and mouse aortas. Sirtuin 2 activity was reduced in aged aortas, and loss of SIRT2 accelerated vascular ageing. In old mice, SIRT2 deficiency aggravated ageing-induced arterial stiffness and constriction-relaxation dysfunction, accompanied by aortic remodelling (thickened vascular medial layers, breakage of elastin fibres, collagen deposition, and inflammation). Transcriptome and biochemical analyses revealed that the ageing-controlling protein p66Shc and metabolism of mitochondrial reactive oxygen species (mROS) contributed to SIRT2 function in vascular ageing. Sirtuin 2 repressed p66Shc activation and mROS production by deacetylating p66Shc at lysine 81. Elimination of reactive oxygen species by MnTBAP repressed the SIRT2 deficiency-mediated aggravation of vascular remodelling and dysfunction in angiotensin II-challenged and aged mice. The SIRT2 coexpression module in aortas was reduced with ageing across species and was a significant predictor of age-related aortic diseases in humans. CONCLUSION: The deacetylase SIRT2 is a response to ageing that delays vascular ageing, and the cytoplasm-mitochondria axis (SIRT2-p66Shc-mROS) is important for vascular ageing. Therefore, SIRT2 may serve as a potential therapeutic target for vascular rejuvenation.

Alternative splicing of GSDMB modulates killer lymphocyte-triggered pyroptosis.

Granzyme A from killer lymphocytes cleaves gasdermin B (GSDMB) and triggers pyroptosis in targeted human tumor cells, eliciting antitumor immunity. However, GSDMB has a controversial role in pyroptosis and has been linked to both anti- and protumor functions. Here, we found that GSDMB splicing variants are functionally distinct. Cleaved N-terminal (NT) fragments of GSDMB isoforms 3 and 4 caused pyroptosis, but isoforms 1, 2, and 5 did not. The nonfunctional isoforms have a deleted or modified exon 6 and therefore lack a stable belt motif. The belt likely contributes to the insertion of oligomeric GSDMB-NTs into the membrane. Consistently, noncytotoxic GSDMB-NTs blocked pyroptosis caused by cytotoxic GSDMB-NTs in a dominant-negative manner. Upon natural killer (NK) cell attack, GSDMB3-expressing cells died by pyroptosis, whereas GSDMB4-expressing cells died by mixed pyroptosis and apoptosis, and GSDMB1/2-expressing cells died only by apoptosis. GSDMB4 partially resisted NK cell-triggered cleavage, suggesting that only GSDMB3 is fully functional. GSDMB1-3 were the most abundant isoforms in the tested tumor cell lines and were similarly induced by interferon-γ and the chemotherapy drug methotrexate. Expression of cytotoxic GSDMB3/4 isoforms, but not GSDMB1/2 isoforms that are frequently up-regulated in tumors, was associated with better outcomes in bladder and cervical cancers, suggesting that GSDMB3/4-mediated pyroptosis was protective in those tumors. Our study indicates that tumors may block and evade killer cell-triggered pyroptosis by generating noncytotoxic GSDMB isoforms. Therefore, therapeutics that favor the production of cytotoxic GSDMB isoforms by alternative splicing may improve antitumor immunity.

Prognostic Significance of Myocardial Blood Flow Quantification for Major Adverse Cardiac Events: A Systematic Review and Meta-analysis.

Chronic coronary syndromes involve reduced myocardial blood flow (MBF). MBF is a reliable predictor of outcomes, independent of the presence of significant stenosis. Whether MBF can predict major adverse cardiac events (MACE) during long-term follow-up is unknown. PubMed, Embase, Cochrane, CNKI, and WANFANG were searched for papers published up to January 2021. The exposure was the incremental unit of stress MBF (mL/g/min) or low MBF versus high MBF. The imaging examinations included positron emission tomography/computed tomography and coronary magnetic resonance. The study outcome was the occurrence of MACE during follow-up, summarized as time-to-event hazard ratios (HRs) and 95% confidence intervals (CIs). Six studies (300 MACEs in 2326 patients) were included. Four studies presented stress MBF data by unit increments. The pooled HR showed that an increase in stress MBF by 1 mL/g/min is a protective factor for MACE (HR = 0.32; 95% CI, 0.18-0.57; I2 = 62.9%, Pheterogeneity = 0.044). Two studies reported stress MBF as low/high. The results showed that a high-stress MBF was protective against MACEs (HR = 0.43; 95% CI, 0.24-0.78; I2 = 39.5%, Pheterogeneity = 0.199). Quantification of stress MBF using positron emission tomography/computed tomography and coronary magnetic resonance might have incremental predictive value for future MACEs in a population at intermediate to high cardiovascular risk. The results will require validation in large prospective randomized controlled trials.

Biomarkers of aging.

Aging biomarkers are a combination of biological parameters to (i) assess age-related changes, (ii) track the physiological aging process, and (iii) predict the transition into a pathological status. Although a broad spectrum of aging biomarkers has been developed, their potential uses and limitations remain poorly characterized. An immediate goal of biomarkers is to help us answer the following three fundamental questions in aging research: How old are we? Why do we get old? And how can we age slower? This review aims to address this need. Here, we summarize our current knowledge of biomarkers developed for cellular, organ, and organismal levels of aging, comprising six pillars: physiological characteristics, medical imaging, histological features, cellular alterations, molecular changes, and secretory factors. To fulfill all these requisites, we propose that aging biomarkers should qualify for being specific, systemic, and clinically relevant.

A clinical-radiomics based nomogram to predict progressive intraparenchymal hemorrhage in mild to moderate traumatic injury patients.

PURPOSE: To develop a non-contrast computed tomography(NCCT)based radiomics model for predicting intraparenchymal hemorrhage progression in patients with mild to moderate traumatic brain injury(TBI). METHODS: We retrospectively analyzed 166 mild to moderate TBI patients with intraparenchymal hemorrhage from January 2018 to December 2021. The enrolled patients were divided into training cohort and test cohort with a ratio of 6:4. Uni- and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), the calibration curve, the decision curve analysis, sensitivity, and specificity. RESULTS: Eleven radiomics features, presence with SDH, and D-dimer > 5 mg/l were selected to construct the combined clinical-radiomic model for the prediction of TICH in mild to moderate TBI patients. The AUC of the combined model was 0.81(95% confidence interval (CI), 0.72 to 0.90) in the training cohort and 0.88 (95% CI 0.79 to 0.96) in the test cohort, which were superior to the clinical model alone (AUCtraining = 0.72, AUCtest = 0.74). The calibration curve demonstrated that the radiomics nomogram had a good agreement between prediction and observation. Decision curve analysis confirmed clinically useful. CONCLUSIONS: The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors can serve as a reliable and powerful tool for Predicting intraparenchymal hemorrhage progression for patients with mild to moderate TBI.

Error identification and compensation regarding the kinematic parameter of the MD-PEF for tibial deformity correction.

The correction accuracy of an external fixator is crucial to the treatment outcome of deformity correction and patient safety. In this study, the mapping model is established between the pose error and kinematic parameter error of the motor-driven parallel external fixator (MD-PEF). Subsequently, the kinematic parameter identification and error compensation algorithm of the external fixator is established based on the least squares method. An experimental platform based on the developed MD-PEF and Vicon motion capture system is constructed for kinematic calibration experiments. Experimental results show that the correction accuracy of the MD-PEF after calibration is as follows: translation accuracy dE1 = 0.36 mm, axial translation accuracy dE2 = 0.25 mm, angulation accuracy dE3 = 0.27°, and rotation accuracy dE4 = 0.2°. The accuracy detection experiment verifies the kinematic calibration results, which further validates the feasibility and reliability of the error identification and compensation algorithm constructed by the least squares method. The calibration approach used in this work also provides an effective way to improve the accuracy of other medical robots.

Prediction of myocardial ischemia in coronary heart disease patients using a CCTA-Based radiomic nomogram.

Objective: The present study aimed to predict myocardial ischemia in coronary heart disease (CHD) patients based on the radiologic features of coronary computed tomography angiography (CCTA) combined with clinical factors. Methods: The imaging and clinical data of 110 patients who underwent CCTA scan before DSA or FFR examination in Changzhou Second People's Hospital, Nanjing Medical University (90 patients), and The First Affiliated Hospital of Soochow University (20 patients) from March 2018 to January 2022 were retrospectively analyzed. According to the digital subtraction angiography (DSA) and fractional flow reserve (FFR) results, all patients were assigned to myocardial ischemia (n = 58) and normal myocardial blood supply (n = 52) groups. All patients were further categorized into training (n = 64) and internal validation (n = 26) sets at a ratio of 7:3, and the patients from second site were used as external validation. Clinical indicators of patients were collected, the left ventricular myocardium were segmented from CCTA images using CQK software, and the radiomics features were extracted using pyradiomics software. Independent prediction models and combined prediction models were established. The predictive performance of the model was assessed by calibration curve analysis, receiver operating characteristic (ROC) curve and decision curve analysis. Results: The combined model consisted of one important clinical factor and eight selected radiomic features. The area under the ROC curve (AUC) of radiomic model was 0.826 in training set, and 0.744 in the internal validation set. For the combined model, the AUCs were 0.873, 0.810, 0.800 in the training, internal validation, and external validation sets, respectively. The calibration curves demonstrated that the probability of myocardial ischemia predicted by the combined model was in good agreement with the observed values in both training and validation sets. The decision curve was within the threshold range of 0.1-1, and the clinical value of nomogram was higher than that of clinical model. Conclusion: The radiomic characteristics of CCTA combined with clinical factors have a good clinical value in predicting myocardial ischemia in CHD patients.