An accurate and explainable ensemble learning method for carotid plaque prediction in an asymptomatic population

The study on risk assessment of carotid plaques in the Northern Chinese population based on LASSO regression

Early identification and management of asymptomatic carotid plaques can reduce the risk of cardiovascular and cerebrovascular events. This study aimed to explore the factors that affect carotid plaques in the Northern Chinese population and construct a nomogram for risk assessment to identify high-risk populations for carotid artery plaques. A cross-sectional study on cardiovascular factors was conducted in Shijingshan District, Beijing, from January 2022 and August to September 2023, targeting individuals aged 18 years and above. Carotid plaques were assessed via carotid ultrasound. LASSO regression was used for feature selection, logistic regression was employed to analyze risk factors, and a risk assessment nomogram was also developed.. The performance was evaluated using the area under the receiver operating characteristic curve (AUC), and the calibration was assessed through the Hosmer‒Lemeshow goodness-of-fit test. The study included a total of 828 subjects, with 558 in the normal group and 270 in the carotid plaque group. Thirty-three risk factors were included in the LASSO regression analysis as independent variables for screening. The results of the adjusted multiple logistic regression analysis show that age (OR = 6.81, 95% CI:4.371-10.758), unmarried marital status (OR = 3.475, 95% CI: 1.927-6.554), current smoking (OR = 2.318, 95% CI: 1.519-3.553), hypertension history (OR = 1.794, 95% CI: 1.123-2.860), dyslipidemia history (OR = 1.920, 95% CI: 1.149-3.215), systolic blood pressure (SBP) (OR = 1.014, 95% CI: 1.004-1.024), GLU (OR = 1.135, 95% CI: 1.017-1.272), and malondialdehyde (MDA) (OR = 1.014, 95% CI: 1.003-1.025) were associated with an increased risk of carotid plaques.In contrast, higher education levels were associated with a lower risk of carotid plaques, with education level (3) (OR = 0.436, 95% CI: 0.208-0.917) and education level (4) (OR = 0.348, 95% CI: 0.170-0.718) indicating a protective association. The constructed nomogram Risk assessment had an AUC of 0.850 (95% CI: 0.823-0.877) and demonstrated good calibration (χ2 = 13.973, P = 0.08246). By integrating age, education level, marital status, current smoking, hypertension history, dyslipidemia history, SBP, GLU and MDA, we developed a high-performance nomogram for assessment., which may be helpful for the early detection and prevention of carotid plaques in the general population. Further studies may be useful to validate the applicability in different regions and populations.

Predicting Vulnerability Status of Carotid Plaques Using CTA-Based Quantitative Analysis

ABSTRACT

The study aimed to develop a radiomics model to assess carotid artery plaque vulnerability using computed tomography angiography images. It retrospectively included 107 patients with carotid artery stenosis who underwent carotid artery stenting from 2017 to 2022. Patients were categorized into stable and vulnerable plaque groups based on pathology. A training group and a testing group were formed in a 7:3 ratio. Clinical data, including demographics and lipid profiles, were collected alongside pretreatment computed tomography angiography images. Radiomics features were extracted and reduced using the LASSO method to minimize redundancy. A radiomics model was then constructed, using 13 features with a minimum penalty coefficient logλ = 0.047. Significant differences were found between stable and vulnerable plaques in terms of stenosis degree. The radiomics model showed high accuracy (area under the curve of 0.959 in training and 0.942 in testing) for identifying vulnerable plaques. When combined with clinical parameters stenosis degree, the model's diagnostic efficacy improved further, with area under the curve values of 0.985 and 0.961 in the training and testing groups, respectively. Decision curve analysis indicated that the combined model offered superior clinical benefits for the clinical model and radiomics model alone. The study concludes that the combined radiomics model, incorporating stenosis degree, presents a promising tool for differentiating vulnerable from stable plaques.

Application of machine learning algorithms in predicting carotid artery plaques using routine health assessments

Background

Cardiovascular diseases (CVD) constitute a grave global health challenge, engendering significant socio-economic repercussions. Carotid artery plaques (CAP) are critical determinants of CVD risk, and proactive screening can substantially mitigate the frequency of cardiovascular incidents. However, the unequal distribution of medical resources precludes many patients from accessing carotid ultrasound diagnostics. Machine learning (ML) offers an effective screening alternative, delivering accurate predictions without the need for advanced diagnostic equipment. This study aimed to construct ML models that utilize routine health assessments and blood biomarkers to forecast the onset of CAP.

Methods

In this study, seven ML models, including LightGBM, LR, multi-layer perceptron (MLP), NBM, RF, SVM, and XGBoost, were used to construct the prediction model, and their performance in predicting the risk of CAP was compared. Data on health checkups and biochemical indicators were collected from 19,751 participants at the Beijing MJ Health Screening Center for model training and validation. Of these, 6,381 were diagnosed with CAP using carotid ultrasonography. In this study, 21 indicators were selected. The performance of the models was evaluated using the accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and area under the curve (AUC) value.

Results

Among the seven ML models, the light gradient boosting machine (LightGBM) had the highest AUC value (85.4%). Moreover, age, systolic blood pressure (SBP), gender, low-density lipoprotein cholesterol (LDL-C), and total cholesterol (CHOL) were the top five predictors of carotid plaque formation.

Conclusions

This study demonstrated the feasibility of predicting carotid plaque risk using ML algorithms. ML offers effective tools for improving public health monitoring and risk assessment, with the potential to improve primary care and community health by identifying high-risk individuals and enabling proactive healthcare measures and resource optimization.

Utilizing machine learning algorithms for the prediction of carotid artery plaques in a Chinese population

Background: Ischemic stroke is a significant global health issue, imposing substantial social and economic burdens. Carotid artery plaques (CAP) serve as an important risk factor for stroke, and early screening can effectively reduce stroke incidence. However, China lacks nationwide data on carotid artery plaques. Machine learning (ML) can offer an economically efficient screening method. This study aimed to develop ML models using routine health examinations and blood markers to predict the occurrence of carotid artery plaques. Methods: This study included data from 5,211 participants aged 18-70, encompassing health check-ups and biochemical indicators. Among them, 1,164 participants were diagnosed with carotid artery plaques through carotid ultrasound. We constructed six ML models by employing feature selection with elastic net regression, selecting 13 indicators. Model performance was evaluated using accuracy, sensitivity, specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV), F1 score, kappa value, and Area Under the Curve (AUC) value. Feature importance was assessed by calculating the root mean square error (RMSE) loss after permutations for each variable in every model. Results: Among all six ML models, LightGBM achieved the highest accuracy at 91.8%. Feature importance analysis revealed that age, Low-Density Lipoprotein Cholesterol (LDL-c), and systolic blood pressure were important predictive factors in the models. Conclusion: LightGBM can effectively predict the occurrence of carotid artery plaques using demographic information, physical examination data and biochemistry data.

Machine learning models for predicting the risk factor of carotid plaque in cardiovascular disease

Introduction

Cardiovascular disease (CVD) is a group of diseases involving the heart or blood vessels and represents a leading cause of death and disability worldwide. Carotid plaque is an important risk factor for CVD that can reflect the severity of atherosclerosis. Accordingly, developing a prediction model for carotid plaque formation is essential to assist in the early prevention and management of CVD.

Methods

In this study, eight machine learning algorithms were established, and their performance in predicting carotid plaque risk was compared. Physical examination data were collected from 4,659 patients and used for model training and validation. The eight predictive models based on machine learning algorithms were optimized using the above dataset and 10-fold cross-validation. The Shapley Additive Explanations (SHAP) tool was used to compute and visualize feature importance. Then, the performance of the models was evaluated according to the area under the receiver operating characteristic curve (AUC), feature importance, accuracy and specificity.

Results

The experimental results indicated that the XGBoost algorithm outperformed the other machine learning algorithms, with an AUC, accuracy and specificity of 0.808, 0.749 and 0.762, respectively. Moreover, age, smoke, alcohol drink and BMI were the top four predictors of carotid plaque formation. It is feasible to predict carotid plaque risk using machine learning algorithms.

Conclusions

This study indicates that our models can be applied to routine chronic disease management procedures to enable more preemptive, broad-based screening for carotid plaque and improve the prognosis of CVD patients.

Combinatorial Use of Machine Learning and Logistic Regression for Predicting Carotid Plaque Risk Among 5.4 Million Adults With Fatty Liver Disease Receiving Health Check-Ups: Population-Based Cross-Sectional Study

BACKGROUND

Carotid plaque can progress into stroke, myocardial infarction, etc, which are major global causes of death. Evidence shows a significant increase in carotid plaque incidence among patients with fatty liver disease. However, unlike the high detection rate of fatty liver disease, screening for carotid plaque in the asymptomatic population is not yet prevalent due to cost-effectiveness reasons, resulting in a large number of patients with undetected carotid plaques, especially among those with fatty liver disease.

OBJECTIVE

This study aimed to combine the advantages of machine learning (ML) and logistic regression to develop a straightforward prediction model among the population with fatty liver disease to identify individuals at risk of carotid plaque.

METHODS

Our study included 5,420,640 participants with fatty liver from Meinian Health Care Center. We used random forest, elastic net (EN), and extreme gradient boosting ML algorithms to select important features from potential predictors. Features acknowledged by all 3 models were enrolled in logistic regression analysis to develop a carotid plaque prediction model. Model performance was evaluated based on the area under the receiver operating characteristic curve, calibration curve, Brier score, and decision curve analysis both in a randomly split internal validation data set, and an external validation data set comprising 32,682 participants from MJ Health Check-up Center. Risk cutoff points for carotid plaque were determined based on the Youden index, predicted probability distribution, and prevalence rate of the internal validation data set to classify participants into high-, intermediate-, and low-risk groups. This risk classification was further validated in the external validation data set.

RESULTS

Among the participants, 26.23% (1,421,970/5,420,640) were diagnosed with carotid plaque in the development data set, and 21.64% (7074/32,682) were diagnosed in the external validation data set. A total of 6 features, including age, systolic blood pressure, low-density lipoprotein cholesterol (LDL-C), total cholesterol, fasting blood glucose, and hepatic steatosis index (HSI) were collectively selected by all 3 ML models out of 27 predictors. After eliminating the issue of collinearity between features, the logistic regression model established with the 5 independent predictors reached an area under the curve of 0.831 in the internal validation data set and 0.801 in the external validation data set, and showed good calibration capability graphically. Its predictive performance was comprehensively competitive compared with the single use of either logistic regression or ML algorithms. Optimal predicted probability cutoff points of 25% and 65% were determined for classifying individuals into low-, intermediate-, and high-risk categories for carotid plaque.

CONCLUSIONS

The combination of ML and logistic regression yielded a practical carotid plaque prediction model, and was of great public health implications in the early identification and risk assessment of carotid plaque among individuals with fatty liver.

Machine Learning and the Conundrum of Stroke Risk Prediction

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.

Early Diagnosis of Intracranial Internal Carotid Artery Stenosis Using Extracranial Hemodynamic Indices from Carotid Doppler Ultrasound

Atherosclerotic intracranial internal carotid artery stenosis (IICAS) is a leading cause of strokes. Due to the limitations of major cerebral imaging techniques, the early diagnosis of IICAS remains challenging. Clinical studies have revealed that arterial stenosis may have complicated effects on the blood flow’s velocity from a distance. Therefore, based on a patient-specific one-dimensional hemodynamic model, we quantitatively investigated the effects of IICAS on extracranial internal carotid artery (ICA) flow velocity waveforms to identify sensitive hemodynamic indices for IICAS diagnoses. Classical hemodynamic indices, including the peak systolic velocity (PSV), end-diastolic velocity (EDV), and resistive index (RI), were calculated on the basis of simulations with and without IICAS. In addition, the first harmonic ratio (FHR), which is defined as the ratio between the first harmonic amplitude and the sum of the amplitudes of the 1st−20th order harmonics, was proposed to evaluate flow waveform patterns. To investigate the diagnostic performance of the indices, we included 52 patients with mild-to-moderate IICAS (<70%) in a case−control study and considered 24 patients without stenosis as controls. The simulation analyses revealed that the existence of IICAS dramatically increased the FHR and decreased the PSV and EDV in the same patient. Statistical analyses showed that the average PSV, EDV, and RI were lower in the stenosis group than in the control group; however, there were no significant differences (p > 0.05) between the two groups, except for the PSV of the right ICA (p = 0.011). The FHR was significantly higher in the stenosis group than in the control group (p < 0.001), with superior diagnostic performance. Taken together, the FHR is a promising index for the early diagnosis of IICAS using carotid Doppler ultrasound methods.