Showing papers by "Lucian Mihai Itu published in 2023"
TL;DR: In this paper , the authors developed a machine learning model based on the integration of clinical and echocardiographic data, which is capable of accurately detecting atrial fibrillation (AF) in patients with HCM.
Abstract:
Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Romanian Ministry of National Education, CNCS-UEFISCDI.
Atrial fibrillation (AF) is the most frequent arrhythmia in hypertrophic cardiomyopathy (HCM), with a major impact on overall survival, thromboembolic risk, and quality of life. Early recognition and treatment of AF are essential to improve the outcome of HCM patients (pts). Despite the existence of several independent predictors of AF development, the identification of HCM pts at risk for AF is still inconsistent. The identification, quantification, and interpretation of the relationships between different clinical and imaging-derived variables may lead to improved risk stratification and prognosis. Predictive models based on machine learning (ML) could reduce variability while providing useful new medical knowledge.
Develop a ML model (emerging from the integration of clinical and echocardiographic data) capable of accurately detecting HCM pts with AF.
A comprehensive clinical and echocardiographic assessment was performed in 151 consecutive pts (52±16 years, 72 men) with HCM, in sinus rhythm. Pts were divided into two groups according to the presence (38 pts) or absence (113 pts) of documented paroxysmal AF (24/48 h ambulatory ECG recordings). 81 features (clinical and echocardiographic parameters) were considered as input to the ML models. Four different ML models were evaluated: Deep Learning (DL), Linear Logistic Regression (LLR), Support Vector Machine (SVM) and Random Forest (RF). Ensemble learning and four-fold cross-validation were employed in all experiments. For each experiment the training dataset was augmented and balanced using the Synthetic Minority Over-sampling Technique. The models were fine-tuned using the following hyper-parameters: learning rate, batch size, number of hidden layers, and number of features used as input. The features were first ranked using the Recursive Feature Elimination method, and the top N features were selected during the hyper-parameter tuning.
Each ML model was trained for 100 epochs, and the results were extracted from the epoch that led to the best results when combining all four folds. DL was the best performing model, with a learning rate of 0.01, a batch size of 32, 4 hidden layers (256/128/128/64 neurons), and 15 input features. The DL model had 5% higher accuracy compared to LLR, 10% higher than SVM and 8% higher than RF, with consistently higher sensitivity. The performance of the various models is detailed in the table below. Moreover, the DL model had significantly higher accuracy compared to conventional imaging parameters consistently related to the presence of AF in previous studies, such as maximum LA volume (AUC 0.66, accuracy 59%) or LA strain (AUC 0.61, accuracy 62%).
The DL based model can detect the presence of paroxysmal AF in patients with HCM with an accuracy of 84% (5% higher than the best classic ML model, and significantly higher than independent conventional imaging parameters).
TL;DR: In this paper , the authors assess hypertension-mediated subclinical and clinical cardiac damage using a post-hoc echocardiographic analysis of a national epidemiological survey and find that the prevalence of cardiac damage in Romanian hypertensives is high.
Abstract: Abstract Background: Data regarding cardiac damage in Romanian hypertensive adults are scarce. Our aim was to assess hypertension-mediated subclinical and clinical cardiac damage using a post-hoc echocardiographic analysis of a national epidemiological survey. Methods: A representative sample of 1477 subjects was included in the SEPHAR IV (Study for the Evaluation of Prevalence of Hypertension and Cardiovascular Risk in an Adult Population in Romania) survey. We retrieved echocardiographic data for 976 subjects, who formed our study group. Cardiac damage included left ventricular (LV) hypertrophy (defined as an LV mass > 95 g/m2 in females and > 115 g/m2 in males), coronary artery disease (CAD), and LV diastolic and systolic dysfunction. Results: Hypertension prevalence was 46.0% in SEPHAR IV and 45.3% in our study subgroup. Hypertensives had a higher prevalence of LV hypertrophy, CAD, diastolic dysfunction (p<0.001 for all) and systolic dysfunction (p=0.03) than normotensives. Age (OR=1.05;95% CI,1.03–1.08;p<0.001), female sex (OR=2.07;95% CI,1.24–3.45;p=0.006), and systolic blood pressure (OR=1.02;95% CI,1.01−1.04;p=0.026) were independent predictors of LVH in hypertensives. Age was a predictor of diastolic dysfunction (OR=1.04;95% CI,1.02−1.06;p<0.001), and female sex was a protective factor against systolic dysfunction (OR=0.26;95% CI,0.10–0.71;p=0.009). Age (OR=1.05;95% CI,1.02−1.07;p<0.001) and dyslipidemia (OR=1.89;95% CI,1.20–3.00;p=0.007) were independent determinants of CAD in hypertensives. Conclusion: The prevalence of cardiac damage in Romanian hypertensives is high. Both non-modifiable risk factors (such as age and gender) and modifiable (such as dyslipidemia and systolic blood pressure) risk factors are independent predictors of cardiac damage in hypertensives.
DOI•
01 Jun 2023
TL;DR: Wang et al. as discussed by the authors proposed a novel deep learning based method to detect coronary collateral circulation (CCC) in angiographic images, which relies on a convolutional backbone to extract spatial features from each frame of an angiography sequence.
Abstract: Coronary artery disease (CAD) is the dominant cause of death and hospitalization across the globe. Atherosclerosis, an inflammatory condition that gradually narrows arteries and has potentially fatal effects, is the most frequent cause of CAD. Nonetheless, the circulation regularly adapts in the presence of atherosclerosis, through the formation of collateral arteries, resulting in significant long-term health benefits. Therefore, timely detection of coronary collateral circulation (CCC) is crucial for CAD personalized medicine. We propose a novel deep learning based method to detect CCC in angiographic images. Our method relies on a convolutional backbone to extract spatial features from each frame of an angiography sequence. The features are then concatenated, and subsequently processed by another convolutional layer that processes embeddings temporally. Due to scarcity of data, we also experiment with pretraining the backbone on coronary artery segmentation, which improves the results consistently. Moreover, we experiment with few-shot learning to further improve performance, given our low data regime. We present our results together with subgroup analyses based on Rentrop grading, collateral flow, and collateral grading, which provide valuable insights into model performance. Overall, the proposed method shows promising results in detecting CCC, and can be further extended to perform landmark based CCC detection and CCC quantification.
TL;DR: In this article , a two-step approach was proposed to generate the Findings from automated interpretation of medical images, specifically chest X-rays (CXRs), which reduces the workload of radiologists who spend most of their time either writing or narrating Findings.
Abstract: Among all the sub-sections in a typical radiology report, the Clinical Indications, Findings, and Impression often reflect important details about the health status of a patient. The information included in Impression is also often covered in Findings. While Findings and Impression can be deduced by inspecting the image, Clinical Indications often require additional context. The cognitive task of interpreting medical images remains the most critical and often time-consuming step in the radiology workflow. Instead of generating an end-to-end radiology report, in this paper, we focus on generating the Findings from automated interpretation of medical images, specifically chest X-rays (CXRs). Thus, this work focuses on reducing the workload of radiologists who spend most of their time either writing or narrating the Findings. Unlike past research, which addresses radiology report generation as a single-step image captioning task, we have further taken into consideration the complexity of interpreting CXR images and propose a two-step approach: (a) detecting the regions with abnormalities in the image, and (b) generating relevant text for regions with abnormalities by employing a generative large language model (LLM). This two-step approach introduces a layer of interpretability and aligns the framework with the systematic reasoning that radiologists use when reviewing a CXR.