OBJECTIVES: We propose a myocardial infarction (MI) detection and localization model for improving the diagnostic accuracy for MI to provide assistance to clinical decision-making. METHODS: The proposed model was constructed based on multi-scale field residual blocks fusion modified channel attention (MSF-RB-MCA). The model utilizes lead II electrocardiogram (ECG) signals to detect and localize MI, and extracts different levels of feature information through the multi-scale field residual block. A modified channel attention for automatic adjustment of the feature weights was introduced to enhance the model's ability to focus on the MI region, thereby improving the accuracy of MI detection and localization. RESULTS: A 5-fold cross-validation test of the model was performed using the publicly available Physikalisch-Technische Bundesanstalt (PTB) dataset. For MI detection, the model achieved an accuracy of 99.96% on the test set with a specificity of 99.84% and a sensitivity of 99.99%. For MI localization, the accuracy, specificity and sensitivity were 99.81%, 99.98% and 99.65%, respectively. The performances of the model for MI detection and localization were superior to those of other comparison models. CONCLUSIONS The proposed MSF-RB-MCA model shows excellent performance in AI detection and localization based on lead II ECG signals, demonstrating its great potential for application in wearable devices.
Myocardial Infarction/diagnosis* ; Humans ; Electrocardiography/methods* ; Signal Processing, Computer-Assisted ; Algorithms ; Sensitivity and Specificity

Ankylosing spondylitis (AS) is linked to an increased prevalence of myocardial infarction (MI). However, research dedicated to elucidating the pathogenesis of AS-MI is lacking. In this study, we explored the biomarkers for enhancing the diagnostic and therapeutic efficiency of AS-MI. Datasets were obtained from the Gene Expression Omnibus database. We employed weighted gene co-expression network analysis and machine learning models to screen hub genes. A receiver operating characteristic curve and a nomogram were designed to assess diagnostic accuracy. Gene set enrichment analysis was conducted to reveal the potential function of hub genes. Immune infiltration analysis indicated the correlation between hub genes and the immune landscape. Subsequently, we performed single-cell analysis to identify the expression and subcellular localization of hub genes. We further constructed a transcription factor (TF)-microRNA (miRNA) regulatory network. Finally, drug prediction and molecular docking were performed. S100A12 and MCEMP1 were identified as hub genes, which were correlated with immune-related biological processes. They exhibited high diagnostic value and were predominantly expressed in myeloid cells. Furthermore, 24 TFs and 9 miRNA were associated with these hub genes. Enzastaurin, meglitinide, and nifedipine were predicted as potential therapeutic agents. Our study indicates that S100A12 and MCEMP1 exhibit significant potential as biomarkers and therapeutic targets for AS-MI, offering novel insights into the underlying etiology of this condition.
Humans ; Spondylitis, Ankylosing/complications* ; Systems Biology/methods* ; Myocardial Infarction/diagnosis* ; Biomarkers/metabolism* ; MicroRNAs/genetics* ; Gene Regulatory Networks ; Gene Expression Profiling ; Machine Learning

Objective To identify disulfidptosis-related gene(DRG)in acute myocardial infarction(AMI)by bioinformatics,analyze the molecular pattern of DRGs in AMI,and construct a DRGs-related prediction model.Methods AMI-related datasets were downloaded from the Gene Expression Omnibus database,and DRGs with differential expression were screened in AMI.CIBERSORT method was used to analyze the immune infiltration.Based on the differentially expressed DRGs,the AMI patients were classified into distinct subtypes via consensus clustering,followed by immune infiltration analysis,differential expression analysis,gene ontology and Kyoto encyclopedia of genes and genomes enrichment analysis,and gene set variation analysis.Weighted gene co-expression network analysis(WGCNA)was then performed to construct subtype-associated modules and identify hub genes.Finally,least absolute shrinkage and selection operator,random forest,and support vector machine-recursive feature elimination were used to screen feature genes to construct a DRGs-related prediction model.The model's diagnostic efficacy was evaluated by nomogram and receiver operating characteristic(ROC)curve analysis,followed by external validation.Results Nine differentially expressed DRGs were identified between AMI patients and controls.Based on the expression levels of these nine DRGs,AMI patients were divided into two DRGs subtypes,C1 and C2.Increased infiltration of monocytes,M0 macrophages,and neutrophils was observed in AMI patients and C1 subtype(all P<0.05),indicating a close correlation between DRGs and immune cells.There were 257 differentially expressed genes between the C1 and C2 subtypes,which were related to biological processes such as myeloid leukocyte activation and positive regulation of cytokines.Fcγ receptor-mediated phagocytosis and NOD-like receptor signaling pathway activity were enhanced in C1 subtype.WGCNA analysis suggested that the brown module exhibited the strongest correlation with DRG subtypes(r=0.67),from which 23 differentially expressed genes were identified.The feature genes screened by three machine learning methods were interpolated to obtain a DRGs-related prediction model consisting of three genes(AQP9,F5 and PYGL).Nomogram and ROC curves(AUC_train=0.891,AUC_test=0.840)showed good diagnostic efficacy.Conclusions DRGs were closely related to the occurrence and progression of AMI.The DRGs-related prediction model consisting of AQP9,F5 and PYGL may provide targets for the diagnosis and personalized treatment of AMI.
Humans ; Myocardial Infarction/diagnosis* ; Transcriptome ; Computational Biology ; Gene Expression Profiling ; ROC Curve ; Gene Regulatory Networks ; Nomograms ; Disulfidptosis

OBJECTIVES: To investigate the correlation of serum levels of bridging integrating factor 1 (BIN1) with acute myocardial infarction (AMI) and Killip class of the patients. METHODS: We retrospectively collected the data from 94 patients with AMI and 30 healthy individuals for analysis of the correlations of serum BIN1 levels with Killip class, TIMI scores, and neutrophil-to-lymphocyte ratio (NLR). We also assessed the diagnostic value of BIN1 combined with NLR for AMI. RESULTS: Serum BIN1 levels were significantly lower in AMI patients than in the healthy individuals (P=0.032). The AMI patients with Killip class I had significantly lower serum BIN1 levels than the healthy individuals (P=0.008). Serum BIN1 level was an independent predictor of AMI with a predictive value of 0.630 (95% CI: 0.513-0.748) at the optimal cutoff level of 0.341 ng/mL, a specificity of 50%, and a sensitivity of 78.5%. Serum BIN1 level was also an independent predictor for Killip class I group in the AMI patients with a predictive value of 0.672 (95% CI: 0.548-0.797) at the optimal cutoff level of 0.287 ng/mL, a specificity of 74.1%, and a sensitivity of 60%. For AMI diagnosis, the combination of NLR and serum BIN1 level had a predictive value of 0.811 (95% CI: 0.727-0.895) at the optimal cutoff level of 0.548 ng/mL, with a specificity of 92.6% and a sensitivity of 62.2%. There was a positive correlation between serum BIN1 level and TIMI score in AMI patients (r=0.186, P=0.003). CONCLUSIONS BIN1 is correlated with AMI and can be helpful for predicting short-term prognosis of the patients, and BIN1 combined with NLR has a high diagnostic value for AMI.
Humans ; Myocardial Infarction/diagnosis* ; Tumor Suppressor Proteins/blood* ; Adaptor Proteins, Signal Transducing/blood* ; Retrospective Studies ; Nuclear Proteins/blood* ; Lymphocytes/cytology* ; Neutrophils/cytology* ; Female ; Male ; Prognosis ; Middle Aged

Myocardial infarction (MI) has the characteristics of high mortality rate, strong suddenness and invisibility. There are problems such as the delayed diagnosis, misdiagnosis and missed diagnosis in clinical practice. Electrocardiogram (ECG) examination is the simplest and fastest way to diagnose MI. The research on MI intelligent auxiliary diagnosis based on ECG is of great significance. On the basis of the pathophysiological mechanism of MI and characteristic changes in ECG, feature point extraction and morphology recognition of ECG, along with intelligent auxiliary diagnosis method of MI based on machine learning and deep learning are all summarized. The models, datasets, the number of ECG, the number of leads, input modes, evaluation methods and effects of different methods are compared. Finally, future research directions and development trends are pointed out, including data enhancement of MI, feature points and dynamic features extraction of ECG, the generalization and clinical interpretability of models, which are expected to provide references for researchers in related fields of MI intelligent auxiliary diagnosis.
Humans ; Electrocardiography ; Myocardial Infarction/diagnosis* ; Recognition, Psychology

OBJECTIVE: To investigate the value of T2 mapping in the assessment of myocardial changes and prognosis in patients with acute ST segment elevation myocardial infarction (STEMI). METHODS: A retrospective study was conducted. A total of 30 patients with acute STEMI admitted to Tianjin First Central Hospital from January 2021 to March 2022 were enrolled as the experimental group. At the same time, 30 age- and sex-matched healthy volunteers and outpatients with non-specific chest pain with no abnormalities in cardiac magnetic resonance (CMR) examination were selected as the control group. CMR was performed within 2 weeks after the diagnosis of STEMI, as the initial reference. A plain CMR review was performed 6 months later (chronic myocardial infarction, CMI). Plain scanning includes film sequence (CINE), T2 weighted short tau inversion recovery (T2-STIR), native-T1 mapping, and T2 mapping. Enhanced scanning includes first-pass perfusion, late gadolinium enhancement (LGE), and post-contrast T1 mapping. Quantitative myocardial parameters were compared between the two groups, before and after STEMI myocardial infarction. The receiver operator characteristic curve (ROC curve) was used to evaluate the diagnostic efficacy of native-T1 before myocardial contrast enhancement and T2 values in differentiating STEMI and CMI after 6 months. RESULTS: There were no statistically significant differences in age, gender, heart rate and body mass index (BMI) between the two groups, which were comparable. The native-T1 value, T2 value and extracellular volume (ECV) were significantly higher than those in the control group [native-T1 value (ms): 1 434.5±165.3 vs. 1 237.0±102.5, T2 value (ms): 48.3±15.6 vs. 21.8±13.1, ECV: (39.6±13.8)% vs. (22.8±5.0)%, all P < 0.05]. In the experimental group, 12 patients were re-examined by plain CMR scan 6 months later. After 6 months, the high signal intensity on T2-STIR was still visible, but the range was smaller than that in the acute phase, and the native-T1 and T2 values were significantly lower than those in the acute phase [native-T1 value (ms): 1 271.0±26.9 vs. 1 434.5±165.3, T2 value (ms): 34.2±11.2 vs. 48.3±15.6, both P < 0.05]. ROC curve analysis showed that the area under the ROC curve (AUC) of native-T1 and T2 values in differentiating acute STEMI from CMI was 0.71 and 0.80, respectively. When native-T1 cut-off value was 1 316.0 ms, the specificity was 100% and the sensitivity was 53.3%; when T2 cut-off value was 46.7 ms, the specificity was 100% and the sensitivity was 73.8%. CONCLUSIONS The T2 mapping is a non-invasive method for the diagnosis of myocardial changes in patients with acute STEMI myocardial infarction, and can be used to to evaluate the clinical prognosis of patients.
Humans ; ST Elevation Myocardial Infarction/diagnosis* ; Contrast Media ; Prognosis ; Retrospective Studies ; Magnetic Resonance Imaging, Cine/methods* ; Gadolinium ; Myocardium/pathology* ; Myocardial Infarction ; Predictive Value of Tests

OBJECTIVE: To evaluate the accuracy of cardiac troponin (cTn) levels in the diagnosis of acute myocardial infarction (AMI) in patients with chronic kidney disease (CKD) and explore a potential strategy for improving the diagnostic accuracy. METHODS: We retrospectively analyzed the data from patients with high-risk chest pain admitted in Zhujiang Hospital from January, 2018 to December, 2020, including 126 patients with and 272 patients without CKD, and 122 patients diagnosed to have AMI and 276 patients without AMI. The baseline clinical data of the patients and blood test results within 12 h after admission were collected. RESULTS: In patients without AMI, cTnT level was significantly higher in those with co-morbid CKD than in those without CKD (P < 0.001), and showed a moderate negative correlation with eGFR (r_s=- 0.501, P < 0.001), while cTnI level did not differ significantly between the two groups (P=0.72). In patients with CKD, the optimal cutoff level was 0.177 μg/L for cTnT and 0.415 ng/mL for cTnI for diagnosis of AMI, for which cTnI had a higher specificity than cTnT. The diagnostic model combining both cTnT and cTnI levels [P=e^Y/(1+ e^Y), Y=6.928 (cTnT)-0.5 (cTnI)-1.491] had a higher AUC value than cTn level alone. CONCLUSION In CKD patients, the cutoff level of cTn is increased for diagnosing AMI, and cTnI has a higher diagnostic specificity than cTnT. The combination of cTnT and cTnI levels may further improve diagnostic efficacy for AMI.
Humans ; Retrospective Studies ; Myocardial Infarction/diagnosis* ; Comorbidity ; Troponin T ; Troponin I ; Renal Insufficiency, Chronic/diagnosis* ; Biomarkers

OBJECTIVE: We aimed to assess the feasibility and superiority of machine learning (ML) methods to predict the risk of Major Adverse Cardiovascular Events (MACEs) in chest pain patients with NSTE-ACS. METHODS: Enrolled chest pain patients were from two centers, Beijing Anzhen Emergency Chest Pain Center Beijing Bo'ai Hospital, China Rehabilitation Research Center. Five classifiers were used to develop ML models. Accuracy, Precision, Recall, F-Measure and AUC were used to assess the model performance and prediction effect compared with HEART risk scoring system. Ultimately, ML model constructed by Naïve Bayes was employed to predict the occurrence of MACEs. RESULTS: According to learning metrics, ML models constructed by different classifiers were superior over HEART (History, ECG, Age, Risk factors, & Troponin) scoring system when predicting acute myocardial infarction (AMI) and all-cause death. However, according to ROC curves and AUC, ML model constructed by different classifiers performed better than HEART scoring system only in prediction for AMI. Among the five ML algorithms, Linear support vector machine (SVC), Naïve Bayes and Logistic regression classifiers stood out with all Accuracy, Precision, Recall and F-Measure from 0.8 to 1.0 for predicting any event, AMI, revascularization and all-cause death ( vs. HEART ≤ 0.78), with AUC from 0.88 to 0.98 for predicting any event, AMI and revascularization ( vs. HEART ≤ 0.85). ML model developed by Naïve Bayes predicted that suspected acute coronary syndrome (ACS), abnormal electrocardiogram (ECG), elevated hs-cTn I, sex and smoking were risk factors of MACEs. CONCLUSION Compared with HEART risk scoring system, the superiority of ML method was demonstrated when employing Linear SVC classifier, Naïve Bayes and Logistic. ML method could be a promising method to predict MACEs in chest pain patients with NSTE-ACS.
Humans ; Acute Coronary Syndrome/epidemiology* ; Bayes Theorem ; Feasibility Studies ; Risk Assessment/methods* ; Chest Pain/etiology* ; Myocardial Infarction/diagnosis*

Objective: To explore associations between lipoprotein-associated phospholipase A2 (Lp-PLA2) and the risk of cardiovascular events in a Chinese population, with a long-term follow-up. Methods: A random sample of 2,031 participants (73.6% males, mean age = 60.4 years) was derived from the Asymptomatic Polyvascular Abnormalities Community study (APAC) from 2010 to 2011. Serum Lp-PLA2 levels were determined by enzyme-linked immunosorbent assay (ELISA). The composite endpoint was a combination of first-ever stroke, myocardial infarction (MI) or all-cause death. Lp-PLA2 associations with outcomes were assessed using Cox models. Results: The median Lp-PLA2 level was 141.0 ng/mL. Over a median follow-up of 9.1 years, we identified 389 events (19.2%), including 137 stroke incidents, 43 MIs, and 244 all-cause deaths. Using multivariate Cox regression, when compared with the lowest Lp-PLA2 quartile, the hazard ratios with 95% confidence intervals for developing composite endpoints, stroke, major adverse cardiovascular events, and all-cause death were 1.77 (1.24-2.54), 1.92 (1.03-3.60), 1.69 (1.003-2.84), and 1.94 (1.18-3.18) in the highest quartile, respectively. Composite endpoints in 145 (28.6%) patients occurred in the highest quartile where Lp-PLA2 (159.0 ng/mL) was much lower than the American Association of Clinical Endocrinologists recommended cut-off point, 200 ng/mL. Conclusion Higher Lp-PLA2 levels were associated with an increased risk of cardiovascular event/death in a middle-aged Chinese population. The Lp-PLA2 cut-off point may be lower in the Chinese population when predicting cardiovascular events.
1-Alkyl-2-acetylglycerophosphocholine Esterase/blood* ; Asians ; Cardiovascular Diseases/diagnosis* ; China/epidemiology* ; Female ; Humans ; Longitudinal Studies ; Male ; Middle Aged ; Mortality ; Myocardial Infarction/blood* ; Predictive Value of Tests ; Risk Factors ; Stroke/blood*

OBJECTIVE: To assess the value of wearable 12-lead electrocardiogram (ECG) devices in pre-hospital diagnosis of acute ST segment elevation myocardial infarction (STEMI). METHODS: This analysis was conducted among 441 patients selected from the''National ECG Network'', who used wearable 12-lead ECG device with critical situation warning of ST change between January 2019, and August, 2021.The general characteristics, response time and complaints of the patients with STEMI were analyzed.The accuracy of pre-hospital diagnosis of STEMI was compared between clinician's interpretation of ECGs and AI diagnosis by the wearable ECG device. RESULTS: In 89 of the patients, a pre-hospital diagnosis of STEMI was made by physicians based on ECGs from the wearable devices, and 58 of them sought medical attention after online warning, with a referral rate of 65.17%.The average time for diagnostic assessment of the ECGs was 153.02 s, and the average time for confirmation of the diagnosis was 178.06 s.The sensitivity for pre-hospital diagnosis of STEMI by clinician's interpretation of the ECGs and by AI diagnosis was 100% and 88.37%, respectively, with a specificity of 95.40% and 79.31%, respectively.The pre-hospital diagnosis by clinicians and AI diagnosis of STEMI both showed a high consistency with the subsequent definite clinical diagnosis of STEMI. CONCLUSION Wearable 12-lead ECG devices can accurately record ECG characteristics of STEMI patients outside the hospital and allow immediate data uploading for an early diagnosis.The diagnoses of STEMI made based on AI technology are highly consistent with those by clinicians, demonstrating excellent clinical performance of the wearable ECG devices.
Humans ; ST Elevation Myocardial Infarction/diagnosis* ; Electrocardiography ; Arrhythmias, Cardiac ; Wearable Electronic Devices ; Hospitals