Artificial Intelligence-Based Atrial Fibrillation Recognition Method for Motion Artifact-Contaminated Electrocardiogram Signals Preprocessed by Adaptive Filtering Algorithm.

Atrial fibrillation (AF) is a common arrhythmia, and out-of-hospital, wearable, long-term electrocardiogram (ECG) monitoring can help with the early detection of AF. The presence of a motion artifact (MA) in ECG can significantly affect the characteristics of the ECG signal and hinder early detection of AF. Studies have shown that (a) using reference signals with a strong correlation with MAs in adaptive filtering (ADF) can eliminate MAs from the ECG, and (b) artificial intelligence (AI) algorithms can recognize AF when there is no presence of MAs. However, no literature has been reported on whether ADF can improve the accuracy of AI for recognizing AF in the presence of MAs. Therefore, this paper investigates the accuracy of AI recognition for AF when ECGs are artificially introduced with MAs and processed by ADF. In this study, 13 types of MA signals with different signal-to-noise ratios ranging from +8 dB to -16 dB were artificially added to the AF ECG dataset. Firstly, the accuracy of AF recognition using AI was obtained for a signal with MAs. Secondly, after removing the MAs by ADF, the signal was further identified using AI to obtain the accuracy of the AF recognition. We found that after undergoing ADF, the accuracy of AI recognition for AF improved under all MA intensities, with a maximum improvement of 60%.

Developing a Five-Minute Normative Database of Heart Rate Variability for Diagnosing Cardiac Autonomic Dysregulation for Patients with Major Depressive Disorder.

Heart rate variability (HRV) is related to cardiac vagal control and emotional regulation and an index for cardiac vagal control and cardiac autonomic activity. This study aimed to develop the Taiwan HRV normative database covering individuals aged 20 to 70 years and to assess its diagnosing validity in patients with major depressive disorder (MDD). A total of 311 healthy participants were in the HRV normative database and divided into five groups in 10-year age groups, and then the means and standard deviations of the HRV indices were calculated. We recruited 272 patients with MDD for cross-validation, compared their HRV indices with the normative database, and then converted them to Z-scores to explore the deviation of HRV in MDD patients from healthy groups. The results found a gradual decline in HRV indices with advancing age in the HC group, and females in the HC group exhibit higher cardiac vagal control and parasympathetic activity than males. Conversely, patients in the MDD group demonstrate lower HRV indices than those in the HC group, with their symptoms of depression and anxiety showing a negative correlation with HRV indices. The Taiwan HRV normative database has good psychometric characteristics of cross-validation.

[Fetal electrocardiogram signal extraction based on multi-scale residual shrinkage U-Net].

In the extraction of fetal electrocardiogram (ECG) signal, due to the unicity of the scale of the U-Net same-level convolution encoder, the size and shape difference of the ECG characteristic wave between mother and fetus are ignored, and the time information of ECG signals is not used in the threshold learning process of the encoder's residual shrinkage module. In this paper, a method of extracting fetal ECG signal based on multi-scale residual shrinkage U-Net model is proposed. First, the Inception and time domain attention were introduced into the residual shrinkage module to enhance the multi-scale feature extraction ability of the same level convolution encoder and the utilization of the time domain information of fetal ECG signal. In order to maintain more local details of ECG waveform, the maximum pooling in U-Net was replaced by Softpool. Finally, the decoder composed of the residual module and up-sampling gradually generated fetal ECG signals. In this paper, clinical ECG signals were used for experiments. The final results showed that compared with other fetal ECG extraction algorithms, the method proposed in this paper could extract clearer fetal ECG signals. The sensitivity, positive predictive value, and F1 scores in the 2013 competition data set reached 93.33%, 99.36%, and 96.09%, respectively, indicating that this method can effectively extract fetal ECG signals and has certain application values for perinatal fetal health monitoring.

Advancing Cardiovascular Risk Assessment with Artificial Intelligence: Opportunities and Implications in North Carolina.

Cardiovascular disease mortality is increasing in North Carolina with persistent inequality by race, income, and location. Artificial intelligence (AI) can repurpose the widely available electrocardiogram (ECG) for enhanced assessment of cardiac dysfunction. By identifying accelerated cardiac aging from the ECG, AI offers novel insights into risk assessment and prevention.

A multimodal physiological and psychological dataset for human with mental stress induced myocardial ischemia.

Accurate differentiation between angina with no obstructive coronary arteries (ANOCA) and mental stress-induced myocardial ischemia (MSIMI) is crucial for tailored treatment strategies, yet public data scarcity hampers understanding. Given the higher incidence of both conditions in women, this study prospectively enrolled 80 female ANOCA and 39 age-matched female controls, subjecting them to three types of mental stress tasks. ECGs were continuously monitored across Rest, Stress, and Recover stages of the mental stress tasks, with PET/CT imaging during the Stress stage to evaluate myocardial perfusion. With PET/CT serving as the gold standard for MSIMI diagnosis, 35 of the 80 ANOCA patients were diagnosed as MSIMI. Using ECG variables from different stages of mental stress tasks, we developed five machine learning models to diagnose MSIMI. The results showed that ECG data from different stages provide valuable information for MSIMI classification. Additionally, the dataset encompassed demographic details, physiological, and blood sample test results of the patients. We anticipate this new dataset will significantly push further progress in ANOCA and MSIMI research.

Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias.

The efficacy of an implantable cardioverter-defibrillator (ICD) in patients with a non-ischaemic cardiomyopathy for primary prevention of sudden cardiac death is increasingly debated. We developed a multimodal deep learning model for arrhythmic risk prediction that integrated late gadolinium enhanced (LGE) cardiac magnetic resonance imaging (MRI), electrocardiography (ECG) and clinical data. Short-axis LGE-MRI scans and 12-lead ECGs were retrospectively collected from a cohort of 289 patients prior to ICD implantation, across two tertiary hospitals. A residual variational autoencoder was developed to extract physiological features from LGE-MRI and ECG, and used as inputs for a machine learning model (DEEP RISK) to predict malignant ventricular arrhythmia onset. In the validation cohort, the multimodal DEEP RISK model predicted malignant ventricular arrhythmias with an area under the receiver operating characteristic curve (AUROC) of 0.84 (95% confidence interval (CI) 0.71-0.96), a sensitivity of 0.98 (95% CI 0.75-1.00) and a specificity of 0.73 (95% CI 0.58-0.97). The models trained on individual modalities exhibited lower AUROC values compared to DEEP RISK [MRI branch: 0.80 (95% CI 0.65-0.94), ECG branch: 0.54 (95% CI 0.26-0.82), Clinical branch: 0.64 (95% CI 0.39-0.87)]. These results suggest that a multimodal model achieves high prognostic accuracy in predicting ventricular arrhythmias in a cohort of patients with non-ischaemic systolic heart failure, using data collected prior to ICD implantation.

USP38 exacerbates pressure overload-induced left ventricular electrical remodeling.

BACKGROUND: Ubiquitin-specific protease 38 (USP38), belonging to the USP family, is recognized for its role in controlling protein degradation and diverse biological processes. Ventricular arrhythmias (VAs) following heart failure (HF) are closely linked to ventricular electrical remodeling, yet the specific mechanisms underlying VAs in HF remain inadequately explored. In this study, we examined the impact of USP38 on VAs in pressure overload-induced HF. METHODS: Cardiac-specific USP38 knockout mice, cardiac-specific USP38 transgenic mice and their matched control littermates developed HF induced by aortic banding (AB) surgery. After subjecting the mice to AB surgery for a duration of four weeks, comprehensive investigations were conducted, including pathological analysis and electrophysiological assessments, along with molecular analyses. RESULTS: We observed increased USP38 expression in the left ventricle of mice with HF. Electrocardiogram showed that the USP38 knockout shortened the QRS interval and QTc, while USP38 overexpression prolonged these parameters. USP38 knockout decreased the susceptibility of VAs by shortening action potential duration (APD) and prolonging effective refractory period (ERP). In addition, USP38 knockout increased ion channel and Cx43 expression in ventricle. On the contrary, the increased susceptibility of VAs and the decreased expression of ventricular ion channels and Cx43 were observed with USP38 overexpression. In both in vivo and in vitro experiments, USP38 knockout inhibited TBK1/AKT/CAMKII signaling, whereas USP38 overexpression activated this pathway. CONCLUSION: Our data indicates that USP38 increases susceptibility to VAs after HF through TBK1/AKT/CAMKII signaling pathway, Consequently, USP38 may emerge as a promising therapeutic target for managing VAs following HF.

Accelerated idioventricular rhythm as a manifestation of chronic renocardiac syndrome: A case report.

In this case report, we describe a patient who presented with chronic symptoms and signs of uremia and persistent accelerated idioventricular rhythm (AIVR) on electrocardiogram. Findings from blood tests, echocardiography, renal ultrasound, and renal scan were suggestive of heart failure with reduced ejection fraction and chronic kidney disease, and attendance of daily hemodialysis sessions led to the restoration of sinus rhythm. Typically, AIVR has a favorable prognosis and, if necessary, medical intervention focuses on addressing the underlying responsible causes. Accumulation of uremic toxins has the potential to trigger the formation of AIVR and clearance of small solutes through conventional hemodialysis may contribute to sinus rhythm restoration.

Data imbalance in cardiac health diagnostics using CECG-GAN.

Heart disease is the world's leading cause of death. Diagnostic models based on electrocardiograms (ECGs) are often limited by the scarcity of high-quality data and issues of data imbalance. To address these challenges, we propose a conditional generative adversarial network (CECG-GAN). This strategy enables the generation of samples that closely approximate the distribution of ECG data. Additionally, CECG-GAN addresses waveform jitter, slow processing speeds, and dataset imbalance issues through the integration of a transformer architecture. We evaluated this approach using two datasets: MIT-BIH and CSPC2020. The experimental results demonstrate that CECG-GAN achieves outstanding performance metrics. Notably, the percentage root mean square difference (PRD) reached 55.048, indicating a high degree of similarity between generated and actual ECG waveforms. Additionally, the Fréchet distance (FD) was approximately 1.139, the root mean square error (RMSE) registered at 0.232, and the mean absolute error (MAE) was recorded at 0.166.

Empagliflozin's role in reducing ventricular repolarization heterogeneity: insights into cardiovascular mortality decline from the EMPATHY-HEART trial.

BACKGROUND: The incidence of myocardial infarction (MI) and sudden cardiac death (SCD) is significantly higher in individuals with Type 2 Diabetes Mellitus (T2DM) than in the general population. Strategies for the prevention of fatal arrhythmias are often insufficient, highlighting the need for additional non-invasive diagnostic tools. The T-wave heterogeneity (TWH) index measures variations in ventricular repolarization and has emerged as a promising predictor for severe ventricular arrhythmias. Although the EMPA-REG trial reported reduced cardiovascular mortality with empagliflozin, the underlying mechanisms remain unclear. This study investigates the potential of empagliflozin in mitigating cardiac electrical instability in patients with T2DM and coronary heart disease (CHD) by examining changes in TWH. METHODS: Participants were adult outpatients with T2DM and CHD who exhibited TWH > 80 µV at baseline. They received a 25 mg daily dose of empagliflozin and were evaluated clinically including electrocardiogram (ECG) measurements at baseline and after 4 weeks. TWH was computed from leads V4, V5, and V6 using a validated technique. The primary study outcome was a significant (p < 0.05) change in TWH following empagliflozin administration. RESULTS: An initial review of 6,000 medical records pinpointed 800 patients for TWH evaluation. Of these, 412 exhibited TWH above 80 µV, with 97 completing clinical assessments and 90 meeting the criteria for high cardiovascular risk enrollment. Empagliflozin adherence exceeded 80%, resulting in notable reductions in blood pressure without affecting heart rate. Side effects were generally mild, with 13.3% experiencing Level 1 hypoglycemia, alongside infrequent urinary and genital infections. The treatment consistently reduced mean TWH from 116 to 103 µV (p = 0.01). CONCLUSIONS: The EMPATHY-HEART trial preliminarily suggests that empagliflozin decreases heterogeneity in ventricular repolarization among patients with T2DM and CHD. This reduction in TWH may provide insight into the mechanism behind the decreased cardiovascular mortality observed in previous trials, potentially offering a therapeutic pathway to mitigate the risk of severe arrhythmias in this population. TRIAL REGISTRATION: NCT: 04117763.

Genetic characterization of KCNQ1 variants improves risk stratification in type 1 long QT syndrome patients.

AIMS: KCNQ1 mutations cause QTc prolongation increasing life-threatening arrhythmias risks. Heterozygous mutations [type 1 long QT syndrome (LQT1)] are common. Homozygous KCNQ1 mutations cause type 1 Jervell and Lange-Nielsen syndrome (JLNS) with deafness and higher sudden cardiac death risk. KCNQ1 variants causing JLNS or LQT1 might have distinct phenotypic expressions in heterozygous patients. The aim of this study is to evaluate QTc duration and incidence of long QT syndrome-related cardiac events according to genetic presentation. METHODS AND RESULTS: We enrolled LQT1 or JLNS patients with class IV/V KCNQ1 variants from our inherited arrhythmia clinic (September 1993 to January 2023). Medical history, ECG, and follow-up were collected. Additionally, we conducted a thorough literature review for JLNS variants. Survival curves were compared between groups, and multivariate Cox regression models identified genetic and clinical risk factors. Among the 789 KCNQ1 variant carriers, 3 groups were identified: 30 JLNS, 161 heterozygous carriers of JLNS variants (HTZ-JLNS), and 550 LQT1 heterozygous carriers of non-JLNS variants (HTZ-Non-JLNS). At diagnosis, mean age was 3.4 ± 4.7 years for JLNS, 26.7 ± 21 years for HTZ-JLNS, and 26 ± 21 years for HTZ-non-JLNS; 55.3% were female; and the mean QTc was 551 ± 54 ms for JLNS, 441 ± 32 ms for HTZ-JLNS, and 467 ± 36 ms for HTZ-Non-JLNS. Patients with heterozygous JLNS mutations (HTZ-JLNS) represented 22% of heterozygous KCNQ1 variant carriers and had a lower risk of cardiac events than heterozygous non-JLNS variant carriers (HTZ-Non-JLNS) [hazard ratio (HR) = 0.34 (0.22-0.54); P < 0.01]. After multivariate analysis, four genetic parameters were independently associated with events: haploinsufficiency [HR = 0.60 (0.37-0.97); P = 0.04], pore localization [HR = 1.61 (1.14-1.2.26); P < 0.01], C-terminal localization [HR = 0.67 (0.46-0.98); P = 0.04], and group [HR = 0.43 (0.27-0.69); P < 0.01]. CONCLUSION: Heterozygous carriers of JLNS variants have a lower risk of cardiac arrhythmic events than other LQT1 patients.

Evaluation of the ODISEA APP for improving a STEMI regional network.

BACKGROUND: The use of technological innovations in ST elevation myocardial infarction (STEMI) care networks has been shown to be effective in improving information flow and coordination, and thus reducing the time to reperfusion. We developed a smartphone application called ODISEA to improve our STEMI care network and evaluated the results of its use. METHOD: Quasi-experimental study that compared the outcomes of STEMI suspected patients with an alert and indication for transfer to a cath lab during a previous period and a period in which the ODISEA APP was used. The main objective was to examine differences in reperfusion time and the proportion of patients with a final diagnosis other than acute coronary syndrome. RESULTS: A total of 699 patients were included (415 before and 284 during the ODISEA-APP period). No differences were observed in patient characteristics, infarct type, or acute complications. We observed a reduction in the time from diagnostic ECG to wire crossing with the use of the ODISEA APP (117 vs 102 min, p < 0.001) and a reduction in the percentage of patients with a final diagnosis other than acute coronary syndrome (17.1% vs 9.5%, p = 0.004). CONCLUSIONS: The use of the ODISEA APP in the management of patients with suspected STEMI may be useful for reducing the time from diagnostic ECG to wire crossing and the percentage of patients with a final diagnosis other than acute coronary syndrome.

Genetic background determines the severity of age-dependent cardiac structural abnormalities and arrhythmia susceptibility in Scn5a-1798insD mice.

AIMS: Patients with mutations in SCN5A encoding NaV1.5 often display variable severity of electrical and structural alterations, but the underlying mechanisms are not fully elucidated. We here investigate the combined modulatory effect of genetic background and age on disease severity in the Scn5a1798insD/+ mouse model. METHODS AND RESULTS: In vivo electrocardiogram and echocardiograms, ex vivo electrical and optical mapping, and histological analyses were performed in adult (2-7 months) and aged (8-28 months) wild-type (WT) and Scn5a1798insD/+ (mutant, MUT) mice from the FVB/N and 129P2 inbred strains. Atrio-ventricular (AV) conduction, ventricular conduction, and ventricular repolarization are modulated by strain, genotype, and age. An aging effect was present in MUT mice, with aged MUT mice of both strains showing prolonged QRS interval and right ventricular (RV) conduction slowing. 129P2-MUT mice were severely affected, with adult and aged 129P2-MUT mice displaying AV and ventricular conduction slowing, prolonged repolarization, and spontaneous arrhythmias. In addition, the 129P2 strain appeared particularly susceptible to age-dependent electrical, functional, and structural alterations including RV conduction slowing, reduced left ventricular (LV) ejection fraction, RV dilatation, and myocardial fibrosis as compared to FVB/N mice. Overall, aged 129P2-MUT mice displayed the most severe conduction defects, RV dilatation, and myocardial fibrosis, in addition to the highest frequency of spontaneous arrhythmia and inducible arrhythmias. CONCLUSION: Genetic background and age both modulate disease severity in Scn5a1798insD/+ mice and hence may explain, at least in part, the variable disease expressivity observed in patients with SCN5A mutations. Age- and genetic background-dependent development of cardiac structural alterations furthermore impacts arrhythmia risk. Our findings therefore emphasize the importance of continued assessment of cardiac structure and function in patients carrying SCN5A mutations.

Cross-sectional study on the health of workers exposed to occupational noise in China.

OBJECTIVE: This study aimed to understand the health of workers exposed to occupational noise and explore the influencing factors related to workers' health, especially the impact of noise on workers' hearing. This work can provide a basis for formulating relevant measures for occupational noise prevention and control in the future. METHODS: On the basis of the key occupational disease monitoring project in Chongqing, China, in 2021, the data of 1125 workers exposed to occupational noise were analyzed. Data included demographic information, occupational history, clinical physical examination information, and noise detection information of the working environment. Chi-square test and multifactorial logistic regression were used for statistical analysis. RESULTS: The prevalence rates of abnormal electrocardiogram (ECG), blood pressure (BP), and pure tone audiometry (PTA) were 21.9% (246/1125), 27.8% (313/1125), and 18.0% (202/1125), respectively. Male workers accounted for 78.8%. Compared with male workers, female workers had a lower prevalence of abnormal PTA (OR = 0.28, 95% CI = 0.16-0.50). Workers working in medium enterprises had a lower prevalence of abnormal BP than workers in micro enterprises (OR = 0.36, 95% CI = 0.19-0.66). The prevalence of abnormal BP and PTA of workers increased with age. After adjusting for age, sex, and body mass index, the prevalence of abnormal ECG of mining workers was higher than that of manufacturing workers (OR = 1.54, 95% CI = 1.07-2.24), and the prevalence of abnormal PTA had a rising trend with the increase in noise exposure value. CONCLUSION: Noise-exposed workers have a high prevalence of abnormal ECG, BP, and PTA, and factors such as age, enterprise size, and workplace noise exposure are correlated with the aberrant health of workers. Governments, enterprises, and individuals need to attach great importance to the possible adverse effects of noise. They must also actively adopt various effective measures to protect the occupational safety and health of workers.

Is Stroke risk analysis (SRA) a reliable method for predicting atrial fibrillation? A systematic review.

INTRODUCTION: Atrial fibrillation is responsible for a considerable number of cases of cardioembolism, accounting for 17% to 30% of the etiologies of all strokes. The software known as Stroke Risk Analysis (SRA) detects patients at high risk of paroxysmal atrial fibrillation by analyzing a continuous electrocardiogram recorded over different periods of time. OBJECTIVES: This article aims to carry out a systematic review investigating the effectiveness of the SRA method in predicting the risk of stroke patients having paroxysmal atrial fibrillation as the cause of the event. METHODS: The methods correspond to the format of the International Prospective Register of Systematic Reviews Protocol, according to CRD Identification Code: CRD42021253974. A systematic search was carried out in BMJB, PubMed/MEDLINE, Science Direct and LILACS. Six cohort studies met the inclusion criteria, representing a total of 2,088 participants with stroke, and compared the detection of patients with paroxysmal atrial fibrillation on the continuous recording electrocardiogram with a time variation of 1 to 48h with the use of SRA. RESULTS: Studies have shown that SRA has a high negative predictive value (between 96 and 99.1%) and can contribute to the selection of patients at high risk of paroxysmal atrial fibrillation to be referred for implantable cardiac monitoring to continue the investigation. CONCLUSIONS: A sequential combination of SRA with implantable cardiac monitoring is a promising strategy for detecting undiagnosed paroxysmal atrial fibrillation. Thus, the SRA can act as a cost-effective pre-selection tool to identify patients at higher risk of having paroxysmal atrial fibrillation as a possible cause of stroke and who may benefit from implantable cardiac monitoring. However, the lack of randomized studies is a limitation that must be considered.

[Risk management with regard to QT-prolonging drugs]. / Risicomanagement rond QT-verlengende geneesmiddelen.

Drug-induced QT prolongation increases the risk of Torsade de Pointes (TdP). Drug-induced QT prolongation is a complex and unpredictable system due to many uncertainties. Risk factors such as electrolyte disturbances, heart failure and genetics play an important role in estimating the effect on QT prolongation. Moreover, the degree of QT prolongation is not always directly related to the risk of TdP and the assessment of the QT-interval is variable depending on the type and timing of QT measurement. Therefore, the variation in QT measurement may be larger than the effect of certain drugs on the QT interval. Because of the potentially lethal risk, several measures are undertaken to reduce the risk of QT prolongation and TdP, while their effect and proportionality are unclear. We suggest we should be less stringent in certain settings when risk of TdP is extremely low given the limited availability of our resources.

Electrophysiological characteristics and catheter ablation of ventricular arrhythmias arising from the superior septal left ventricle.

BACKGROUND AND AIMS: Electrophysiological characteristics and radiofrequency catheter ablation (RFCA) of premature ventricular contractions (PVCs) originating from the superior septal left ventricle (SSLV) have not yet been fully characterized. METHODS AND RESULTS: This study included 247 patients who underwent RFCA for PVCs arising from the ventricular outflow tract between February 2020 and August 2022. The successful ablation site was on the SSLV in 37 of the 247 patients. In 12 (32.4%) of those 37 patients, a low amplitude and high frequency spiky potential (SP) was recognized. Five patients showed a narrow QRS duration (86.8 ± 4.6 ms), with a discrete SP observed in PVCs and sinus rhythm, which showed an isoelectric line with the ventricular electrogram at the earliest activation site. Seven patients showed a wide QRS duration (131.6 ± 4.5 ms), with SP observed in PVCs without an isoelectric line with the ventricular electrogram. RFCA was successful at the site of the earliest SP in all 12 patients. The time from SP onset at the successful ablation site to the QRS onset (local activation time) was 30 ± 12 ms, which differed significantly from that for the remaining 25 patients withoutSP(22.1 ± 7.1 ms, P < 0.05). CONCLUSIONS: SPs were recorded in 12 (32.4%) of the 37 patients with PVCs originating from the SSLV. The morphology of the PVCs may show a narrow or wide QRS duration and the target site for successful ablation should be identified by the earliest SP.

The Relationship between Fragmented QRS and Myocardial Injury in Patients with Acute Carbon Monoxide Poisoning.

Background and Objectives: Carbon monoxide (CO) intoxication is one of the most common causes of poisoning-related deaths and complications. Myocardial injury is an important complication of CO poisoning. In our study, we aimed to evaluate the relationship between the presence and prevalence of fragmented QRS (fQRS) and myocardial injury in patients with CO intoxication. Materials and Methods: We retrospectively evaluated patients who presented to the emergency department of our tertiary care center with CO intoxication between January 2020 and December 2023. In our study, we performed subgroup analyses according to the presence of myocardial injury and fQRS. We evaluated the parameters and risk factors associated with myocardial injury. Results: Myocardial injury was detected in 44 patients, and fQRS was detected in 38 patients. In the myocardial injury (+) group, the fQRS rate was 38.6%, and the median number of leads with fQRS was 3 (2-6) and was significantly higher than in the myocardial injury (-) group (p < 0.001). We found that carboxyhemoglobin had a significant positive correlation with troponin (p = 0.001) and pro-B-type natriuretic peptide (proBNP) (p = 0.009). As a result of multivariate analysis, we determined that age, creatinine, proBNP, fQRS, and ≥3 leads with fQRS are independent risk factors for myocardial injury. Conclusions: Myocardial injury in CO intoxication patients is associated with proBNP, the presence of fQRS, and the number of leads with fQRS. Age, creatinine level, proBNP, the presence of fQRS, and ≥3 leads with fQRS are independent risk factors for myocardial injury in patients with CO intoxication.