PQPeng Qi

Peng Qi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Peng Qi has a total of 53 co-authors. Here are the top co-authors by number of shared publications:

  • Daming Wang

    Department of Neurosurgery, Beijing Hospital, National Center of Gerontology, National Health Commission, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, PR China

    5 shared publications
  • Jun Lu

    Department of Neurosurgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China

    3 shared publications
  • Jun Lu

    Department of Neurosurgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China

    3 shared publications
  • Junjie Wang

    Department of Neurosurgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China

    3 shared publications
  • Aihua Liu

    Beijing Neurosurgical Institute, Beijing Tiantan Hospital, Capital Medical University

    2 shared publications
  • Juan Chen

    Department of Neurosurgery, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China

    2 shared publications

Latest Publications

  • Evaluating long-term outcomes of endovascular revascularization in symptomatic chronic internal carotid artery occlusion: A multicenter cohort study

    by Xiaoliang Yin, Xiaodong Chen, Jiachun Liu, Junjie Wang, Jun Lu, Qi Peng, Yiling Cai, Xiaogang Li, Yu Fu, Xumin Pan, et al.

  • Open Access

    Comparative study on clinical outcomes and cost-effectiveness of chronic subdural hematomas treated by middle meningeal artery embolization and conventional treatment: a national cross-sectional study

    by Xin Tong, Xiaopeng Xue, Aihua Liu, Peng Qi

    Background: The authors compared the efficacy and cost-effectiveness of middle meningeal artery embolization (MMAE) and conventional treatment for chronic subdural hematomas (cSDH). Methods: The Nationwide Readmissions Database of 9963 patients (27.2% women) with cSDH between 2016 and 2020 was analyzed. Finally, 9532 patients were included (95.7%, treated conventionally; 4.3%, treated with MMAE). Baseline demographics, comorbidities, adverse events, treatment strategies, and outcomes were compared between patients treated with MMAE and conventional treatment. After propensity score matching, the authors compared primary outcomes, including the 90-day treatment rate, functional outcome, length of hospital stays, and cost. A Markov model estimated lifetime costs and quality-adjusted life years (QALYs) associated with different treatments. The incremental cost-effectiveness ratio (ICER) was calculated to evaluate the base-case scenario. One-way, two-way, and probabilistic sensitivity analyses were performed to evaluate the uncertainty in the results. Results: After propensity score matching, MMAE had a lower 90-day retreatment rate (2.6 vs. 9.0%, P=0.001), shorter length of hospital stays (4.61±6.19 vs. 5.73±5.76 days, P=0.037), similar functional outcomes compared (favorable outcomes, 80.9 vs. 74.8%, P=0.224) but higher costs ($119 757.71±90 378.70 vs. $75 745.55±100 701.28, P<0.001) with conventional treatment. MMAE was associated with an additional cost of US$19 280.0 with additional QALY of 1.3. Its ICER was US$15199.8/QALY. Conclusion: MMAE is more effective in treating cSDH than conventional treatment. Based on real-world data, though MMAE incurs higher overall costs, the Markov model showed it to be cost-effective compared to conventional treatment under the American healthcare system. These comparative and economic analyses further support the consideration of a paradigm shift in cSDH treatment.


  • Open Access

    Non-Contrasted CT Radiomics for SAH Prognosis Prediction

    by Dezhi Shan, Junjie Wang, Peng Qi, Jun Lu, Daming Wang

    Subarachnoid hemorrhage (SAH) denotes a serious type of hemorrhagic stroke that often leads to a poor prognosis and poses a significant socioeconomic burden. Timely assessment of the prognosis of SAH patients is of paramount clinical importance for medical decision making. Currently, clinical prognosis evaluation heavily relies on patients’ clinical information, which suffers from limited accuracy. Non-contrast computed tomography (NCCT) is the primary diagnostic tool for SAH. Radiomics, an emerging technology, involves extracting quantitative radiomics features from medical images to serve as diagnostic markers. However, there is a scarcity of studies exploring the prognostic prediction of SAH using NCCT radiomics features. The objective of this study is to utilize machine learning (ML) algorithms that leverage NCCT radiomics features for the prognostic prediction of SAH. Retrospectively, we collected NCCT and clinical data of SAH patients treated at Beijing Hospital between May 2012 and November 2022. The modified Rankin Scale (mRS) was utilized to assess the prognosis of patients with SAH at the 3-month mark after the SAH event. Based on follow-up data, patients were classified into two groups: good outcome (mRS ≤ 2) and poor outcome (mRS > 2) groups. The region of interest in NCCT images was delineated using 3D Slicer software, and radiomic features were extracted. The most stable and significant radiomic features were identified using the intraclass correlation coefficient, t-test, and least absolute shrinkage and selection operator (LASSO) regression. The data were randomly divided into training and testing cohorts in a 7:3 ratio. Various ML algorithms were utilized to construct predictive models, encompassing logistic regression (LR), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and multi-layer perceptron (MLP). Seven prediction models based on radiomic features related to the outcome of SAH patients were constructed using the training cohort. Internal validation was performed using five-fold cross-validation in the entire training cohort. The receiver operating characteristic curve, accuracy, precision, recall, and f-1 score evaluation metrics were employed to assess the performance of the classifier in the overall dataset. Furthermore, decision curve analysis was conducted to evaluate model effectiveness. The study included 105 SAH patients. A comprehensive set of 1316 radiomics characteristics were initially derived, from which 13 distinct features were chosen for the construction of the ML model. Significant differences in age were observed between patients with good and poor outcomes. Among the seven constructed models, model_SVM exhibited optimal outcomes during a five-fold cross-validation assessment, with an average area under the curve (AUC) of 0.98 (standard deviation: 0.01) and 0.88 (standard deviation: 0.08) on the training and testing cohorts, respectively. In the overall dataset, model_SVM achieved an accuracy, precision, recall, f-1 score, and AUC of 0.88, 0.84, 0.87, 0.84, and 0.82, respectively, in the testing cohort. Radiomics features associated with the outcome of SAH patients were successfully obtained, and seven ML models were constructed. Model_SVM exhibited the best predictive performance. The radiomics model has the potential to provide guidance for SAH prognosis prediction and treatment guidance.


  • Open Access

    Computed tomography angiography-based radiomics model for predicting carotid atherosclerotic plaque vulnerability

    by Dezhi Shan, Siyu Wang, Junjie Wang, Jun Lu, Junhong Ren, Juan Chen, Daming Wang, Peng Qi

    Vulnerable carotid atherosclerotic plaque (CAP) significantly contributes to ischemic stroke. Neovascularization within plaques is an emerging biomarker linked to plaque vulnerability that can be detected using contrast-enhanced ultrasound (CEUS). Computed tomography angiography (CTA) is a common method used in clinical cerebrovascular assessments that can be employed to evaluate the vulnerability of CAPs. Radiomics is a technique that automatically extracts radiomic features from images. This study aimed to identify radiomic features associated with the neovascularization of CAP and construct a prediction model for CAP vulnerability based on radiomic features. CTA data and clinical data of patients with CAPs who underwent CTA and CEUS between January 2018 and December 2021 in Beijing Hospital were retrospectively collected. The data were divided into a training cohort and a testing cohort using a 7:3 split. According to the examination of CEUS, CAPs were dichotomized into vulnerable and stable groups. 3D Slicer software was used to delineate the region of interest in CTA images, and the Pyradiomics package was used to extract radiomic features in Python. Machine learning algorithms containing logistic regression (LR), support vector machine (SVM), random forest (RF), light gradient boosting machine (LGBM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and multi-layer perception (MLP) were used to construct the models. The confusion matrix, receiver operating characteristic (ROC) curve, accuracy, precision, recall, and f-1 score were used to evaluate the performance of the models. A total of 74 patients with 110 CAPs were included. In all, 1,316 radiomic features were extracted, and 10 radiomic features were selected for machine-learning model construction. After evaluating several models on the testing cohorts, it was discovered that model_RF outperformed the others, achieving an AUC value of 0.93 (95% CI: 0.88–0.99). The accuracy, precision, recall, and f-1 score of model_RF in the testing cohort were 0.85, 0.87, 0.85, and 0.85, respectively. Radiomic features associated with the neovascularization of CAP were obtained. Our study highlights the potential of radiomics-based models for improving the accuracy and efficiency of diagnosing vulnerable CAP. In particular, the model_RF, utilizing radiomic features extracted from CTA, provides a noninvasive and efficient method for accurately predicting the vulnerability status of CAP. This model shows great potential for offering clinical guidance for early detection and improving patient outcomes.


  • Open Access

    CT-based thrombus radiomics nomogram for predicting secondary embolization during mechanical thrombectomy for large vessel occlusion

    by Shadamu Yusuying, Yao Lu, Shun Zhang, Junjie Wang, Juan Chen, Daming Wang, Jun Lu, Peng Qi

    Background and aims: Secondary embolization (SE) during mechanical thrombectomy (MT) for cerebral large vessel occlusion (LVO) could reduce the anterior blood flow and worsen clinical outcomes. The current SE prediction tools have limited accuracy. In this study, we aimed to develop a nomogram to predict SE following MT for LVO based on clinical features and radiomics extracted from computed tomography (CT) images.Materials and methods: A total of 61 patients with LVO stroke treated by MT at Beijing Hospital were included in this retrospective study, of whom 27 developed SE during the MT procedure. The patients were randomly divided (7:3) into training (n = 42) and testing (n = 19) cohorts. The thrombus radiomics features were extracted from the pre-interventional thin-slice CT images, and the conventional clinical and radiological indicators associated with SE were recorded. A support vector machine (SVM) learning model with 5-fold cross-verification was used to obtain the radiomics and clinical signatures. For both signatures, a prediction nomogram for SE was constructed. The signatures were then combined using the logistic regression analysis to construct a combined clinical radiomics nomogram.Results: In the training cohort, the area under the receiver operating characteristic curve (AUC) of the nomograms was 0.963 for the combined model, 0.911 for the radiomics, and 0.891 for the clinical model. Following validation, the AUCs were 0.762 for the combined model, 0.714 for the radiomics model, and 0.637 for the clinical model. The combined clinical and radiomics nomogram had the best prediction accuracy in both the training and test cohort.Conclusion: This nomogram could be used to optimize the surgical MT procedure for LVO based on the risk of developing SE.


  • Open Access

    Collateral Circulation and BNP in Predicting Outcome of Acute Ischemic Stroke Patients with Atherosclerotic versus Cardioembolic Cerebral Large-Vessel Occlusion Who Underwent Endovascular Treatment

    by Ruoyao Cao, Yao Lu, Peng Qi, Yanyan Wang, Hailong Hu, Yun Jiang, Min Chen, Juan Chen

    Purpose: The aim of this study was to verify the value of collateral circulation and B-type natriuretic peptide (BNP) in predicting clinical outcomes of patients with acute ischemic stroke (AIS) and their biomarker value for stroke subtypes before endovascular treatment (EVT). Patients and Methods: In this retrospective study, 182 patients who underwent EVT for unilateral anterior circulation large-vessel occlusion between March 2016 and January 2022 were analyzed. The modified collateral circulation scoring system on four-dimensional computed tomography angiography (4D CTA-CS) was used to assess collateral status, and stroke subtypes were determined according to the TOAST classification criteria. Patients were divided into good (mRS ≤ 2) and poor outcome (mRS > 2) groups based on their modified Rankin Scale (mRS) score at 3 months. Results: 4D CTA-CS was an independent predictor of the clinical outcome for all AIS patients (odds ratio = 0.253; 95% CI, 0.147–0.437; p < 0.001), CE stroke patients (odds ratio = 0.513; 95% CI, 0.280–0.939; p = 0.030), and LAA stroke patients (odds ratio = 0.148; 95% CI, 0.049–0.447; p = 0.001). The BNP was a biomarker for clinical outcome prediction in CE (odds ratio = 1.004; 95% CI, 1.001–1.008; p = 0.005) but not in LAA patients. Combined with BNP, 4D CTA-CS improved predictive values for clinical outcomes (p < 0.05). Conclusion: Collateral status and BNP could be used as independent predictors of clinical outcomes in AIS patients and could determine stroke subtypes (CE stroke or LAA stroke). In addition, the model of 4D CTA-CS combined with BNP was the most effective in predicting clinical outcomes compared with collateral status or BNP alone.


  • Open Access

    Plaque characteristics after endovascular treatment in patients with intracranial atherosclerotic disease

    by Shun Zhang, Junjie Wang, Jun Lu, Peng Qi, Shen Hu, Ximeng Yang, Kunpeng Chen, Daming Wang

    Background: Endovascular treatment (EVT) is an alternative option for symptomatic intracranial atherosclerotic disease (ICAD). However, the effect of EVT treatment on ICAD plaques is still unclear. This study describes the ICAD plaque characteristics after EVT treatment and analyzes the effect of different EVT treatments on plaque characteristics. Method: From 2017 January to 2022 January, ICAD patients who underwent endovascular treatment and had follow-up high-resolution magnetic resonance image (HRMRI) were enrolled in the study. Multiple plaque characteristics, including plaque enhancement, plaque burden, were measured based on preoperative, and follow-up HRMRI. Plaque characteristics and postoperative plaque changes were analyzed between different treatment groups. Result: Finally, 50 intracranial atherosclerotic plaques in 45 patients were included. Including 28 male patients and 17 female, media age 63.0 years old. Among 50 plaques, 41 received percutaneous angioplasty (including 22 plain balloons and 19 drug-coated balloons (DCB)) and the other 9 underwent stenting. Stenosis rate, plaque burden and eccentricity index at the lesion site were significantly decreased after EVT compared with preoperative periods (p p < 0.001). No significant preoperative and postoperative changes in other plaque characteristics were found. Conclusion: EVT treatment could compromise the characteristics of intracranial periarterial atherosclerotic plaques, and DCB treatment may result in a reduction in plaque enhancement after treatment.


  • Additive Effect of Coexisting Aneurysms Increases Subarachnoid Hemorrhage Risk in Patients With Multiple Aneurysms

    by Xin Feng, Xin Tong, Fei Peng, Hao Niu, Peng Qi, Jun Lu, Yang Zhao, Weitao Jin, Zhongxue Wu, He Liu, et al.

    Background and Purpose: It remains unclear whether the additive effect of coexisting intracranial aneurysms increases the risk of subarachnoid hemorrhage (SAH) in patients with multiple intracranial aneurysms. We have performed a tentative analysis for the additive effect of coexisting aneurysms. Methods: This multi-institutional cross-sectional study included 1781 aneurysms from 746 patients with multiple intracranial aneurysms. Using the generalized linear mixed model, we analyzed risk factors associated with individual aneurysm rupture and assessed the additive risk of SAH for each patient. Results: The coexisting aneurysms number was not significantly associated with individual intracranial aneurysm rupture, both in unadjusted and adjusted analyses. Patient-level analysis found that an increased number of coexisting aneurysms was significantly associated with a greater estimated additive risk ( P P <0.001). Compared with aneurysm-related factors, the estimated additive effect had better discrimination power for SAH risk, with areas under the receiver operating characteristic curve of 0.821. Conclusions: We found that a greater number of coexisting aneurysms did not increase rupture risk of individual aneurysms, but the potential additive effect might increase SAH risk in patients with multiple intracranial aneurysms.


  • Open Access

    Morphological Irregularity of Unruptured Intracranial Aneurysms is More Related with Aneurysm Size Rather Than Cerebrovascular Atherosclerosis: A Case-Control Study

    by Peng Qi, Xin Feng, Jun Lu, Junjie Wang, Shen Hu, Daming Wang

    Objective: It remains unclear whether irregular morphological features of intracranial aneurysms (IAs) are associated with atherosclerosis. We investigated the effect of cerebrovascular atherosclerosis stenosis (CAS) on irregular morphology of IAs. Patients and Methods: This single-center case-control study included consecutive patients with IAs at our institution from September 2011 to September 2018. Cases were patients with irregular IAs, and age- and location-matched controls were patients with regular IAs. Conditional logistic regression models were used to assess the relationship between angiographic variables of CAS and aneurysmal irregularity. Results: A total of 140 cases of irregular IAs and 140 controls were included in the analysis. Sixteen patients with irregular IAs (11.4%) and eleven patients with regular IAs (7.9%) had > 50% parent artery stenosis; however, the differences were not statistically significant between these two groups. In addition, no significant between-group differences were observed in distributions of the cerebrovascular stenosis, number of arterial stenoses, and location of the stenosis. In the final adjusted conditional logistic regression model, only aneurysm size (≥ 7 mm) was significantly associated with irregular IA morphology (P = 0.022). Moreover, 89 cases of irregular IAs and 89 controls were included in the analysis of unruptured IAs (UIAs). In the final adjusted conditional logistic regression model, only aneurysm size (≥ 7 mm) was significantly associated with irregular UIA morphology (P = 0.020). Conclusion: Our findings indicate that the morphological irregularity of unruptured intracranial aneurysms is more related with aneurysm size rather than cerebrovascular atherosclerosis. Further studies are needed to use prospective data to identify causative factors responsible for aneurysmal irregularity.