The Predictive Value of Carotid Ultrasonography With Cardiovascular Risk Factors—A “SPIDER” Promoting Atherosclerosis

Li, Hongwei; Xu, Xiaolin; Luo, Baoming; Zhang, Yuling

doi:10.3389/fcvm.2021.706490

Cited by 18 publications

(15 citation statements)

References 142 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Noninvasive carotid ultrasound assessment of carotid plaques, including various CPS-based algorithms, is widely used to evaluate the atherosclerosis and carotid plaque burden. All the CPS systems have demonstrated clinical significance and predictive values for cardiovascular risks [ 19 , 20 , 21 , 22 , 23 , 24 ]. We selected the CPS developed by Handa et al in this study because of its convenience: it entails a simple summation of the maximal plaque thickness without consideration of the plaque morphology, which might vary, and the degree of stenosis, which might be time-consuming with measurement bias.…”

Section: Discussionmentioning

confidence: 99%

“…Special concerns have been aroused in elderly women regarding underdiagnosis and insufficient treatment to reduce cardiovascular morbidity and mortality [ 33 ]. Furthermore, even without them needing to treat minor carotid atherosclerosis, having patients aware of subclinical carotid atherosclerosis is beneficial for reducing cardiovascular risk, which might be attributable to improved patient compliance with medication and lifestyle modifications [ 24 , 34 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Nomogram and Carotid Risk Score for Predicting Moderate or High Carotid Atherosclerosis among Asymptomatic Elderly Recycling Volunteers

et al. 2022

View full text Add to dashboard Cite

Carotid atherosclerosis is associated with cardiovascular and cerebrovascular events. We explored an appropriate method for selecting participants without ischemic cerebrovascular disease but with various comorbidities eligible for a carotid ultrasound. This was a retrospective subgroup analysis of the carotid plaque burden from a previous study involving a vascular and cognitive survey of 956 elderly recycling volunteers (778 women and 178 men; mean age: 70.8 years). We used carotid ultrasound to detect the carotid plaque and computed the carotid plaque score (CPS). A moderate or high degree of carotid atherosclerosis (MHCA) was defined as CPS > 5 and was observed in 22% of the participants. The CPS had positive linear correlations with age, systolic blood pressure, and fasting glucose. We stratified the participants into four age groups: 60–69, 70–74, 75–79, and ≥80 years. Multivariable analysis revealed that significant predictors for MHCA were age, male sex, hypertension, diabetes mellitus, hyperlipidemia, coronary artery disease, and a nonvegetarian diet. Coronary artery disease and advanced age were the two strongest predictors. We chose the aforementioned seven significant predictors to establish a nomogram for MHCA prediction. The area under the receiver operating characteristic curve in internal validation with 10-fold cross-validation and the classification accuracy of the nomogram were 0.785 and 0.797, respectively. We presumed people who have a ≥50% probability of MHCA warranted a carotid ultrasound. A flowchart table derived from the nomogram addressing the probabilities of all models of combinations of comorbidities was established to identify participants who had a probability of MHCA ≥ 50% (corresponding to a total nomogram score of ≥15 points). We further established a carotid risk score range from 0 to 17 comprising the seven predictors. A carotid risk score ≥ 7 was the most optimal cutoff value associated with a probability of MHCA ≥ 50%. Both total nomogram score ≥ 15 points and carotid risk score ≥ 7 can help in the rapid identification of individuals without stroke but who have a ≥50% probability of MHCA—these individuals should schedule a carotid ultrasound.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Nomogram and Carotid Risk Score for Predicting Moderate or High Carotid Atherosclerosis among Asymptomatic Elderly Recycling Volunteers

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Результаты многочисленных эпидемиологических, в т.ч. проспективных, исследований продемонстрировали высокое прогностическое значение СКА в отношении риска развития сердечно-сосудистых осложнений, а его предсказательная ценность сопоставима с таковой при использовании коронарного кальциевого индекса [7][8][9].…”

Section: ключевые моментыunclassified

Verification of subclinical carotid atherosclerosis as part of risk stratification in overweight and obesity: the role of machine learning in the development of a diagnostic algorithm

Дружилов

Kuznetsova

Gavrilov³

et al. 2022

Cardiovasc Ther Prev

View full text Add to dashboard Cite

Aim. Comparative analysis of mathematical models obtained using multivariate logistic regression (MLR) with stepwise inclusion of predictors and machine learning (ML) for assessing the probability of subclinical carotid atherosclerosis in normotensive overweight and obese patients without cardiovascular diseases and/or diabetes.Material and methods. We received data on patients from the Webiomed platform database. The inclusion criteria were age ≥18 years, body mass index ≥25 kg/m2, extracranial artery ultrasound results, while the exclusion criteria included diabetes and/or cardiovascular disease. MLR analysis was carried out with stepwise inclusion of predictors. ML algorithms were used to create an alternative model.Results. The overall percentage of true results for MLR model was 73,2%, while the proportion of true negative and positive predictions was 80,1% and 63,4%, respectively. Mathematical models created using ML methods are characterized by a predictive value from 75 to 97% with a sensitivity of 77 to 92% and a specificity of 80 to 98%.Conclusion. A significant superiority of ML models was revealed in the study of available clinical and paraclinical parameters. Integration of ML mathematical models into a diagnostic algorithm for making a decision to refer a low-risk patient for extracranial artery ultrasound will significantly improve its accuracy and cost efficiency.

show abstract

“…на сосудистую стенку всего спектра неблагоприятных факторов при избыточном весе и ожирении [3]. По данным многочисленных срезовых и проспективных исследований выявление СКА имеет высокое прогностическое значение в отношении риска развития сердечно-сосудистых осложнений, сопоставимое с оценкой коронарного кальциевого индекса [6][7][8].…”

unclassified

Predicting the subclinical carotid atherosclerosis in overweight and obese patients using a machine learning model

Gavrilov¹,

Kuznetsova

Дружилов

et al. 2022

Russ J Cardiol

View full text Add to dashboard Cite

Aim. To develop a model for predicting the subclinical carotid atherosclerosis (SCA) in order to refine cardiovascular risk (CVR) using machine learning methods in overweight and obese patients without hypertension, diabetes and/or cardiovascular disease (CVD).Material and methods. Anonymized database (DB) Webiomed (2.9 million patients) was used. There were following inclusion criteria: age ≥18 years, body mass index ≥25 kg/m2, availability of data on ultrasound of extracranial arteries. Patients with hypertension, diabetes and/or CVD were excluded from the analysis. Data on 5750 patients were selected, of which atherosclerotic plaques were detected in 385 people. The final data set contained information on 447 patients, 197 (44,1%) of which had SCA. Quantitative and categorical traits for model training were taken with 40% occupancy in the database. The number of final traits for machine learning was 28. When creating the model, 3 Random Forest algorithms, AdaBoostClassifier, KNeighborsClassifier and the Scikit-learn library were used. To improve the model performance, the fill missing function was used. The target parameters of the model were given a predictive ability (accuracy) of at least 75%, while the area under the ROC curve was at least 0,75.Results. The resulting dataset was divided into training and test parts in a ratio of 80:20. Depending on the applied algorithms, the learned model was characterized by a predictive ability of 75-97%, sensitivity of 77-92%, specificity of 80-98%, and area under the ROC-curve of 0,88-0,97. Taking into account the accuracy metrics, the best results were obtained for the model learned by the Random Forest algorithm (95%, 92%, 98% and 0,95, respectively).Conclusion. The developed model can help a physician make a decision to refer an overweight and obese patient without cardiovascular diseases for ultrasound of extracranial arteries, which contributes to a more accurate CVR stratification. The introduction of such risk stratification algorithms into practice will increase the accuracy and quality of CVR prediction and optimize the system of preventive measures.

show abstract

The Predictive Value of Carotid Ultrasonography With Cardiovascular Risk Factors—A “SPIDER” Promoting Atherosclerosis

Cited by 18 publications

References 142 publications

Nomogram and Carotid Risk Score for Predicting Moderate or High Carotid Atherosclerosis among Asymptomatic Elderly Recycling Volunteers

Nomogram and Carotid Risk Score for Predicting Moderate or High Carotid Atherosclerosis among Asymptomatic Elderly Recycling Volunteers

Verification of subclinical carotid atherosclerosis as part of risk stratification in overweight and obesity: the role of machine learning in the development of a diagnostic algorithm

Predicting the subclinical carotid atherosclerosis in overweight and obese patients using a machine learning model

Contact Info

Product

Resources

About