Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry

Plasma circulating cell-free DNA integrity and relative telomere length as diagnostic biomarkers for Parkinson's disease and multiple system atrophy: a cross-sectional study

JOURNAL/nrgr/04.03/01300535-202512000-00025/figure1/v/2025-01-31T122243Z/r/image-tiff In clinical specialties focusing on neurological disorders, there is a need for comprehensive and integrated non-invasive, sensitive, and specific testing methods. Both Parkinson's disease and multiple system atrophy are classified as α-synucleinopathies, characterized by abnormal accumulation of α-synuclein protein, which provides a shared pathological background for their comparative study. In addition, both Parkinson's disease and multiple system atrophy involve neuronal death, a process that may release circulating cell-free DNA (cfDNA) into the bloodstream, leading to specific alterations. This premise formed the basis for investigating cell-free DNA as a potential biomarker. Cell-free DNA has garnered attention for its potential pathological significance, yet its characteristics in the context of Parkinson's disease and multiple system atrophy are not fully understood. This study investigated the total concentration, nonapoptotic level, integrity, and cell-free DNA relative telomere length of cell-free DNA in the peripheral blood of 171 participants, comprising 76 normal controls, 62 patients with Parkinson's disease, and 33 patients with multiple system atrophy. In our cohort, 75.8% of patients with Parkinson's disease (stage 1-2 of Hoehn & Yahr) and 60.6% of patients with multiple system atrophy (disease duration less than 3 years) were in the early stages. The diagnostic potential of the cell-free DNA parameters was evaluated using receiver operating characteristic (ROC) analysis, and their association with disease prevalence was examined through logistic regression models, adjusting for confounders such as age, sex, body mass index, and education level. The results showed that cell-free DNA integrity was significantly elevated in both Parkinson's disease and multiple system atrophy patients compared with normal controls ( P < 0.001 for both groups), whereas cell-free DNA relative telomere length was markedly shorter ( P = 0.003 for Parkinson's disease and P = 0.010 for multiple system atrophy). Receiver operating characteristic analysis indicated that both cell-free DNA integrity and cell-free DNA relative telomere length possessed good diagnostic accuracy for differentiating Parkinson's disease and multiple system atrophy from normal controls. Specifically, higher cell-free DNA integrity was associated with increased risk of Parkinson's disease (odds ratio [OR]: 5.72; 95% confidence interval [CI]: 1.54-24.19) and multiple system atrophy (OR: 10.10; 95% CI: 1.55-122.98). Conversely, longer cell-free DNA relative telomere length was linked to reduced risk of Parkinson's disease (OR: 0.16; 95% CI: 0.04-0.54) and multiple system atrophy (OR: 0.10; 95% CI: 0.01-0.57). These findings suggest that cell-free DNA integrity and cell-free DNA relative telomere length may serve as promising biomarkers for the early diagnosis of Parkinson's disease and multiple system atrophy, potentially reflecting specific underlying pathophysiological processes of these neurodegenerative disorders.

Prediction of obstructive coronary artery disease using coronary calcification and epicardial adipose tissue assessments from CT calcium scoring scans

BACKGROUND

Low-cost/no-cost non-contrast CT calcium scoring (CTCS) exams can provide direct evidence of coronary atherosclerosis. In this study, using features from CTCS images, we developed a novel machine learning model to predict obstructive coronary artery disease (CAD), as defined by the coronary artery disease-reporting and data system (CAD-RADS).

METHODS

This study analyzed 1324 patients from the SCOT-HEART trial who underwent both CTCS and CT angiography. Obstructive CAD was defined as CAD-RADS 4A-5, while CAD-RADS 0-3 were considered non-obstructive CAD. We analyzed clinical, Agatston-score-derived, and epicardial fat-omics features to predict obstructive CAD. The most predictive features were selected using elastic net logistic regression and used to train a CatBoost model. Model performance was evaluated using 1000 repeated five-fold cross-validation and survival analyses to predict major adverse cardiovascular event (MACE) and revascularization. Generalizability was assessed using an external validation set of 2316 patients for survival predictions.

RESULTS

Among the 1324 patients, obstructive CAD was identified in 334 patients (25.2 ​%). Elastic net regression identified the top 14 features (5 clinical, 2 Agatston-score-derived, and 7 fat-omics). The proposed method achieved excellent performance for classifying obstructive CAD, with an AUC of 90.1 ​± ​0.9 ​% and sensitivity/specificity/accuracy of 83.5 ​± ​5.5 ​%/93.7 ​± ​1.9 ​%/82.4 ​± ​2.0 ​%. The inclusion of Agatston-score-derived and fat-omics features significantly improved classification performance. Survival analyses showed that both actual and predicted obstructive CAD significantly differentiated patients who experienced MACE and revascularization.

CONCLUSIONS

We developed a novel machine learning model to predict obstructive CAD from non-contrast CTCS scans. Our findings highlight the potential clinical benefits of CTCS imaging in identifying patients likely to benefit from advanced imaging.

Development, validation, and clinical application of a machine learning model for risk stratification and management of cervical cancer screening based on full-genotyping hrHPV test (SMART-HPV): a modelling study

Background

High-risk human papillomavirus (hrHPV) full genotyping facilitates risk stratification and efficiency in cervical cancer screening, widely verified and adopted in various screening settings. We aimed develop a cervical cancer predictive model that can guide referrals for colposcopy using hrHPV full genotyping data in a setting where screening rate is low.

Methods

We developed, compared and validated four machine learning models (eXtreme gradient boosting [XGBoost], support vector machine [SVM], random forest [RF], and naïve bayes [NB]) for cervical cancer prediction, using data from a national cervical cancer screening project conducted in 267 healthcare centers in China. Cervical intraepithelial neoplasia grade 2 or worse (CIN2+) and CIN3+ were the primary and secondary outcomes. In various screening settings across China, the performance of discrimination was evaluated using area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, area under the precision-recall curve (AUPRC), and accuracy. Calibration and clinical utility were assessed with brier score, calibration curve and decision curve analysis (DCA).

Findings

1,112,846 women were recruited, of whom 599,043 were included in the analysis based on hrHPV full genotyping. Of these, 254,434 (age [years, median, IQR]: 48, 42-54), 297,479 (49, 43-55), 38,500 (37, 32-44), 1950 (38, 33-46), 1590 (53, 47-58), 779 (38, 31-49) and 4311 (40, 33-50) were in the development, temporal validation and external validation 1-5 datasets, respectively. The final simplified clinical risk prediction model includes hrHPV, number of HPV genotypes, cervical cytology, HPV16, HPV18, age, HPV52, HPV39 and gynecological examination. The final optimal XGBoost model for predicting CIN2+ showed good discrimination (AUROC, maximum 0.989 [0.987-0.992]; minimum 0.781 [0.74-0.819]), and calibration (brier score, maximum 0.118 [0.099-0.137]) in the five external validation sets. DCA showed that when the clinical decision threshold probability for optimal XGBoost model was less than 0.80, the model for predicting CIN2+ provided a superior standardized net benefit. The optimal XGBoost model obtained similar results in predicting CIN3+.

Interpretation

We developed a cervical cancer screening risk prediction model that employs hrHPV full genotyping and simple test results to achieve risk prediction and stratified management for colposcopy referrals. This predictive tool is particularly suitable for settings with low screening rates.

Funding

National Natural Science Foundation of China; Major Scientific Research Program for Young and Middle-aged Health Professionals of Fujian Province, China; Fujian Province Central Government-Guided Local Science and Technology Development Project; Fujian Province's Third Batch of Flexible Introduction of High-Level Medical Talent Teams; Fujian Provincial Natural Science Foundation of China; Fujian Provincial Science and Technology Innovation Joint Fund.

Development of a recommendation system and data analysis in personalized medicine: an approach towards healthy vascular ageing

Purpose

Understanding early vascular ageing has become crucial for preventing adverse cardiovascular events. To this respect, recent AI-based risk clustering models offer early detection strategies focused on healthy populations, yet their complexity limits clinical use. This work introduces a novel recommendation system embedded in a web app to assess and mitigate early vascular ageing risk, leading patients towards improved cardiovascular health.

Methods

This system employs a methodology that calculates distances within multidimensional spaces and integrates cost functions to obtain personalized optimisation of recommendations. It also incorporates a classification system for determining the intensity levels of the clinical interventions.

Results

The recommendation system showed high efficiency in identifying and visualizing individuals at high risk of early vascular ageing among healthy patients. Additionally, the system corroborated its consistency and reliability in generating personalized recommendations among different levels of granularity, emphasizing its focus on moderate or low-intensity recommendations, which could improve patient adherence to the intervention.

Conclusion

This tool might significantly aid healthcare professionals in their daily analysis, improving the prevention and management of cardiovascular diseases.

Personalized risk prediction of mortality and rehospitalization for heart failure in patients undergoing mitral valve repair surgery

Background

Accurately assessing the postoperative mortality and rehospitalization for heart failure risks in patients undergoing mitral valve repair surgery is of significant importance for individualized medical strategies.

Objective

We sought to develop and validate a risk assessment system for the prediction of mortality and rehospitalization for heart failure.

Methods

Personalized risk prediction system of mortality and rehospitalization for heart failure was developed. For developing a prediction system with death as the outcome, there were 965 patients (70%) and 413 patients (30%) were included in the the derivation cohort and the validation cohort. For developing a prediction system with rehospitalization for heart failure as the outcome, there were 927 patients (70%) and 398 patients (30%) were included in the derivation cohort and the validation cohort. There were 42 routine clinical variables used to develop the models. The performance evaluation of the model is based on the area under the curve (AUC). Evaluate the improvement with Euro Score II according to NRI and IDI net reclassification improvement (NRI) and integrated discrimination improvement (IDI).

Results

The median follow-up time was 685 days, the incidence of death was 3.85% (n = 53), and the incidence of rehospitalization for heart failure was 10.01% (n = 138). The AUC values of the mortality prediction model in the derivation and validation cohorts were 0.825 (0.764-0.886) and 0.808 (0.699-0.917), respectively. The AUC values of the rehospitalization for heart failure prediction model in the derivation and validation cohorts were 0.794 (0.756-0.832) and 0.812 (0.758-0.866), respectively. NRI and IDI showed that the mortality prediction model exhibited superior performance than the Euro Score II. The mortality and rehospitalization for heart failure risk prediction models effectively stratified patients into different risk subgroups.

Conclusion

The developed and validated models exhibit satisfactory performance in prediction of all-cause mortality and rehospitalization for heart failure after mitral valve repair surgery.

Clinical Trial Registration

http://www.clinicaltrials.gov, Unique identifier: (NCT05141292).

Between Two Worlds: Investigating the Intersection of Human Expertise and Machine Learning in the Case of Coronary Artery Disease Diagnosis

Coronary artery disease (CAD) presents a significant global health burden, with early and accurate diagnostics crucial for effective management and treatment strategies. This study evaluates the efficacy of human evaluators compared to a Random Forest (RF) machine learning model in predicting CAD risk. It investigates the impact of incorporating human clinical judgments into the RF model's predictive capabilities. We recruited 606 patients from the Department of Nuclear Medicine at the University Hospital of Patras, Greece, from 16 February 2018 to 28 February 2022. Clinical data inputs included age, sex, comprehensive cardiovascular history (including prior myocardial infarction and revascularisation), CAD predisposing factors (such as hypertension, dyslipidemia, smoking, diabetes, and peripheral arteriopathy), baseline ECG abnormalities, and symptomatic descriptions ranging from asymptomatic states to angina-like symptoms and dyspnea on exertion. The diagnostic accuracies of human evaluators and the RF model (when trained with datasets inclusive of human judges' assessments) were comparable at 79% and 80.17%, respectively. However, the performance of the RF model notably declined to 73.76% when human clinical judgments were excluded from its training dataset. These results highlight a potential synergistic relationship between human expertise and advanced algorithmic predictions, suggesting a hybrid approach as a promising direction for enhancing CAD diagnostics.

The predictive value of coronary artery calcium score combined with traditional risk factors for obstructive coronary heart disease in young people

OBJECTIVES

This study attempts to compare the predictive effects of several prediction models on obstructive coronary artery disease (OCAD) in young patients (30-50 years old), with a view to providing a new evaluation tool for the prediction of premature coronary artery disease (PCAD).

METHODS

A total of 532 hospitalized patients aged 30-50 were included in the study.All of them underwent coronary computed tomography angiography (CCTA) for suspected symptoms of coronary heart disease.Coronary artery calcium score (CACS) combined with traditional risk factors and pre-test probability models are the prediction models to be compared in this study.The PTP model was selected from the upgraded Diamond-Forrester model (UDFM) and the Duke clinical score (DCS).

RESULTS

All patients included in the study were aged 30-50 years. Among them, women accounted for 24.4%, and 355 patients (66.7%) had a CACS of 0. OCAD was diagnosed in 43 patients (8.1%). The CACS combined with traditional risk factors to predict the OCAD area under the curve of receiver operating characteristic (ROC) (AUC = 0.794,p < 0.001) was greater than the PTP models (AUCUDFM=0.6977,p < 0.001;AUCDCS=0.6214,p < 0.001). By calculating the net reclassification index (NRI) and the integrated discrimination index (IDI), the ability to predict the risk of OCAD using the CACS combined with traditional risk factors was improved compared with the PTP models (NRI&IDI > 0,p < 0.05).

CONCLUSION

The predictive value of CACS combined with traditional risk factors for OCAD in young patients is better than the PTP models.

Use machine learning models to identify and assess risk factors for coronary artery disease

Accurate prediction of coronary artery disease (CAD) is crucial for enabling early clinical diagnosis and tailoring personalized treatment options. This study attempts to construct a machine learning (ML) model for predicting CAD risk and further elucidate the complex nonlinear interactions between the disease and its risk factors. Employing the Z-Alizadeh Sani dataset, which includes records of 303 patients, univariate analysis and the Boruta algorithm were applied for feature selection, and nine different ML techniques were subsequently deployed to produce predictive models. To elucidate the intricate pathogenesis of CAD, this study harnessed the analytical capabilities of Shapley values, alongside the use of generalized additive models for curve fitting, to probe into the nonlinear interactions between the disease and its associated risk factors. Furthermore, we implemented a piecewise linear regression model to precisely pinpoint inflection points within these complex nonlinear dynamics. The findings of this investigation reveal that logistic regression (LR) stands out as the preeminent predictive model, demonstrating remarkable efficacy, it achieved an Area Under the Receiver Operating Characteristic curve (AUROC) of 0.981 (95% CI: 0.952-1), and an Area Under the Precision-Recall Curve (AUPRC) of 0.993. The utilization of the 14 most pivotal features in constructing a dynamic nomogram. Analysis of the Shapley smoothing curves uncovered distinctive "S"-shaped and "C"-shaped relationships linking age and triglycerides to CAD, respectively. In summary, machine learning models could provide valuable insights for the early diagnosis of CAD. The SHAP method may provide a personalized risk assessment of the relationship between CAD and its risk factors.

Development and validation of machine learning models for predicting HER2-zero and HER2-low breast cancers

OBJECTIVES

To develop and validate machine learning models for human epidermal growth factor receptor 2 (HER2)-zero and HER2-low using MRI features pre-neoadjuvant therapy (NAT).

METHODS

Five hundred and sixteen breast cancer patients post-NAT surgery were randomly divided into training (n = 362) and internal validation sets (n = 154) for model building and evaluation. MRI features (tumour diameter, enhancement type, background parenchymal enhancement, enhancement pattern, percentage of enhancement, signal enhancement ratio, breast oedema, and apparent diffusion coefficient) were reviewed. Logistic regression (LR), support vector machine (SVM), k-nearest neighbour (KNN), and extreme gradient boosting (XGBoost) models utilized MRI characteristics for HER2 status assessment in training and validation datasets. The best-performing model generated a HER2 score, which was subsequently correlated with pathological complete response (pCR) and disease-free survival (DFS).

RESULTS

The XGBoost model outperformed LR, SVM, and KNN, achieving an area under the receiver operating characteristic curve (AUC) of 0.783 (95% CI, 0.733-0.833) and 0.787 (95% CI, 0.709-0.865) in the validation dataset. Its HER2 score for predicting pCR had an AUC of 0.708 in the training datasets and 0.695 in the validation dataset. Additionally, the low HER2 score was significantly associated with shorter DFS in the validation dataset (hazard ratio: 2.748, 95% CI, 1.016-7.432, P = .037).

CONCLUSIONS

The XGBoost model could help distinguish HER2-zero and HER2-low breast cancers and has the potential to predict pCR and prognosis in breast cancer patients undergoing NAT.

ADVANCES IN KNOWLEDGE

HER2-low-expressing breast cancer can benefit from the HER2-targeted therapy. Prediction of HER2-low expression is crucial for appropriate management. MRI features offer a solution to this clinical issue.

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events

BACKGROUND

The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters.

OBJECTIVES

This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM.

METHODS

A total of 758 patients with HCM (67% male; age 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke.

RESULTS

MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS).

CONCLUSIONS

ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

A Machine Learning Model for Predicting In-Hospital Mortality in Chinese Patients With ST-Segment Elevation Myocardial Infarction: Findings From the China Myocardial Infarction Registry

BACKGROUND

Machine learning (ML) risk prediction models, although much more accurate than traditional statistical methods, are inconvenient to use in clinical practice due to their nontransparency and requirement of a large number of input variables.

OBJECTIVE

We aimed to develop a precise, explainable, and flexible ML model to predict the risk of in-hospital mortality in patients with ST-segment elevation myocardial infarction (STEMI).

METHODS

This study recruited 18,744 patients enrolled in the 2013 China Acute Myocardial Infarction (CAMI) registry and 12,018 patients from the China Patient-Centered Evaluative Assessment of Cardiac Events (PEACE)-Retrospective Acute Myocardial Infarction Study. The Extreme Gradient Boosting (XGBoost) model was derived from 9616 patients in the CAMI registry (2014, 89 variables) with 5-fold cross-validation and validated on both the 9125 patients in the CAMI registry (89 variables) and the independent China PEACE cohort (10 variables). The Shapley Additive Explanations (SHAP) approach was employed to interpret the complex relationships embedded in the proposed model.

RESULTS

In the XGBoost model for predicting all-cause in-hospital mortality, the variables with the top 8 most important scores were age, left ventricular ejection fraction, Killip class, heart rate, creatinine, blood glucose, white blood cell count, and use of angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs). The area under the curve (AUC) on the CAMI validation set was 0.896 (95% CI 0.884-0.909), significantly higher than the previous models. The AUC for the Global Registry of Acute Coronary Events (GRACE) model was 0.809 (95% CI 0.790-0.828), and for the TIMI model, it was 0.782 (95% CI 0.763-0.800). Despite the China PEACE validation set only having 10 available variables, the AUC reached 0.840 (0.829-0.852), showing a substantial improvement to the GRACE (0.762, 95% CI 0.748-0.776) and TIMI (0.789, 95% CI 0.776-0.803) scores. Several novel and nonlinear relationships were discovered between patients' characteristics and in-hospital mortality, including a U-shape pattern of high-density lipoprotein cholesterol (HDL-C).

CONCLUSIONS

The proposed ML risk prediction model was highly accurate in predicting in-hospital mortality. Its flexible and explainable characteristics make the model convenient to use in clinical practice and could help guide patient management.

TRIAL REGISTRATION

ClinicalTrials.gov NCT01874691; https://clinicaltrials.gov/study/NCT01874691.

Evaluating the American Heart Association/American College of Cardiology Guideline-Recommended and Contemporary Pretest Probability Models in a Mixed Asian Cohort: The Contribution of Coronary Artery Calcium

BACKGROUND

Most pretest probability (PTP) tools for obstructive coronary artery disease (CAD) were Western -developed. The most appropriate PTP models and the contribution of coronary artery calcium score (CACS) in Asian populations remain unknown. In a mixed Asian cohort, we compare 5 PTP models: local assessment of the heart (LAH), CAD Consortium (CAD2), risk factor-weighted clinical likelihood, the American Heart Association/American College of Cardiology and the European Society of Cardiology PTP and 3 extended versions of these models that incorporated CACS: LAH(CACS), CAD2(CACS), and the CACS-clinical likelihood.

METHODS AND RESULTS

The study cohort included 771 patients referred for stable chest pain. Obstructive CAD prevalence was 27.5%. Calibration, area under the receiver-operating characteristic curves (AUC) and net reclassification index were evaluated. LAH clinical had the best calibration (χ2 5.8; P=0.12). For CACS models, LAH(CACS) showed least deviation between observed and expected cases (χ2 37.5; P<0.001). There was no difference in AUCs between the LAH clinical (AUC, 0.73 [95% CI, 0.69-0.77]), CAD2 clinical (AUC, 0.72 [95% CI, 0.68-0.76]), risk factor-weighted clinical likelihood (AUC, 0.73 [95% CI: 0.69-0.76) and European Society of Cardiology PTP (AUC, 0.71 [95% CI, 0.67-0.75]). CACS improved discrimination and reclassification of the LAH(CACS) (AUC, 0.88; net reclassification index, 0.46), CAD2(CACS) (AUC, 0.87; net reclassification index, 0.29) and CACS-CL (AUC, 0.87; net reclassification index, 0.25).

CONCLUSIONS

In a mixed Asian cohort, Asian-derived LAH models had similar discriminatory performance but better calibration and risk categorization for clinically relevant PTP cutoffs. Incorporating CACS improved discrimination and reclassification. These results support the use of population-matched, CACS-inclusive PTP tools for the prediction of obstructive CAD.

Construction and Validation of a Predictive Model for Coronary Artery Disease Using Extreme Gradient Boosting

Purpose

Early recognition of coronary artery disease (CAD) could delay its progress and significantly reduce mortality. Sensitive, specific, cost-efficient and non-invasive indicators for assessing individual CAD risk in community population screening are urgently needed.

Patients and Methods

3112 patients with CAD and 3182 controls were recruited from three clinical centers in China, and differences in baseline and clinical characteristics were compared. For the discovery cohort, the least absolute shrinkage and selection operator (LASSO) regression was used to identify significant features and four machine learning algorithms (logistic regression, support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost)) were applied to construct models for CAD risk assessment, the receiver operating characteristics (ROC) curve and precision-recall (PR) curve were conducted to evaluate their predictive accuracy. The optimal model was interpreted by Shapley additive explanations (SHAP) analysis and assessed by the ROC curve, calibration curve, and decision curve analysis (DCA) and validated by two external cohorts.

Results

Using LASSO filtration, all included variables were considered to be statistically significant. Four machine learning models were constructed based on these features and the results of ROC and PR curve implied that the XGBoost model exhibited the highest predictive performance, which yielded a high area of ROC curve (AUC) of 0.988 (95% CI: 0.986-0.991) to distinguish CAD patients from controls with a sensitivity of 94.6% and a specificity of 94.6%. The calibration curve showed that the predicted results were in good agreement with actual observations, and DCA exhibited a better net benefit across a wide range of threshold probabilities. External validation of the model also exhibited favorable discriminatory performance, with an AUC, sensitivity, and specificity of 0.953 (95% CI: 0.945-0.960), 89.9%, and 87.1% in the validation cohort, and 0.935 (95% CI: 0.915-0.955), 82.0%, and 90.3% in the replication cohort.

Conclusion

Our model is highly informative for clinical practice and will be conducive to primary prevention and tailoring the precise management for CAD patients.

Radiomics analysis of lesion-specific pericoronary adipose tissue to predict major adverse cardiovascular events in coronary artery disease

OBJECTIVE

To investigate the prognostic performance of radiomics analysis of lesion-specific pericoronary adipose tissue (PCAT) for major adverse cardiovascular events (MACE) with the guidance of CT derived fractional flow reserve (CT-FFR) in coronary artery disease (CAD).

MATERIALS AND METHODS

The study retrospectively analyzed 608 CAD patients who underwent coronary CT angiography. Lesion-specific PCAT was determined by the lowest CT-FFR value and 1691 radiomic features were extracted. MACE included cardiovascular death, nonfatal myocardial infarction, unplanned revascularization and hospitalization for unstable angina. Four models were generated, incorporating traditional risk factors (clinical model), radiomics score (Rad-score, radiomics model), traditional risk factors and Rad-score (clinical radiomics model) and all together (combined model). The model performances were evaluated and compared with Harrell concordance index (C-index), area under curve (AUC) of the receiver operator characteristic.

RESULTS

Lesion-specific Rad-score was associated with MACE (adjusted HR = 1.330, p = 0.009). The combined model yielded the highest C-index of 0.718, which was higher than clinical model (C-index = 0.639), radiomics model (C-index = 0.653) and clinical radiomics model (C-index = 0.698) (all p < 0.05). The clinical radiomics model had significant higher C-index than clinical model (p = 0.030). There were no significant differences in C-index between clinical or clinical radiomics model and radiomics model (p values were 0.796 and 0.147 respectively). The AUC increased from 0.674 for clinical model to 0.721 for radiomics model, 0.759 for clinical radiomics model and 0.773 for combined model.

CONCLUSION

Radiomics analysis of lesion-specific PCAT is useful in predicting MACE. Combination of lesion-specific Rad-score and CT-FFR shows incremental value over traditional risk factors.

Machine Learning Model in Obesity to Predict Weight Loss One Year after Bariatric Surgery: A Pilot Study

Roux-en-Y gastric bypass (RYGB) is a treatment for severe obesity. However, many patients have insufficient total weight loss (TWL) after RYGB. Although multiple factors have been involved, their influence is incompletely known. The aim of this exploratory study was to evaluate the feasibility and reliability of the use of machine learning (ML) techniques to estimate the success in weight loss after RYGP, based on clinical, anthropometric and biochemical data, in order to identify morbidly obese patients with poor weight responses. We retrospectively analyzed 118 patients, who underwent RYGB at the Hospital Clínico Universitario of Valencia (Spain) between 2013 and 2017. We applied a ML approach using local linear embedding (LLE) as a tool for the evaluation and classification of the main parameters in conjunction with evolutionary algorithms for the optimization and adjustment of the parameter model. The variables associated with one-year postoperative %TWL were obstructive sleep apnea, osteoarthritis, insulin treatment, preoperative weight, insulin resistance index, apolipoprotein A, uric acid, complement component 3, and vitamin B12. The model correctly classified 71.4% of subjects with TWL < 30% although 36.4% with TWL ≥ 30% were incorrectly classified as "unsuccessful procedures". The ML-model processed moderate discriminatory precision in the validation set. Thus, in severe obesity, ML-models can be useful to assist in the selection of patients before bariatric surgery.

Deep learning-based prediction of coronary artery calcium scoring in hemodialysis patients using radial artery calcification

OBJECTIVE

This study used random forest model to explore the feasibility of radial artery calcification in prediction of coronary artery calcification in hemodialysis patients.

MATERIAL AND METHODS

We enrolled hemodialysis patients and performed ultrasound examinations on their radial arteries to evaluate the calcification status using a calcification index. All involved patients received coronary artery computed tomography scans to generate coronary artery calcification scores (CACS). Clinical variables were collected from all patients. We constructed both a random forest model and a logistic regression model to predict CACS. Logistic regression model was used to identify the risk factors of radial artery calcification.

RESULTS

One hundred eighteen patients were included in our analysis. In random forest model, the radial artery calcification index, age, serum C-reactive protein, body mass index (BMI), diabetes, and hypertension history were related to CACS based on the average decrease of the Gini coefficient. The random forest model achieved a sensitivity of 76.9%, specificity of 75.0%, and area under receiver operating characteristic of 0.869, while the logistic regression model achieved a sensitivity of 75.2%, specificity of 68.7%, and area under receiver operating characteristic of 0.742 in prediction of CACS. Sex, BMI index, smoking history, hypertension history, diabetes history, and serum total calcium were all the risk factors related to radial artery calcification.

CONCLUSIONS

A random forest model based on radial artery calcification could be used to predict CACS in hemodialysis patients, providing a potential method for rapid screening and prediction of coronary artery calcification.

Artificial Intelligence in Cardiology and Atherosclerosis in the Context of Precision Medicine: A Scoping Review

Cardiovascular diseases remain the main cause of death worldwide which makes it essential to better understand, diagnose, and treat atherosclerosis. Artificial intelligence (AI) and novel technological solutions offer us new possibilities and enable the practice of individually tailored medicine. The study was performed using the PRISMA protocol. As of January 10, 2023, the analysis has been based on a review of 457 identified articles in PubMed and MEDLINE databases. The search covered reviews, original articles, meta-analyses, comments, and editorials published in the years 2009-2023. In total, 123 articles met inclusion criteria. The results were divided into the subsections presented in the review (genome-wide association studies, radiomics, and other studies). This paper presents actual knowledge concerning atherosclerosis, in silico, and big data analyses in cardiology that affect the way medicine is practiced in order to create an individual approach and adjust the therapy of atherosclerosis.

Deep learning-based coronary artery calcium score to predict coronary artery disease in type 2 diabetes mellitus

Background

Coronary artery disease (CAD) in type 2 diabetes mellitus (T2DM) patients often presents diffuse lesions, with extensive calcification, and it is time-consuming to measure coronary artery calcium score (CACS).

Objectives

To explore the predictive ability of deep learning (DL)-based CACS for obstructive CAD and hemodynamically significant CAD in T2DM.

Methods

469 T2DM patients suspected of CAD who accepted CACS scan and coronary CT angiography between January 2013 and December 2020 were enrolled. Obstructive CAD was defined as diameter stenosis ≥50%. Hemodynamically significant CAD was defined as CT-derived fractional flow reserve ≤0.8. CACS was calculated with a fully automated method based on DL algorithm. Logistic regression was applied to determine the independent predictors. The predictive performance was evaluated with area under receiver operating characteristic curve (AUC).

Results

DL-CACS (adjusted odds ratio (OR): 1.005; 95% CI: 1.003-1.006; P ＜ 0.001) was significantly associated with obstructive CAD. DL-CACS (adjusted OR:1.003; 95% CI: 1.002-1.004; P ＜ 0.001) was also an independent predictor for hemodynamically significant CAD. The AUCs, sensitivities, specificities, positive predictive values and negative predictive values of DL-CACS for obstructive CAD and hemodynamically significant CAD were 0.753 (95% CI: 0.712-0.792), 75.9%, 66.5%, 74.8%, 67.8% and 0.769 (95% CI: 0.728-0.806), 80.7%, 62.1%, 59.6% and 82.3% respectively. It took 1.17 min to perform automated measurement of DL-CACS in total, which was significantly less than manual measurement of 1.73 min (P ＜ 0.001).

Conclusions

DL-CACS, with less time-consuming, can accurately and effectively predict obstructive CAD and hemodynamically significant CAD in T2DM.

Machine learning models using symptoms and clinical variables to predict coronary artery disease on coronary angiography

Introduction

Coronary angiography (CAG) is invasive and expensive, while numbers of patients suspected of coronary artery disease (CAD) undergoing CAG results have no coronary lesions.

Aim

To develop machine learning algorithms using symptoms and clinical variables to predict CAD.

Material and methods

This study was conducted as a cross-sectional study of patients undergoing CAG. We randomly chose 2082 patients from 2602 patients suspected of CAD as the training set, and 520 patients as the test set. We utilized LASSO regression to do feature selection. The area under the receiver operating characteristic curve (AUC), confusion matrix of different thresholds, positive predictive value (PPV) and negative predictive value (NPV) were shown. Support vector machine algorithm performances in 10 folds were conducted in the training set for detecting severe CAD, while XGBoost algorithm performances were conducted in the test set for detecting severe CAD.

Results

The algorithm of logistic regression achieved an average AUC of 0.77 in the training set during 10-fold validation and an AUC of 0.75 in the test set. When probability predicted by the model was less than 0.1, 11 patients in the test set (520 patients) were screened out, and NPV reached 90.9%. When probability predicted by the model was less than 0.2, 110 patients in the test set were screened out, and reached 83.6%. Meanwhile, when threshold was set to 0.9, PPV reached 97.4%. When the threshold was set to 0.8, PPV reached 91.5%.

Conclusions

Machine learning algorithm using data from hospital information systems could assist in severe CAD exclusion and confirmation, and thus help patients avoid unnecessary CAG.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

Artificial intelligence applied in cardiovascular disease: a bibliometric and visual analysis

Background

With the rapid development of technology, artificial intelligence (AI) has been widely used in the diagnosis and prognosis prediction of a variety of diseases, including cardiovascular disease. Facts have proved that AI has broad application prospects in rapid and accurate diagnosis.

Objective

This study mainly summarizes the research on the application of AI in the field of cardiovascular disease through bibliometric analysis and explores possible future research hotpots.

Methods

The articles and reviews regarding application of AI in cardiovascular disease between 2000 and 2023 were selected from Web of Science Core Collection on 30 December 2023. Microsoft Excel 2019 was applied to analyze the targeted variables. VOSviewer (version 1.6.16), Citespace (version 6.2.R2), and a widely used online bibliometric platform were used to conduct co-authorship, co-citation, and co-occurrence analysis of countries, institutions, authors, references, and keywords in this field.

Results

A total of 4,611 articles were selected in this study. AI-related research on cardiovascular disease increased exponentially in recent years, of which the USA was the most productive country with 1,360 publications, and had close cooperation with many countries. The most productive institutions and researchers were the Cedar sinai medical center and Acharya, Ur. However, the cooperation among most institutions or researchers was not close even if the high research outputs. Circulation is the journal with the largest number of publications in this field. The most important keywords are "classification", "diagnosis", and "risk". Meanwhile, the current research hotpots were "late gadolinium enhancement" and "carotid ultrasound".

Conclusions

AI has broad application prospects in cardiovascular disease, and a growing number of scholars are devoted to AI-related research on cardiovascular disease. Cardiovascular imaging techniques and the selection of appropriate algorithms represent the most extensively studied areas, and a considerable boost in these areas is predicted in the coming years.

A novel machine learning model to predict high on-treatment platelet reactivity on clopidogrel in Asian patients after percutaneous coronary intervention

BACKGROUND

Various genetic and nongenetic variables influence the high on-treatment platelet reactivity (HTPR) in patients taking clopidogrel.

AIM

This study aimed to develop a novel machine learning (ML) model to predict HTPR in Chinese patients after percutaneous coronary intervention (PCI).

METHOD

This cohort study collected information on 507 patients taking clopidogrel. Data were randomly divided into a training set (90%) and a testing set (10%). Nine candidate Machine learning (ML) models and multiple logistic regression (LR) analysis were developed on the training set. Their performance was assessed according to the area under the receiver operating characteristic curve, precision, recall, F1 score, and accuracy on the test set. Model interpretations were generated using importance scores by transforming model variables into scaled features and representing in radar plots. Finally, we established a prediction platform for the prediction of HTPR.

RESULTS

A total of 461 patients (HTPR rate: 19.52%) were enrolled in building the prediction model for HTPR. The XGBoost model had an optimized performance, with an AUC of 0.82, a precision of 0.80, a recall of 0.44, an F1 score of 0.57, and an accuracy of 0.87, which was superior to those of LR. Furthermore, the XGBoost method identified 7 main predictive variables. To facilitate the application of the model, we established an XGBoost prediction platform consisting of 7 variables and all variables for the HTPR prediction.

CONCLUSION

A ML-based approach, such as XGBoost, showed optimum performance and might help predict HTPR on clopidogrel after PCI and guide clinical decision-making. Further validated studies will strengthen this finding.

Anti-inflammatory response-based risk assessment in acute type A aortic dissection: A national multicenter cohort study

Background

Early identification of patients at high risk of operative mortality is important for acute type A aortic dissection (TAAD). We aimed to investigate whether patients with distinct risk stratifications respond differently to anti-inflammatory pharmacotherapy.

Methods

From 13 cardiovascular hospitals, 3110 surgically repaired TAAD patients were randomly divided into a training set (70%) and a test set (30%) to develop and validate a risk model to predict operative mortality using extreme gradient boosting. Performance was measured by the area under the receiver operating characteristic curve (AUC). Subgroup analyses were performed by risk stratifications (low versus middle-high risk) and anti-inflammatory pharmacotherapy (absence versus presence of ulinastatin use).

Results

A simplified risk model was developed for predicting operative mortality, consisting of the top ten features of importance: platelet-leukocyte ratio, D-dimer, activated partial thromboplastin time, urea nitrogen, glucose, lactate, base excess, hemoglobin, albumin, and creatine kinase-MB, which displayed a superior discrimination ability (AUC: 0.943, 95 % CI 0.928-0.958 and 0.884, 95 % CI 0.836-0.932) in the derivation and validation cohorts, respectively. Ulinastatin use was not associated with decreased risk of operative mortality among each risk stratification, however, ulinastatin use was associated with a shorter mechanical ventilation duration among patients with middle-high risk (defined as risk probability >5.0 %) (β -1.6 h, 95 % CI [-3.1, -0.1] hours; P = 0.048).

Conclusion

This risk model reflecting inflammatory, coagulation, and metabolic pathways achieved acceptable predictive performances of operative mortality following TAAD surgery, which will contribute to individualized anti-inflammatory pharmacotherapy.

Development of an efficient novel method for coronary artery disease prediction using machine learning and deep learning techniques

BACKGROUND

Heart disease is a severe health issue that results in high fatality rates worldwide. Identifying cardiovascular diseases such as coronary artery disease (CAD) and heart attacks through repetitive clinical data analysis is a significant task. Detecting heart disease in its early stages can save lives. The most lethal cardiovascular condition is CAD, which develops over time due to plaque buildup in coronary arteries, causing incomplete blood flow obstruction. Machine Learning (ML) is progressively used in the medical sector to detect CAD disease.

OBJECTIVE

The primary aim of this work is to deliver a state-of-the-art approach to enhancing CAD prediction accuracy by using a DL algorithm in a classification context.

METHODS

A unique ML technique is proposed in this study to predict CAD disease accurately using a deep learning algorithm in a classification context. An ensemble voting classifier classification model is developed based on various methods such as Naïve Bayes (NB), Logistic Regression (LR), Decision Tree (DT), XGBoost, Random Forest (RF), Convolutional Neural Network (CNN), Support Vector Machine (SVM), K Nearest Neighbor (KNN), Bidirectional LSTM and Long Short-Term Memory (LSTM). The performance of the ensemble models and a novel model are compared in this study. The Alizadeh Sani dataset, which consists of a random sample of 216 cases with CAD, is used in this study. Synthetic Minority Over Sampling Technique (SMOTE) is used to address the issue of imbalanced datasets, and the Chi-square test is used for feature selection optimization. Performance is assessed using various assessment methodologies, such as confusion matrix, accuracy, recall, precision, f1-score, and auc-roc.

RESULTS

When a novel algorithm achieves the highest accuracy relative to other algorithms, it demonstrates its effectiveness in several ways, including superior performance, robustness, generalization capability, efficiency, innovative approaches, and benchmarking against baselines. These characteristics collectively contribute to establishing the novel algorithm as a promising solution for addressing the target problem in machine learning and related fields.

CONCLUSION

Implementing the novel model in this study significantly improved performance, achieving a prediction accuracy rate of 92% in the detection of CAD. These findings are competitive and on par with the top outcomes among other methods.

Simplified Approach to Predicting Obstructive Coronary Disease With Integration of Coronary Calcium: Development and External Validation

BACKGROUND

The Diamond-Forrester model was used extensively to predict obstructive coronary artery disease (CAD) but overestimates probability in current populations. Coronary artery calcium (CAC) is a useful marker of CAD, which is not routinely integrated with other features. We derived simple likelihood tables, integrating CAC with age, sex, and cardiac chest pain to predict obstructive CAD.

METHODS AND RESULTS

The training population included patients from 3 multinational sites (n=2055), with 2 sites for external testing (n=3321). We determined associations between age, sex, cardiac chest pain, and CAC with the presence of obstructive CAD, defined as any stenosis ≥50% on coronary computed tomography angiography. Prediction performance was assessed using area under the receiver-operating characteristic curves (AUCs) and compared with the CAD Consortium models with and without CAC, which require detailed calculations, and the updated Diamond-Forrester model. In external testing, the proposed likelihood tables had higher AUC (0.875 [95% CI, 0.862-0.889]) than the CAD Consortium clinical+CAC score (AUC, 0.868 [95% CI, 0.855-0.881]; P=0.030) and the updated Diamond-Forrester model (AUC, 0.679 [95% CI, 0.658-0.699]; P<0.001). The calibration for the likelihood tables was better than the CAD Consortium model (Brier score, 0.116 versus 0.121; P=0.005).

CONCLUSIONS

We have developed and externally validated simple likelihood tables to integrate CAC with age, sex, and cardiac chest pain, demonstrating improved prediction performance compared with other risk models. Our tool affords physicians with the opportunity to rapidly and easily integrate a small number of important features to estimate a patient's likelihood of obstructive CAD as an aid to clinical management.

Using Artificial Intelligence to Semi-Quantitate Coronary Calcium as an 'Incidentaloma' on Non-Gated, Non-Contrast CT Scans, A Single-Center Descriptive Study in West Michigan

INTRODUCTION

Non-gated, non-contrast computed tomography (CT) scans are commonly ordered for a variety of non-cardiac indications, but do not routinely comment on the presence of coronary artery calcium (CAC)/atherosclerotic cardiovascular disease (ASCVD) which is known to correlate with increased cardiovascular risk. Artificial intelligence (AI) algorithms can help detect and quantify CAC/ASCVD which can lead to early treatment and improved outcomes.

METHODS

Using an FDA-approved algorithm (NANOX AI) to measure coronary artery calcium (CAC) on non-gated, non-contrast CT chest, 536 serial scans were evaluated in this single-center retrospective study. Scans were categorized by Agatston scores as normal-mild (<100), moderate (100-399), or severe (≥400). AI results were validated by cardiologist's overread. Patient charts were retrospectively analyzed for clinical characteristics.

RESULTS

Of the 527 patients included in this analysis, a total of 258 (48.96%) had moderate-severe disease; of these, 164 patients (63.57%, p< 0.001) had no previous diagnosis of CAD. Of those with moderate-severe disease 135 of 258 (52.33% p=0.006) were not on aspirin and 96 (37.21% p=0.093) were not on statin therapy. Cardiologist interpretation demonstrated 88.76% agreement with AI classification.

DISCUSSION/CONCLUSION

Machine learning utilized in CT scans obtained for non-cardiac indications can detect and semi-quantitate CAC accurately. Artificial intelligence algorithms can accurately be applied to non-gated, non-contrast CT scans to identify CAC/ASCVD allowing for early medical intervention and improved clinical outcomes.

Explainable machine learning model for predicting furosemide responsiveness in patients with oliguric acute kidney injury

BACKGROUND

Although current guidelines didn't support the routine use of furosemide in oliguric acute kidney injury (AKI) management, some patients may benefit from furosemide administration at an early stage. We aimed to develop an explainable machine learning (ML) model to differentiate between furosemide-responsive (FR) and furosemide-unresponsive (FU) oliguric AKI.

METHODS

From Medical Information Mart for Intensive Care-IV (MIMIC-IV) and eICU Collaborative Research Database (eICU-CRD), oliguric AKI patients with urine output (UO) < 0.5 ml/kg/h for the first 6 h after ICU admission and furosemide infusion ≥ 40 mg in the following 6 h were retrospectively selected. The MIMIC-IV cohort was used in training a XGBoost model to predict UO > 0.65 ml/kg/h during 6-24 h succeeding the initial 6 h for assessing oliguria, and it was validated in the eICU-CRD cohort. We compared the predictive performance of the XGBoost model with the traditional logistic regression and other ML models.

RESULTS

6897 patients were included in the MIMIC-IV training cohort, with 2235 patients in the eICU-CRD validation cohort. The XGBoost model showed an AUC of 0.97 (95% CI: 0.96-0.98) for differentiating FR and FU oliguric AKI. It outperformed the logistic regression and other ML models in correctly predicting furosemide diuretic response, achieved 92.43% sensitivity (95% CI: 90.88-93.73%) and 95.12% specificity (95% CI: 93.51-96.3%).

CONCLUSION

A boosted ensemble algorithm can be used to accurately differentiate between patients who would and would not respond to furosemide in oliguric AKI. By making the model explainable, clinicians would be able to better understand the reasoning behind the prediction outcome and make individualized treatment.

Fusion Modeling: Combining Clinical and Imaging Data to Advance Cardiac Care

In addition to the traditional clinical risk factors, an increasing amount of imaging biomarkers have shown value for cardiovascular risk prediction. Clinical and imaging data are captured from a variety of data sources during multiple patient encounters and are often analyzed independently. Initial studies showed that fusion of both clinical and imaging features results in superior prognostic performance compared with traditional scores. There are different approaches to fusion modeling, combining multiple data resources to optimize predictions, each with its own advantages and disadvantages. However, manual extraction of clinical and imaging data is time and labor intensive and often not feasible in clinical practice. An automated approach for clinical and imaging data extraction is highly desirable. Convolutional neural networks and natural language processing can be utilized for the extraction of electronic medical record data, imaging studies, and free-text data. This review outlines the current status of cardiovascular risk prediction and fusion modeling; and in addition gives an overview of different artificial intelligence approaches to automatically extract data from images and electronic medical records for this purpose.

Machine Learning in Cardiovascular Risk Prediction and Precision Preventive Approaches

PURPOSE OF REVIEW

In this review, we sought to provide an overview of ML and focus on the contemporary applications of ML in cardiovascular risk prediction and precision preventive approaches. We end the review by highlighting the limitations of ML while projecting on the potential of ML in assimilating these multifaceted aspects of CAD in order to improve patient-level outcomes and further population health.

RECENT FINDINGS

Coronary artery disease (CAD) is estimated to affect 20.5 million adults across the USA, while also impacting a significant burden at the socio-economic level. While the knowledge of the mechanistic pathways that govern the onset and progression of clinical CAD has improved over the past decade, contemporary patient-level risk models lag in accuracy and utility. Recently, there has been renewed interest in combining advanced analytic techniques that utilize artificial intelligence (AI) with a big data approach in order to improve risk prediction within the realm of CAD. By virtue of being able to combine diverse amounts of multidimensional horizontal data, machine learning has been employed to build models for improved risk prediction and personalized patient care approaches. The use of ML-based algorithms has been used to leverage individualized patient-specific data and the associated metabolic/genomic profile to improve CAD risk assessment. While the tool can be visualized to shift the paradigm toward a patient-specific care, it is crucial to acknowledge and address several challenges inherent to ML and its integration into healthcare before it can be significantly incorporated in the daily clinical practice.

Machine learning based ischemia-specific stenosis prediction: A Chinese multicenter coronary CT angiography study

OBJECTIVES

To evaluate the performance of coronary computed tomography angiography (CCTA) derived characteristics including CT derived fractional flow reserve (CT-FFR) with FFR as a reference standard in identifying the lesion-specific ischemia by machine learning (ML) algorithms.

METHODS

The retrospective analysis enrolled 596 vessels in 462 patients (mean age, 61 years ± 11 [SD]; 71.4 % men) with suspected coronary artery disease who underwent CCTA and invasive FFR. The data were divided into training cohort, internal validation cohort, external validation cohorts 1 and 2 according to participating centers. All CCTA-derived parameters, which contained 10 qualitative and 33 quantitative plaque parameters, were collected to establish ML model. The Boruta and unsupervised clustering algorithm were implemented to select important and non-redundant parameters. Finally, the eight features with the highest mean importance were included for further ML model establishment and decision tree building. Five models were built to predict lesion-specific ischemia: stenosis degree from CCTA, CT-FFR, ΔCT-FFR, ML model and nested model.

RESULTS

Low-attenuation plaque, bend and lesion length were the main predictors of ischemia-specific lesions. Of 5 models, the ML model showed favorable discrimination for ischemia-specific lesions in the training and three validation sets (area under the curve [95 % confidence interval], 0.93 [0.90-0.96], 0.86 [0.79-0.94], 0.88 [0.83-0.94], and 0.90 [0.84-0.96], respectively). The nested model which combined the ML model and CT-FFR showed better diagnostic efficacy (AUC [95 %CI], 0.96 [0.94-0.99], 0.92 [0.86-0.99], 0.92 [0.86-0.99] and 0.94 [0.91-0.98], respectively; all P < 0.05), and net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were significantly higher than CT-FFR alone.

CONCLUSIONS

Comprehensive CCTA-derived multiparameter model could better predict the ischemia-specific lesions by ML algorithms compared to stenosis degree from CTA, CT-FFR and ΔCT-FFR. Decision tree can be used to predict myocardial ischemia effectively.

Using Machine Learning Methods to Assess Lymphovascular Invasion and Survival in Breast Cancer: Performance of Combining Preoperative Clinical and MRI Characteristics

BACKGROUND

Preoperative assessment of lymphovascular invasion (LVI) in invasive breast cancer (IBC) is of high clinical relevance for treatment decision-making and prognosis.

PURPOSE

To investigate the associations of preoperative clinical and magnetic resonance imaging (MRI) characteristics with LVI and disease-free survival (DFS) by using machine learning methods in patients with IBC.

STUDY TYPE

Retrospective.

POPULATION

Five hundred and seventy-five women (range: 24-79 years) with IBC who underwent preoperative MRI examinations at two hospitals, divided into the training (N = 386) and validation datasets (N = 189).

FIELD STRENGTH/SEQUENCE

Axial fat-suppressed T2-weighted turbo spin-echo sequence and dynamic contrast-enhanced with fat-suppressed T1-weighted three-dimensional gradient echo imaging.

ASSESSMENT

MRI characteristics (clinical T stage, breast edema score, MRI axillary lymph node status, multicentricity or multifocality, enhancement pattern, adjacent vessel sign, and increased ipsilateral vascularity) were reviewed independently by three radiologists. Logistic regression (LR), eXtreme Gradient Boosting (XGBoost), k-Nearest Neighbor (KNN), and Support Vector Machine (SVM) algorithms were used to establish the models by combing preoperative clinical and MRI characteristics for assessing LVI status in the training dataset, and the methods were further applied in the validation dataset. The LVI score was calculated using the best-performing of the four models to analyze the association with DFS.

STATISTICAL TESTS

Chi-squared tests, variance inflation factors, receiver operating characteristics (ROC), Kaplan-Meier curve, log-rank, Cox regression, and intraclass correlation coefficient were performed. The area under the ROC curve (AUC) and hazard ratios (HR) were calculated. A P-value <0.05 was considered statistically significant.

RESULTS

The model established by the XGBoost algorithm had better performance than LR, SVM, and KNN models, achieving an AUC of 0.832 (95% confidence interval [CI]: 0.789, 0.876) in the training dataset and 0.838 (95% CI: 0.775, 0.901) in the validation dataset. The LVI score established by the XGBoost model was an independent indicator of DFS (adjusted HR: 2.66, 95% CI: 1.22-5.80).

DATA CONCLUSION

The XGBoost model based on preoperative clinical and MRI characteristics may help to investigate the LVI status and survival in patients with IBC.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Utility of Machine Learning Algorithms in Predicting Preoperative Lymph Node Metastasis in Patients With Rectal Cancer Based on Three-Dimensional Endorectal Ultrasound and Clinical and Laboratory Data

BACKGROUND

We aimed to investigate the value of a machine learning (ML) algorithm in the preoperative prediction of lymph node metastasis in patients with rectal cancer.

METHODS

Based on the histopathological results, 126 rectal cancer patients were divided into two groups: lymph node metastasis-positive and metastasis-negative groups. We collected clinical and laboratory data, three-dimensional endorectal ultrasound (3D-ERUS) findings, and parameters of the tumor for between-group comparisons. We constructed a clinical prediction model based on the ML algorithm, which demonstrated the best diagnostic performance. Finally, we analyzed the diagnostic results and processes of the ML model.

RESULTS

Between the two groups, there were significant differences in serum carcinoembryonic antigen (CEA) levels, tumor length, tumor breadth, circumferential extent of the tumor, resistance index (RI), and ultrasound T-stage (P < 0.05). The extreme gradient boosting (XGBoost) model had the best comprehensive diagnostic performance for predicting lymph node metastasis in patients with rectal cancer. Compared with experienced radiologists, the XGBoost model showed significantly higher diagnostic value in predicting lymph node metastasis; the area under curve (AUC) value of the receiver operating characteristic (ROC) curve of the XGBoost model and experienced radiologists was 0.82 and 0.60, respectively.

CONCLUSIONS

Preoperative predictive utility in lymph node metastasis was demonstrated by the XGBoost model based on the 3D-ERUS finding and related clinical information. This could be useful in guiding clinical decisions on the selection of different treatment strategies.

Predictive value of machine learning algorithm of coronary artery calcium score and clinical factors for obstructive coronary artery disease in hypertensive patients

BACKGROUND

The addition of coronary artery calcium score (CACS) to prediction models has been verified to improve performance. Machine learning (ML) algorithms become important medical tools in an era of precision medicine, However, combined utility by CACS and ML algorithms in hypertensive patients to forecast obstructive coronary artery disease (CAD) on coronary computed tomography angiography (CCTA) is rare.

METHODS

This retrospective study was composed of 1,273 individuals with hypertension and without a history of CAD, who underwent dual-source computed tomography evaluation. We applied five ML algorithms, coupled with clinical factors, imaging parameters, and CACS to construct predictive models. Moreover, 80% individuals were randomly taken as a training set on which 5-fold cross-validation was done and the remaining 20% were regarded as a validation set.

RESULTS

16.7% (212 out of 1,273) of hypertensive patients had obstructive CAD. Extreme Gradient Boosting (XGBoost) posted the biggest area under the receiver operator characteristic curve (AUC) of 0.83 in five ML algorithms. Continuous net reclassification improvement (NRI) was 0.55 (95% CI (0.39-0.71), p < 0.001), and integrated discrimination improvement (IDI) was 0.04 (95% CI (0.01-0. 07), p = 0.0048) when the XGBoost model was compared with traditional Models. In the subgroup analysis stratified by hypertension levels, XGBoost still had excellent performance.

CONCLUSION

The ML model incorporating clinical features and CACS may accurately forecast the presence of obstructive CAD on CCTA among hypertensive patients. XGBoost is superior to other ML algorithms.

Illness severity assessment of older adults in critical illness using machine learning (ELDER-ICU): an international multicentre study with subgroup bias evaluation

BACKGROUND

Comorbidity, frailty, and decreased cognitive function lead to a higher risk of death in elderly patients (more than 65 years of age) during acute medical events. Early and accurate illness severity assessment can support appropriate decision making for clinicians caring for these patients. We aimed to develop ELDER-ICU, a machine learning model to assess the illness severity of older adults admitted to the intensive care unit (ICU) with cohort-specific calibration and evaluation for potential model bias.

METHODS

In this retrospective, international multicentre study, the ELDER-ICU model was developed using data from 14 US hospitals, and validated in 171 hospitals from the USA and Netherlands. Data were extracted from the Medical Information Mart for Intensive Care database, electronic ICU Collaborative Research Database, and Amsterdam University Medical Centers Database. We used six categories of data as predictors, including demographics and comorbidities, physical frailty, laboratory tests, vital signs, treatments, and urine output. Patient data from the first day of ICU stay were used to predict in-hospital mortality. We used the eXtreme Gradient Boosting algorithm (XGBoost) to develop models and the SHapley Additive exPlanations method to explain model prediction. The trained model was calibrated before internal, external, and temporal validation. The final XGBoost model was compared against three other machine learning algorithms and five clinical scores. We performed subgroup analysis based on age, sex, and race. We assessed the discrimination and calibration of models using the area under receiver operating characteristic (AUROC) and standardised mortality ratio (SMR) with 95% CIs.

FINDINGS

Using the development dataset (n=50 366) and predictive model building process, the XGBoost algorithm performed the best in all types of validations compared with other machine learning algorithms and clinical scores (internal validation with 5037 patients from 14 US hospitals, AUROC=0·866 [95% CI 0·851-0·880]; external validation in the US population with 20 541 patients from 169 hospitals, AUROC=0·838 [0·829-0·847]; external validation in European population with 2411 patients from one hospital, AUROC=0·833 [0·812-0·853]; temporal validation with 4311 patients from one hospital, AUROC=0·884 [0·869-0·897]). In the external validation set (US population), the median AUROCs of bias evaluations covering eight subgroups were above 0·81, and the overall SMR was 0·99 (0·96-1·03). The top ten risk predictors were the minimum Glasgow Coma Scale score, total urine output, average respiratory rate, mechanical ventilation use, best state of activity, Charlson Comorbidity Index score, geriatric nutritional risk index, code status, age, and maximum blood urea nitrogen. A simplified model containing only the top 20 features (ELDER-ICU-20) had similar predictive performance to the full model.

INTERPRETATION

The ELDER-ICU model reliably predicts the risk of in-hospital mortality using routinely collected clinical features. The predictions could inform clinicians about patients who are at elevated risk of deterioration. Prospective validation of this model in clinical practice and a process for continuous performance monitoring and model recalibration are needed.

FUNDING

National Institutes of Health, National Natural Science Foundation of China, National Special Health Science Program, Health Science and Technology Plan of Zhejiang Province, Fundamental Research Funds for the Central Universities, Drug Clinical Evaluate Research of Chinese Pharmaceutical Association, and National Key R&D Program of China.

Machine learning approaches that use clinical, laboratory, and electrocardiogram data enhance the prediction of obstructive coronary artery disease

Pretest probability (PTP) for assessing obstructive coronary artery disease (ObCAD) was updated to reduce overestimation. However, standard laboratory findings and electrocardiogram (ECG) raw data as first-line tests have not been evaluated for integration into the PTP estimation. Therefore, this study developed an ensemble model by adopting machine learning (ML) and deep learning (DL) algorithms with clinical, laboratory, and ECG data for the assessment of ObCAD. Data were extracted from the electronic medical records of patients with suspected ObCAD who underwent coronary angiography. With the ML algorithm, 27 clinical and laboratory data were included to identify ObCAD, whereas ECG waveform data were utilized with the DL algorithm. The ensemble method combined the clinical-laboratory and ECG models. We included 7907 patients between 2008 and 2020. The clinical and laboratory model showed an area under the curve (AUC) of 0.747; the ECG model had an AUC of 0.685. The ensemble model demonstrated the highest AUC of 0.767. The sensitivity, specificity, and F1 score of the ensemble model ObCAD were 0.761, 0.625, and 0.696, respectively. It demonstrated good performance and superior prediction over traditional PTP models. This may facilitate personalized decisions for ObCAD assessment and reduce PTP overestimation.

Machine learning based model to diagnose obstructive coronary artery disease using calcium scoring, PET imaging, and clinical data

INTRODUCTION

Accurate risk stratification in patients with suspected stable coronary artery disease is essential for choosing an appropriate treatment strategy. Our aim was to develop and validate a machine learning (ML) based model to diagnose obstructive CAD (oCAD).

METHOD

We retrospectively have included 1007 patients without a prior history of CAD who underwent CT-based calcium scoring (CACS) and a Rubidium-82 PET scan. The entire dataset was split 4:1 into a training and test dataset. An ML model was developed on the training set using fivefold stratified cross-validation. The test dataset was used to compare the performance of expert readers to the model. The primary endpoint was oCAD on invasive coronary angiography (ICA).

RESULTS

ROC curve analysis showed an AUC of 0.92 (95% CI 0.90-0.94) for the training dataset and 0.89 (95% CI 0.84-0.93) for the test dataset. The ML model showed no significant differences as compared to the expert readers (p ≥ 0.03) in accuracy (89% vs. 88%), sensitivity (68% vs. 69%), and specificity (92% vs. 90%).

CONCLUSION

The ML model resulted in a similar diagnostic performance as compared to expert readers, and may be deployed as a risk stratification tool for obstructive CAD. This study showed that utilization of ML is promising in the diagnosis of obstructive CAD.

Deep learning-based prediction for significant coronary artery stenosis on coronary computed tomography angiography in asymptomatic populations

Background

Although coronary computed tomography angiography (CCTA) is currently utilized as the frontline test to accurately diagnose coronary artery disease (CAD) in clinical practice, there are still debates regarding its use as a screening tool for the asymptomatic population. Using deep learning (DL), we sought to develop a prediction model for significant coronary artery stenosis on CCTA and identify the individuals who would benefit from undergoing CCTA among apparently healthy asymptomatic adults.

Methods

We retrospectively reviewed 11,180 individuals who underwent CCTA as part of routine health check-ups between 2012 and 2019. The main outcome was the presence of coronary artery stenosis of ≥70% on CCTA. We developed a prediction model using machine learning (ML), including DL. Its performance was compared with pretest probabilities, including the pooled cohort equation (PCE), CAD consortium, and updated Diamond-Forrester (UDF) scores.

Results

In the cohort of 11,180 apparently healthy asymptomatic individuals (mean age 56.1 years; men 69.8%), 516 (4.6%) presented with significant coronary artery stenosis on CCTA. Among the ML methods employed, a neural network with multi-task learning (19 selected features), one of the DL methods, was selected due to its superior performance, with an area under the curve (AUC) of 0.782 and a high diagnostic accuracy of 71.6%. Our DL-based model demonstrated a better prediction than the PCE (AUC, 0.719), CAD consortium score (AUC, 0.696), and UDF score (AUC, 0.705). Age, sex, HbA1c, and HDL cholesterol were highly ranked features. Personal education and monthly income levels were also included as important features of the model.

Conclusion

We successfully developed the neural network with multi-task learning for the detection of CCTA-derived stenosis of ≥70% in asymptomatic populations. Our findings suggest that this model may provide more precise indications for the use of CCTA as a screening tool to identify individuals at a higher risk, even in asymptomatic populations, in clinical practice.

Machine learning algorithm can provide assistance for the diagnosis of non-ST-segment elevation myocardial infarction

INTRODUCTION

Our aim was to use the constructed machine learning (ML) models as auxiliary diagnostic tools to improve the diagnostic accuracy of non-ST-elevation myocardial infarction (NSTEMI).

MATERIALS AND METHODS

A total of 2878 patients were included in this retrospective study, including 1409 patients with NSTEMI and 1469 patients with unstable angina pectoris. The clinical and biochemical characteristics of the patients were used to construct the initial attribute set. SelectKBest algorithm was used to determine the most important features. A feature engineering method was applied to create new features correlated strongly to train ML models and obtain promising results. Based on the experimental dataset, the ML models of extreme gradient boosting, support vector machine, random forest, naïve Bayesian, gradient boosting machines and logistic regression were constructed. Each model was verified by test set data, and the diagnostic performance of each model was comprehensively evaluated.

RESULTS

The six ML models based on the training set all play an auxiliary role in the diagnosis of NSTEMI. Although all models taken for comparison performed differences, the extreme gradient boosting ML model performed the best in terms of accuracy rate (0.95±0.014), precision rate (0.94±0.011), recall rate (0.98±0.003) and F-1 score (0.96±0.007) in NSTEMI.

CONCLUSIONS

The ML model constructed based on clinical data can be used as an auxiliary tool to improve the accuracy of NSTEMI diagnosis. According to our comprehensive evaluation, the performance of the extreme gradient boosting model was the best.

Classification models for assessing coronary artery disease instances using clinical and biometric data: an explainable man-in-the-loop approach

The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert's opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert's diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model's performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.

Use of machine learning to identify risk factors for coronary artery disease

Coronary artery disease (CAD) is the leading cause of death in both developed and developing nations. The objective of this study was to identify risk factors for coronary artery disease through machine-learning and assess this methodology. A retrospective, cross-sectional cohort study using the publicly available National Health and Nutrition Examination Survey (NHANES) was conducted in patients who completed the demographic, dietary, exercise, and mental health questionnaire and had laboratory and physical exam data. Univariate logistic models, with CAD as the outcome, were used to identify covariates that were associated with CAD. Covariates that had a p<0.0001 on univariate analysis were included within the final machine-learning model. The machine learning model XGBoost was used due to its prevalence within the literature as well as its increased predictive accuracy in healthcare prediction. Model covariates were ranked according to the Cover statistic to identify risk factors for CAD. Shapely Additive Explanations (SHAP) explanations were utilized to visualize the relationship between these potential risk factors and CAD. Of the 7,929 patients that met the inclusion criteria in this study, 4,055 (51%) were female, 2,874 (49%) were male. The mean age was 49.2 (SD = 18.4), with 2,885 (36%) White patients, 2,144 (27%) Black patients, 1,639 (21%) Hispanic patients, and 1,261 (16%) patients of other race. A total of 338 (4.5%) of patients had coronary artery disease. These were fitted into the XGBoost model and an AUROC = 0.89, Sensitivity = 0.85, Specificity = 0.87 were observed (Fig 1). The top four highest ranked features by cover, a measure of the percentage contribution of the covariate to the overall model prediction, were age (Cover = 21.1%), Platelet count (Cover = 5.1%), family history of heart disease (Cover = 4.8%), and Total Cholesterol (Cover = 4.1%). Machine learning models can effectively predict coronary artery disease using demographic, laboratory, physical exam, and lifestyle covariates and identify key risk factors.

Exploring the EVolution in PrognOstic CapabiLity of MUltisequence Cardiac MagneTIc ResOnance in PatieNts Affected by Takotsubo Cardiomyopathy Based on Machine Learning Analysis: Design and Rationale of the EVOLUTION Study

PURPOSE

Takotsubo cardiomyopathy (TTC) is a transient but severe acute myocardial dysfunction with a wide range of outcomes from favorable to life-threatening. The current risk stratification scores of TTC patients do not include cardiac magnetic resonance (CMR) parameters. To date, it is still unknown whether and how clinical, trans-thoracic echocardiography (TTE), and CMR data can be integrated to improve risk stratification.

METHODS

EVOLUTION (Exploring the eVolution in prognOstic capabiLity of mUlti-sequence cardiac magneTIc resOnance in patieNts affected by Takotsubo cardiomyopathy) is a multicenter, international registry of TTC patients who will undergo a clinical, TTE, and CMR evaluation. Clinical data including demographics, risk factors, comorbidities, laboratory values, ECG, and results from TTE and CMR analysis will be collected, and each patient will be followed-up for in-hospital and long-term outcomes. Clinical outcome measures during hospitalization will include cardiovascular death, pulmonary edema, arrhythmias, stroke, or transient ischemic attack.Clinical long-term outcome measures will include cardiovascular death, pulmonary edema, heart failure, arrhythmias, sudden cardiac death, and major adverse cardiac and cerebrovascular events defined as a composite endpoint of death from any cause, myocardial infarction, recurrence of TTC, transient ischemic attack, and stroke. We will develop a comprehensive clinical and imaging score that predicts TTC outcomes and test the value of machine learning models, incorporating clinical and imaging parameters to predict prognosis.

CONCLUSIONS

The main goal of the study is to develop a comprehensive clinical and imaging score, that includes TTE and CMR data, in a large cohort of TTC patients for risk stratification and outcome prediction as a basis for possible changes in patient management.

Development of a 32-gene signature using machine learning for accurate prediction of inflammatory bowel disease

Inflammatory bowel disease (IBD) is a chronic inflammatory condition caused by multiple genetic and environmental factors. Numerous genes are implicated in the etiology of IBD, but the diagnosis of IBD is challenging. Here, XGBoost, a machine learning prediction model, has been used to distinguish IBD from healthy cases following elaborative feature selection. Using combined unsupervised clustering analysis and the XGBoost feature selection method, we successfully identified a 32-gene signature that can predict IBD occurrence in new cohorts with 0.8651 accuracy. The signature shows enrichment in neutrophil extracellular trap formation and cytokine signaling in the immune system. The probability threshold of the XGBoost-based classification model can be adjusted to fit personalized lifestyle and health status. Therefore, this study reveals potential IBD-related biomarkers that facilitate an effective personalized diagnosis of IBD.

Predictive value of CAC score combined with clinical features for obstructive coronary heart disease on coronary computed tomography angiography: a machine learning method

OBJECTIVE

We investigated the predictive value of clinical factors combined with coronary artery calcium (CAC) score based on a machine learning method for obstructive coronary heart disease (CAD) on coronary computed tomography angiography (CCTA) in individuals with atypical chest pain.

METHODS

The study included data from 1,906 individuals undergoing CCTA and CAC scanning because of atypical chest pain and without evidence for the previous CAD. A total of 63 variables including traditional cardiovascular risk factors, CAC score, laboratory results, and imaging parameters were used to build the Random forests (RF) model. Among all the participants, 70% were randomly selected to train the models on which fivefold cross-validation was done and the remaining 30% were regarded as a validation set. The prediction performance of the RF model was compared with two traditional logistic regression (LR) models.

RESULTS

The incidence of obstructive CAD was 16.4%. The area under the receiver operator characteristic (ROC) for obstructive CAD of the RF model was 0.841 (95% CI 0.820-0.860), the CACS model was 0.746 (95% CI 0.722-0.769), and the clinical model was 0.810 (95% CI 0.788-0.831). The RF model was significantly superior to the other two models (p < 0.05). Furthermore, the calibration curve and Hosmer-Lemeshow test showed that the RF model had good classification performance (p = 0.556). CAC score, age, glucose, homocysteine, and neutrophil were the top five important variables in the RF model.

CONCLUSION

RF model was superior to the traditional models in the prediction of obstructive CAD. In clinical practice, the RF model may improve risk stratification and optimize individual management.

Coronary calcium score in the initial evaluation of suspected coronary artery disease

OBJECTIVE

We evaluated coronary artery calcium (CAC) scoring as an initial diagnostic tool in outpatients and in patients presenting at the emergency department due to suspected coronary artery disease (CAD).

METHODS

10 857 patients underwent CAC scoring and coronary CT angiography (CCTA) at Haukeland University Hospital in Norway during 2013-2020. Based on CCTA, obstructive CAD was defined as at least one coronary stenosis ≥50%. High-risk CAD included obstructive stenoses of the left main stem, the proximal left ascending artery or affecting all three major vascular territories with at least one proximal segment involved.

RESULTS

Median age was 58 years and 49.5% were women. The overall prevalence of CAC=0 was 45.0%. Among those with CAC=0, 1.8% had obstructive CAD and 0.6% had high-risk CAD on CCTA. Overall, the sensitivity, specificity, positive predictive value and negative predictive value (NPV) of CAC=0 for obstructive CAD were 95.3%, 53.4%, 30.0% and 98.2%, respectively. However, among patients <45 years of age, although the NPV was high at 98.9%, the sensitivity of CAC=0 for obstructive CAD was only 82.3%.

CONCLUSIONS

In symptomatic patients, CAC=0 correctly ruled out obstructive CAD and high-risk CAD in 98.2% and 99.4% of cases. This large registry-based cross-sectional study supports the incorporation of CAC testing in the early triage of patients with chest pain and as a gatekeeper to further cardiac testing. However, a full CCTA may be needed for safely ruling out obstructive CAD in the youngest patients (<45 years of age).

A clinical decision support system for predicting coronary artery stenosis in patients with suspected coronary heart disease

Invasive coronary angiography imposes risks and high medical costs. Therefore, accurate, reliable, non-invasive, and cost-effective methods for diagnosing coronary stenosis are required. We designed a machine learning-based risk-prediction system as an accurate, noninvasive, and cost-effective alternative method for evaluating suspected coronary heart disease (CHD) patients. Electronic medical record data were collected from suspected CHD patients undergoing coronary angiography between May 1, 2017, and December 31, 2019. Multi-Class XGBoost, LightGBM, Random Forest, NGBoost, logistic models and MLP were constructed to identify patients with normal coronary arteries (class 0: no coronary artery stenosis), minimum coronary artery stenosis (class 1: 0 < stenosis <50%), and CHD (class 2: stenosis ≥50%). Model stability was verified externally. A risk-assessment and management system was established for patient-specific intervention guidance. Of 1577 suspected CHD patients, 81 (5.14%) had normal coronary arteries. The XGBoost model demonstrated the best overall classification performance (micro-average receiver operating characteristic [ROC] curve: 0.92, macro-average ROC curve: 0.89, class 0 ROC curve: 0.88, class 1 ROC curve: 0.90, class 2 ROC curve: 0.89), with good external verification. In class-specific classification, the XGBoost model yielded F1 values of 0.636, 0.850, and 0.858, for Classes 0, 1, and 2, respectively. The visualization system allowed disease diagnosis and probability estimation, and identified the intervention focus for individual patients. Thus, the system distinguished coronary artery stenosis well in suspected CHD patients. Personalized probability curves provide individualized intervention guidance. This may reduce the number of invasive inspections in negative patients, while facilitating decision-making regarding appropriate medical intervention, improving patient prognosis.