A Machine Learning Framework for Diagnosing and Predicting the Severity of Coronary Artery Disease.

Background: Although machine learning (ML)-based prediction of coronary artery disease (CAD) has gained increasing attention, assessment of the severity of suspected CAD in symptomatic patients remains challenging. Methods: The training set for this study consisted of 284 retrospective participants, while the test set included 116 prospectively enrolled participants from whom we collected 53 baseline variables and coronary angiography results. The data was pre-processed with outlier processing and One-Hot coding. In the first stage, we constructed a ML model that used baseline information to predict the presence of CAD with a dichotomous model. In the second stage, baseline information was used to construct ML regression models for predicting the severity of CAD. The non-CAD population was included, and two different scores were used as output variables. Finally, statistical analysis and SHAP plot visualization methods were employed to explore the relationship between baseline information and CAD. Results: The study included 269 CAD patients and 131 healthy controls. The eXtreme Gradient Boosting (XGBoost) model exhibited the best performance amongst the different models for predicting CAD, with an area under the receiver operating characteristic curve of 0.728 (95% CI 0.623-0.824). The main correlates were left ventricular ejection fraction, homocysteine, and hemoglobin (p < 0.001). The XGBoost model performed best for predicting the SYNTAX score, with the main correlates being brain natriuretic peptide (BNP), left ventricular ejection fraction, and glycated hemoglobin (p < 0.001). The main relevant features in the model predictive for the GENSINI score were BNP, high density lipoprotein, and homocysteine (p < 0.001). Conclusions: This data-driven approach provides a foundation for the risk stratification and severity assessment of CAD. Clinical Trial Registration: The study was registered in www.clinicaltrials.gov protocol registration system (number NCT05018715).

Investigation of waste alkali-activated cementing material using municipal solid waste incineration fly ash and dravite as precursors: Mechanisms, performance, and on-site application.

The proper treatment of municipal solid waste incineration fly ash (MSWIFA) is a crucial concern due to its hazardous nature and potential environmental harm. To address this issue, this study innovatively utilized dravite and black liquor to solidify MSWIFA. The semi-dry pressing method was employed, resulting in the production of waste alkali-activated cementing material (WACM). This material demonstrated impressive compressive and flexural strength, reaching 45.89 MPa and 6.55 MPa respectively, and effectively solidified heavy metal ions (Pb, Cr, Cu, Cd, and Zn). The leaching concentrations of these ions decreased from 27.15, 10.36, 8.94, 7.00, and 104.4 mg/L to 0.13, 1.05, 0.29, 0.06, and 12.28 mg/L, respectively. The strength of WACM increased by 3 times compared to conventionally produced materials. Furthermore, WACM exhibited excellent long-term performance, with acceptable heavy metal leaching and minimal mechanical degradation. Experimental and theoretical analyses revealed the heavy metal solidification mechanisms, including chemical binding, ion substitution and physical encapsulation. Finally, the on-site application of WACM confirmed its feasibility in meeting both environmental and strength requirements.

Effect of infarct location and volume on cognitive dysfunction in elderly patients with acute insular cerebral infarction.

BACKGROUND: The aging of the population has become increasingly obvious in recent years, and the incidence of cerebral infarction has shown an increasing trend annually, with high death and disability rates. AIM: To analyze the effects of infarct location and volume on cognitive dysfunction in elderly patients with acute insular cerebral infarction. METHODS: Between January 2020 and December 2023, we treated 98 cases of elderly acute insula, patients with cerebral infarction in the cerebral infarction acute phase (3-4 weeks) and for the course of 6 months in Montreal Cognitive Assessment Scale (MoCA) for screening of cognition. Notably, 58 and 40 patients were placed in the cognitive impairment group and without-cognitive impairment group, respectively. In patients with cerebral infarction, magnetic resonance imaging was used to screen and clearly analyze the MoCA scores of two groups of patients with different infarctions, the relationship between the parts of the infarction volume, and analysis of acute insula cognitive disorder in elderly patients with cerebral infarction and the relationship between the two. RESULTS: The number of patients with cognitive impairment in the basal ganglia and thalamus was significantly higher than that without cognitive impairment (P < 0.05). The total infarct volume in the cognitive impairment group was higher than that in the non-cognitive impairment group, and the difference was statistically significant (P < 0.05). The infarct volumes at different sites in the cognitive impairment group was higher than in the non-cognitive impairment group (P < 0.05). In the cognitive impairment group, the infarct volumes in the basal ganglia, thalamus, and mixed lesions were negatively correlated with the total MoCA score, with correlation coefficients of -0.67, -0.73, and -0.77, respectively. CONCLUSION: In elderly patients with acute insular infarction, infarction in the basal ganglia, thalamus, and mixed lesions were more likely to lead to cognitive dysfunction than in other areas, and patients with large infarct volumes were more likely to develop cognitive dysfunction. The infarct volume in the basal ganglia, thalamus, and mixed lesions was significantly negatively correlated with the MoCA score.

Deep learning of heart-sound signals for efficient prediction of obstructive coronary artery disease.

Background: Due to the limitations of current methods for detecting obstructive coronary artery disease (CAD), many individuals are mistakenly or unnecessarily referred for coronary angiography (CAG). Objectives: Our goal is to create a comprehensive database of heart sounds in CAD and develop accurate deep learning algorithms to efficiently detect obstructive CAD based on heart sound signals. This will enable effective screening before undergoing CAG. Methods: We included 320 subjects suspected of CAD who underwent CAG. We employed advanced filtering techniques and state-of-the-art deep learning models (VGG-16, 1D CNN, and ResNet18) to analyze the heart sound signals and identify obstructive CAD (defined as at least one ≥50 % stenosis). To assess the performance of our models, we prospectively recruited an additional 80 subjects for testing. Results: In the test set, VGG-16 exhibited the highest performance with an area under the ROC curve (AUC) of 0.834 (95 % CI, 0.736-0.930), while ResNet-18 and CNN-7 achieved AUCs of only 0.755 (95 % CI, 0.614-0.819) and 0.652 (95 % CI, 0.554-0.770) respectively. VGG-16 demonstrated a sensitivity of 80.4 % and specificity of 86.2 % in the test set. The combined diagnostic model of VGG and DF scores achieved an AUC of 0.915 (95 % CI: 0.855-0.974), and the AUC for VGG combined with PTP scores was 0.908 (95 % CI: 0.845-0.971). The sensitivity and specificity of VGG-16 exceeded 0.85 in patients with coronary artery occlusion and those with 3 vascular lesions. Conclusions: Our deep learning model, based on heart sounds, offers a non-invasive and efficient screening method for obstructive CAD. It is expected to significantly reduce the number of unnecessary referrals for downstream screening.