ObjectiveTo explore the utility of machine learning-based radiomics models for risk stratification of severe asymptomatic carotid stenosis (ACS). MethodsThe clinical data and head and neck CT angiography images of 188 patients with severe carotid artery stenosis at the Department of Cardiovascular Surgery, China-Japan Friendship Hospital from 2017 to 2021 were retrospectively collected. The patients were randomly divided into a training set (n=131, including 107 males and 24 females aged 68±8 years), and a validation set (n=57, including 50 males and 7 females aged 67±8 years). The volume of interest was manually outlined layer by layer along the edge of the carotid plaque on cross-section. Radiomics features were extracted using the Pyradiomics package of Python software. Intraclass and interclass correlation coefficient analysis, redundancy analysis, and least absolute shrinkage and selection operator regression analysis were used for feature selection. The selected radiomics features were constructed into a predictive model using 6 different supervised machine learning algorithms: logistic regression, decision tree, random forest, support vector machine, naive Bayes, and K nearest neighbor. The diagnostic efficacy of each prediction model was compared using the receiver operating characteristic (ROC) curve and the area under the curve (AUC), which were validated in the validation set. Calibration and clinical usefulness of the prediction model were evaluated using calibration curve and decision curve analysis (DCA). ResultsFour radiomics features were finally selected based on the training set for the construction of a predictive model. Among the 6 machine learning models, the logistic regression model exhibited higher and more stable diagnostic efficacy, with an AUC of 0.872, a sensitivity of 100.0%, and a specificity of 66.2% in the training set; the AUC, sensitivity and specificity in the validation set were 0.867, 83.3% and 78.8%, respectively. The calibration curve and DCA showed that the logistic regression model had good calibration and clinical usefulness. ConclusionThe machine learning-based radiomics model shows application value in the risk stratification of patients with severe ACS.
Objective To observe the clinical characteristics and therapeutic effects of carotid artery stenosisrelated ocular ischemic appearance(OIA).Methods The clinical data of 210 patients of carotid artery stenosis (81 of them with OIA) were retrospectively reviewed. They were diagnosed by color doppler image（CDI）or digital subtraction angiography (DSA),and had undergone medicine,carotid artery stenting (CAS)and carotid endarterectomy (CEA). Of 81 patients with OIA,49 patients (60.49%) with OIA only, 32 patients（39.51%）with ocular ischemic disease (OID).24/32 OID patients received ophthalmic treatment such as retinal laser photocoagulation and anti glaucoma therapy (drugs and cyclocryotherapy). Results The ocular manifestations of 81 OIA patients included transient amaurosis in 38 cases (47.14%),flash before the eye in 30 cases (36.67%), periorbital swelling and pain in 28 cases (34.57%), diplopia in 11 cases (13.58%) and vision loss in 9 cases (11.11%). The ocular manifestations of 32 OID patients included ischemic optic neuropathy in 9 cases (28.13%), ocular ischemic syndrome in 6 cases (18.75%), central or branch retinal artery occlusion in 6 cases (18.75%), retinal hemorrhage in 5 patients (15.62%)，extraocular muscle paralysis in 4 patients (12.50%) and neovascular glaucoma in 2 patients (6.25%). The higher the degree of carotid stenosis,the higher incidence of ocular ischemic disease,there was highly positive correlation between each other (R=0.837, P＜0.05).The total effective rate of carotid artery stenting and carotid endarterectomy was significantly higher than drug treatment alone (t=2.73, 3.14; P＜0.01). Conclusion The ocular manifestations of carotid stenosis related ocular ischemic appearance can be transient amaurosis, eyes flashing,eye redness,periorbital pain, diplopia and decreased visual acuity.The ocular manifestations of carotid stenosisrelated ocular ischemic disease can be ischemic optic neuropathy, ocular ischemic symptoms, central or branch retinal artery occlusion and neovascular Carotid artery stenting and carotid endarterectomy are more effective than drug treatment alone for those patients.
ObjectiveTo analyze the short-term and long-term efficacy of staged coronary artery bypass grafting (CABG) and carotid artery stenting (CAS) compared with CABG alone in patients with coronary heart disease with preoperative history of stroke and carotid stenosis. MethodsWe reviewed the clinical data of 55 patients (48 males, 7 females, aged 67.62±7.06 years) with coronary heart disease and carotid stenosis who had a history of stroke and underwent CABG+CAS or CABG alone in Zhongshan Hospital from 2008 to 2017. There were 13 patients in the staged CABG+CAS group and 42 patients in the CABG alone group. The differences in the incidence of perioperative adverse events and long-term survival between the two groups were studied, and univariate and multivariate analyses were carried out to determine the independent risk factors of long-term adverse events. Results Perioperative adverse events occurred in 1 (7.69%) patient of the staged CABG+CAS group, and 4 (9.52%) patients of the CABG alone group (P=0.84). During the follow-up period (67.84±37.99 months), the long-term survival rate of patients in the staged CABG+CAS group was significantly higher than that in the CABG alone group (P=0.02). The risk of long-term adverse events in the staged CABG+CAS group was 0.22 times higher than that in the CABG alone group (95%CI 0.05-0.92, P=0.04). ConclusionStaged CABG+CAS can significantly improve the long-term survival prognosis without increasing the perioperative risk. It is a safe and effective treatment, but prospective randomized studies are still needed to further confirm this finding.
Objective To observe the choroidal blood flow and morphological changes in patients with severe stenosis of internal carotid artery stenosis (ICAS). Methods A retrospective case-control study. Forty-six patients (46 eyes) with ICAS were enrolled in this study. There was severe stenosis in one side (the eyes in this side were set as case group) and mild or no stenosis in other side (the eyes in this side were set as control group). Color doppler ultrasound (CDI) was used to observe the changes of hemodynamic parameters of the ophthalmic artery (OA) and posterior ciliary artery (PCA), the main parameters of ultrasound Doppler imaging are peak systolic velocity (PSV), end diastolic velocity (EDV), resistance indices (RI) and the calculation of the pulsation indices (PI) through the use of a formula. Enhanced binarization of deep imaging coherence tomography (EDI-OCT) was used to measure the subfoveal choroidal thickness (SFCT). The total subfoveal choroidal area (TCA), luminal (LA), stromal (SA) and choroidal vascularity index (CVI) were obtained by modified image binarization technique. Results In the case group, the PSV in the OA and PCA was significantly lower than that of the control group (t=−2.200, −2.612; P=0.030, 0.011). There were no significant differences in EDV, RI, PI of OA (t=0.337, −1.810, −1.848; P=0.737, 0.074, 0.068) and PCA (t=−1.160, 1.400, 0.815; P=0.249, 0.165, 0.417). The SFCT (t=−3.711, P＜0.001), TCA (t=−2.736, P=0.007), LA (t=−3.188, P=0.002) and CVI (t=−2.096, P=0.039) of the case group was significantly lower than that of the control group. There were no significant differences in SA (t=−1.262, P=0.210) and LA/SA (t=−1.696, P=0.093). Conclusion In severe stenosis ICAS eyes, the PSV in the PCA and SFCT, TCA, LA, CVI are decreased.
Objective To investigate the clinical characteristics and mechanisms of ocular manifestations related to carotid artery stenosis. Methods The general clinic data and related ocular manifestations in 124 patients with carotid artery stenosis were retrospectively. Results In the 124 patients, 36 (29%) had ocular manifestations, and 28 (22. 6 %) complained the ocular discomfort as the first symptom. Among the 36 patients, 31 patients (86.1%) had been disclosed unilateral or double stenosis of internal carotid artery by carotid Doppler ultrasound examination, and the result of digital subtract angiography revealed middle and severe degree of internal carotid artery stenosis in 8 and 23 patients respectively. There was no statistic difference of incidence of ocular manifestations between 67 patients of severe internal carotid artery stenosis and 34 patients with middle one（chi;２test,P =0.266 2，P＞0.05). The ocular manifestations included amaurosis fugax (52.8%),acute decline or loss of the visual ability and defect of visual fields (36.1%), binocular diplopia (13.9%), ptosis (13.9%), and persistent high intraocular pressure(2.8%) one patient might had several ocular manifestations simultaneously. In 36 patients, central retinal artery occlusion had been diagnosed in 4, venous stasis retinopathy in 1,central or branch retinal vein occlusion in 6, neovascular glaucoma in 1, and anterior ischemic opticneuropathy in 2. One patient with double occlusion of internal carotid artery didnrsquo;t have any ocular manifestation. Conclusion Carotid artery stenosis, especially internal carotid artery may lead to acute or chronic ocular ischemic lesions, and the occurrence of ocular manifestations in chronic ocular ischemic lesions relates to compensa tion of collateral circulation；patients with ocular ischemic lesions are recomm end to undergo a routine carotid artery examination. (Chin J Ocul Fundus Dis, 2006,22:376-378)
ObjectiveTo investigate the risk factors of carotid endarterectomy.MethodThe literatures about carotid artery stenosis in the past 30 years were screened through literature retrieval, and the study of surgical risk factors related to carotid artery stenosis were reviewed.ResultsThere were many risk factors associated with the carotid endarterectomy, including demographic, underlying disease, surgical factors, perioperative management, and so on. However, the risk factors analysis were not comprehensive enough in the current study, so there was still lack of effective methods to predict the surgical risk of carotid artery stenosis.ConclusionTo fully understand the risk factors of carotid endarterectomy and to establish a multi-factor prediction model is the direction of further research.