Deep learning-based diagnosis of aortic dissection using an electrocardiogram: Development, validation, and clinical implications of the AADE score.

BACKGROUND: Aortic dissection (AD) is frequently associated with abnormalities in electrocardiographic findings. Advancements in medical technology present an opportunity to leverage these observations to improve patient diagnosis and care. OBJECTIVES: This study aimed to develop a deep learning artificial intelligence (AI) model for AD detection using electrocardiograms (ECGs) and introduce the AI-Aortic-Dissection-ECG (AADE) score to provide clinicians with a measure to determine AD severity. METHODS: From a cohort of 1878 patients, including 313 with AD, and 313 with chest pain (control group), we created training and validation subsets (7:3 ratio). A convolutional neural networks (CNN) model was trained for AD detection, with performance metrics like accuracy and F1 score (the harmonic mean of precision and recall) monitored. The AI-derived AADE score (0-1) was investigated against clinical parameters and ECG features over a median follow-up of 21.2 months. RESULTS: The CNN model demonstrated robust performance with an accuracy of 0.93 and an F1 score of 0.93 for the AD group, and an accuracy of 0.871 with an F1 score of 0.867 for the chest pain group. The AADE score showed correlations with specific ECG patterns and demonstrated that higher scores aligned with increased mortality risk. CONCLUSIONS: Our CNN-based AI model offers a promising approach for AD detection using ECG. The AADE score, based on AI, can serve as a pivotal tool in refining clinical assessments and management strategies.

Artificial intelligence-enabled 8-lead ECG detection of atrial septal defect among adults: a novel diagnostic tool.

Background: Patients with atrial septal defect (ASD) exhibit distinctive electrocardiogram (ECG) patterns. However, ASD cannot be diagnosed solely based on these differences. Artificial intelligence (AI) has been widely used for specifically diagnosing cardiovascular diseases other than arrhythmia. Our study aimed to develop an artificial intelligence-enabled 8-lead ECG to detect ASD among adults. Method: In this study, our AI model was trained and validated using 526 ECGs from patients with ASD and 2,124 ECGs from a control group with a normal cardiac structure in our hospital. External testing was conducted at Wuhan Central Hospital, involving 50 ECGs from the ASD group and 46 ECGs from the normal group. The model was based on a convolutional neural network (CNN) with a residual network to classify 8-lead ECG data into either the ASD or normal group. We employed a 10-fold cross-validation approach. Results: Statistically significant differences (p < 0.05) were observed in the cited ECG features between the ASD and normal groups. Our AI model performed well in identifying ECGs in both the ASD group [accuracy of 0.97, precision of 0.90, recall of 0.97, specificity of 0.97, F1 score of 0.93, and area under the curve (AUC) of 0.99] and the normal group within the training and validation datasets from our hospital. Furthermore, these corresponding indices performed impressively in the external test data set with the accuracy of 0.82, precision of 0.90, recall of 0.74, specificity of 0.91, F1 score of 0.81 and the AUC of 0.87. And the series of experiments of subgroups to discuss specific clinic situations associated to this issue was remarkable as well. Conclusion: An ECG-based detection of ASD using an artificial intelligence algorithm can be achieved with high diagnostic performance, and it shows great clinical promise. Our research on AI-enabled 8-lead ECG detection of ASD in adults is expected to provide robust references for early detection of ASD, healthy pregnancies, and related decision-making. A lower number of leads is also more favorable for the application of portable devices, which it is expected that this technology will bring significant economic and societal benefits.

Study on the relationship between hydrodynamic conditions and arsenic content in Quaternary sediments.

Groundwater is susceptible to arsenic contamination by sediment with high arsenic content, which is the primary culprit of regional arsenic pollution and poisoning. To explore the influence of the change in hydrodynamic conditions caused by changes in the sedimentary environment over time on arsenic content in sediments during the Quaternary, the hydrodynamic characteristics and arsenic content enrichment of borehole sediments were studied in typical high-arsenic groundwater areas of the Jianghan-Dongting Basin, China. The regional hydrodynamic conditions represented by each borehole location were analyzed, the correlation between the variation in groundwater dynamics characteristics and arsenic content in different hydrodynamic periods was analyzed, and the relationship between arsenic content and grain size distribution was quantitatively investigated using grain size parameter calculation, elemental analysis, and statistical estimates of arsenic content in borehole sediments. We observed that the relationship between arsenic content and hydrodynamic conditions differed between sedimentary periods. Furthermore, arsenic content in the sediments from the borehole at Xinfei Village was significantly and positively correlated with a grain size of 127.0-240.0 µm. For the borehole at Wuai Village, arsenic content was significantly and positively correlated with a grain size of 1.38-9.82 µm size (at 0.05 level of significance). However, arsenic content was inversely correlated with grain sizes of 110.99-716.87 and 133.75-282.07 µm at p values of 0.05 and 0.01, respectively. For the borehole at Fuxing Water Works, arsenic content was significantly and positively correlated with a grain size of 409.6-655.0 µm size (at 0.05 level of significance). Arsenic tended to be enriched in transitional and turbidity facies sediments with normal corresponding hydrodynamic strength but poor sorting. Furthermore, continuous and stable sedimentary sequences were conducive to arsenic enrichment. Fine-grain sediments provided abundant potential adsorption sites for high-arsenic sediments, but finer particle size was not correlated with higher arsenic levels.

Coronavirus disease 2019 death prediction by electrocardiographic abnormalities and elevated D-dimer levels.

Background: Electrocardiography (ECG) plays a very important role in various cardiovascular diseases and elevated D-dimer in serum associated with thrombosis. In patients with coronavirus disease 2019 (COVID-19), immense pieces of evidence showed that ECG abnormalities or elevated D-dimer in serum occurred frequently. However, it remains unclear whether ECG abnormalities combined with elevated D-dimer could be a new risk predictor in patients with COVID-19. Methods and results: This retrospective cohort study enrolled 416 patients with COVID-19 at Wuhan Tongji Hospital from 1 February to 20 March 2020. ECG manifestations, D-dimer levels, and in-hospital deaths were recorded for all patients. Logistic regression analysis was performed to examine the association between ECG manifestations and in-hospital mortality in patients with elevated D-dimer levels. In patients hospitalized for COVID-19, ST-T abnormalities (34.3%) were the most frequent ECG manifestations, whereas sinus tachycardia (ST) (13.3%) and atrial arrhythmias with rapid rhythms (8.5%) were the two most common cardiac arrhythmias. Compared to severely ill patients with COVID-19, ST-T abnormalities, ST and atrial arrhythmias (p<0.001) with rapid rhythms, D-dimer levels, and in-hospital deaths were significantly more frequent in critically ill patients with COVID-19. Moreover, elevated D-dimer levels were observed in all the patients who died. In the subgroup of 303 patients with elevated serum D-dimer levels, the patient's age, the incidence of ST-T abnormalities, ST, atrial fibrillation (AF), and atrial premature beat were significantly higher than those in the non-elevated D-dimer subgroup. Multivariate logistic regression analysis further revealed that ST and AF were risk factors for in-hospital mortality in COVID-19 patients with elevated D-dimer levels. Conclusions: ECG abnormalities and elevated D-dimer levels were associated with a higher risk of critical illness and death in patients hospitalized for COVID-19. ECG abnormalities, including ST and AF, combined with elevated D-dimer levels, can be used to predict death in COVID-19.