RESUMO
Aims: Cardiovascular disease (CVD) may not be detected in time with conventional clinical approaches. Abnormal gait patterns have been associated with pathological conditions and can be monitored continuously by gait video. We aim to test the association between non-contact, video-based gait information and general CVD status. Methods and results: Individuals undergoing confirmatory CVD evaluation were included in a prospective, cross-sectional study. Gait videos were recorded with a Kinect camera. Gait features were extracted from gait videos to correlate with the composite and individual components of CVD, including coronary artery disease, peripheral artery disease, heart failure, and cerebrovascular events. The incremental value of incorporating gait information with traditional CVD clinical variables was also evaluated. Three hundred fifty-two participants were included in the final analysis [mean (standard deviation) age, 59.4 (9.8) years; 25.3% were female]. Compared with the baseline clinical variable model [area under the receiver operating curve (AUC) 0.717, (0.690-0.743)], the gait feature model demonstrated statistically better performance [AUC 0.753, (0.726-0.780)] in predicting the composite CVD, with further incremental value when incorporated with the clinical variables [AUC 0.764, (0.741-0.786)]. Notably, gait features exhibited varied association with different CVD component conditions, especially for peripheral artery disease [AUC 0.752, (0.728-0.775)] and heart failure [0.733, (0.707-0.758)]. Additional analyses also revealed association of gait information with CVD risk factors and the established CVD risk score. Conclusion: We demonstrated the association and predictive value of non-contact, video-based gait information for general CVD status. Further studies for gait video-based daily living CVD monitoring are promising.
RESUMO
BACKGROUND: Current approaches for initial coronary artery disease (CAD) assessment rely on pretest probability (PTP) based on risk factors and presentations, with limited performance. Infrared thermography (IRT), a non-contact technology that detects surface temperature, has shown potential in assessing atherosclerosis-related conditions, particularly when measured from body regions such as faces. We aim to assess the feasibility of using facial IRT temperature information with machine learning for the prediction of CAD. METHODS: Individuals referred for invasive coronary angiography or coronary CT angiography (CCTA) were enrolled. Facial IRT images captured before confirmatory CAD examinations were used to develop and validate a deep-learning IRT image model for detecting CAD. We compared the performance of the IRT image model with the guideline-recommended PTP model on the area under the curve (AUC). In addition, interpretable IRT tabular features were extracted from IRT images to further validate the predictive value of IRT information. RESULTS: A total of 460 eligible participants (mean (SD) age, 58.4 (10.4) years; 126 (27.4%) female) were included. The IRT image model demonstrated outstanding performance (AUC 0.804, 95% CI 0.785 to 0.823) compared with the PTP models (AUC 0.713, 95% CI 0.691 to 0.734). A consistent level of superior performance (AUC 0.796, 95% CI 0.782 to 0.811), achieved with comprehensive interpretable IRT features, further validated the predictive value of IRT information. Notably, even with only traditional temperature features, a satisfactory performance (AUC 0.786, 95% CI 0.769 to 0.803) was still upheld. CONCLUSION: In this prospective study, we demonstrated the feasibility of using non-contact facial IRT information for CAD prediction.
Assuntos
Doença da Artéria Coronariana , Face , Termografia , Humanos , Termografia/métodos , Doença da Artéria Coronariana/diagnóstico por imagem , Masculino , Feminino , Pessoa de Meia-Idade , Face/diagnóstico por imagem , Idoso , Valor Preditivo dos Testes , Estudos de Viabilidade , Temperatura Corporal , Aprendizado de Máquina , Angiografia Coronária , Angiografia por Tomografia Computadorizada , Estudos Prospectivos , Raios InfravermelhosRESUMO
BACKGROUND: Lipoprotein(a) is a possible causal risk factor for atherosclerosis and related complications. The distribution and prognostic implication of lipoprotein(a) in patients undergoing coronary artery bypass grafting remain unknown. This study aimed to assess the impact of high lipoprotein(a) on the long-term prognosis of patients undergoing coronary artery bypass grafting. METHODS AND RESULTS: Consecutive patients with stable coronary artery disease who underwent isolated coronary artery bypass grafting from January 2013 to December 2018 from a single-center cohort were included. The primary outcome was all-cause death. The secondary outcome was a composite of major adverse cardiovascular and cerebrovascular events. Of the 18 544 patients, 4072 (22.0%) were identified as the high-lipoprotein(a) group (≥50 mg/dL). During a median follow-up of 3.2 years, primary outcomes occurred in 587 patients. High lipoprotein(a) was associated with increased risk of all-cause death (high lipoprotein(a) versus low lipoprotein(a): adjusted hazard ratio [aHR], 1.31 [95% CI, 1.09-1.59]; P=0.005; lipoprotein(a) per 1-mg/dL increase: aHR, 1.003 [95% CI, 1.001-1.006]; P=0.011) and major adverse cardiovascular and cerebrovascular events (high lipoprotein(a) versus low lipoprotein(a): aHR, 1.18 [95% CI, 1.06-1.33]; P=0.004; lipoprotein(a) per 1-mg/dL increase: aHR, 1.002 [95% CI, 1.001-1.004]; P=0.002). The lipoprotein(a)-related risk was greater in patients with European System for Cardiac Operative Risk Evaluation <3, and tended to attenuate in patients receiving arterial grafts. CONCLUSIONS: More than 1 in 5 patients with stable coronary artery disease who underwent coronary artery bypass grafting were exposed to high lipoprotein(a), which is associated with higher risks of death and major adverse cardiovascular and cerebrovascular events. The adverse effects of lipoprotein(a) were more pronounced in patients with clinically low-risk profiles or not receiving arterial grafts.
Assuntos
Aterosclerose , Doença da Artéria Coronariana , Humanos , Lipoproteína(a) , Resultado do Tratamento , Ponte de Artéria Coronária , Aterosclerose/complicações , Fatores de Risco , Estudos RetrospectivosRESUMO
AIMS: Preoperative risk assessment is crucial for cardiac surgery. Although previous studies suggested machine learning (ML) may improve in-hospital mortality predictions after cardiac surgery compared to traditional modeling approaches, the validity is doubted due to lacking external validation, limited sample sizes, and inadequate modeling considerations. We aimed to assess predictive performance between ML and traditional modelling approaches, while addressing these major limitations. METHODS AND RESULTS: Adult cardiac surgery cases (n = 168 565) between 2013 and 2018 in the Chinese Cardiac Surgery Registry were used to develop, validate, and compare various ML vs. logistic regression (LR) models. The dataset was split for temporal (2013-2017 for training, 2018 for testing) and spatial (geographically-stratified random selection of 83 centers for training, 22 for testing) experiments, respectively. Model performances were evaluated in testing sets for discrimination and calibration. The overall in-hospital mortality was 1.9%. In the temporal testing set (n = 32 184), the best-performing ML model demonstrated a similar area under the receiver operating characteristic curve (AUC) of 0.797 (95% CI 0.779-0.815) to the LR model (AUC 0.791 [95% CI 0.775-0.808]; P = 0.12). In the spatial experiment (n = 28 323), the best ML model showed a statistically better but modest performance improvement (AUC 0.732 [95% CI 0.710-0.754]) than LR (AUC 0.713 [95% CI 0.691-0.737]; P = 0.002). Varying feature selection methods had relatively smaller effects on ML models. Most ML and LR models were significantly miscalibrated. CONCLUSION: ML provided only marginal improvements over traditional modelling approaches in predicting cardiac surgery mortality with routine preoperative variables, which calls for more judicious use of ML in practice.
Assuntos
Procedimentos Cirúrgicos Cardíacos , Propanolaminas , Adulto , Humanos , Mortalidade Hospitalar , Aprendizado de Máquina , Sistema de RegistrosRESUMO
Although N-terminal pro-B-type natriuretic peptide (NT-proBNP) has been validated as a cardiovascular biomarker, its ability to predict long-term outcomes after coronary artery bypass grafting (CABG) has not been fully explored. We aimed to assess the prognostic value of NT-proBNP beyond clinical risk prediction tools, and its relevance to follow-up events and interactions with different treatment selections. The study included 11,987 patients who underwent CABG who underwent surgery between 2014 and 2018. The primary end point was all-cause mortality during follow-up, whereas the secondary end points included cardiac death and major adverse cardiac and cerebrovascular events, which comprised death, myocardial infarction, and ischemic cerebrovascular accident. We evaluated the associations between NT-proBNP levels and outcome and the added prognostic value of NT-proBNP to clinical tools. Patients were followed up for a median of 4.0 years. Higher preoperative NT-proBNP levels were significantly associated with all-cause mortality, cardiac death, and major adverse cardiac and cerebrovascular events (all p <0.001). These associations remained significant after the full adjustment. Integration of NT-proBNP into clinical tools significantly improved the prediction accuracy for all end points. We also found that patients with higher preoperative NT-proBNP levels benefited more from ß blockers (p for interaction = 0.045). In conclusion, we demonstrated the prognostic value of NT-proBNP in risk stratification and personalized treatment decisions in patients who underwent CABG.
Assuntos
Ponte de Artéria Coronária , Peptídeo Natriurético Encefálico , Humanos , Prognóstico , Biomarcadores , Fragmentos de PeptídeosRESUMO
OBJECTIVE: Warfarin anticoagulation management requires sequential decision-making to adjust dosages based on patients' evolving states continuously. We aimed to leverage reinforcement learning (RL) to optimize the dynamic in-hospital warfarin dosing in patients after surgical valve replacement (SVR). MATERIALS AND METHODS: 10 408 SVR cases with warfarin dosage-response data were retrospectively collected to develop and test an RL algorithm that can continuously recommend daily warfarin doses based on patients' evolving multidimensional states. The RL algorithm was compared with clinicians' actual practice and other machine learning and clinical decision rule-based algorithms. The primary outcome was the ratio of patients without in-hospital INRs >3.0 and the INR at discharge within the target range (1.8-2.5) (excellent responders). The secondary outcomes were the safety responder ratio (no INRs >3.0) and the target responder ratio (the discharge INR within 1.8-2.5). RESULTS: In the test set (n = 1260), the excellent responder ratio under clinicians' guidance was significantly lower than the RL algorithm: 41.6% versus 80.8% (relative risk [RR], 0.51; 95% confidence interval [CI], 0.48-0.55), also the safety responder ratio: 83.1% versus 99.5% (RR, 0.83; 95% CI, 0.81-0.86), and the target responder ratio: 49.7% versus 81.1% (RR, 0.61; 95% CI, 0.58-0.65). The RL algorithms performed significantly better than all the other algorithms. Compared with clinicians' actual practice, the RL-optimized INR trajectory reached and maintained within the target range significantly faster and longer. DISCUSSION: RL could offer interactive, practical clinical decision support for sequential decision-making tasks and is potentially adaptable for varied clinical scenarios. Prospective validation is needed. CONCLUSION: An RL algorithm significantly optimized the post-operation warfarin anticoagulation quality compared with clinicians' actual practice, suggesting its potential for challenging sequential decision-making tasks.
Assuntos
Anticoagulantes , Varfarina , Anticoagulantes/uso terapêutico , Hospitais , Humanos , Estudos Retrospectivos , Instrumentos Cirúrgicos , Varfarina/uso terapêuticoRESUMO
AIMS: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) directly binds to ACE2 (angiotensin-converting enzyme 2) to facilitate cellular entry. Compared with the lung or respiratory tract, the human heart exhibits greater ACE2 expression. However, little substantial damage was found in the heart tissue, and no viral particles were observed in the cardiac myocytes. This study aims to analyse ACE2 and SARS-CoV-2 spike (S) protein proteases at the single-cell level, to explore the cardiac involvement in COVID-19 and improve our understanding of the potential cardiovascular implications of COVID-19. METHODS AND RESULTS: With meta-analysis, the prevalence of cardiac injury in COVID-19 patients varies from 2% [95% confidence interval (CI) 0-5%, I2 = 0%] in non-ICU patients to 59% (95% CI 48-71%, I2 = 85%) in non-survivors. With public single-cell sequence data analysis, ACE2 expression in the adult human heart is higher than that in the lung (adjusted P < 0.0001). Inversely, the most important S protein cleavage protease TMPRSS2 (transmembrane protease serine protease-2) in the heart exhibits an extremely lower expression than that in the lung (adjusted P < 0.0001), which may restrict entry of SARS-CoV-2 into cardiac cells. Furthermore, we discovered that other S protein proteases, CTSL (cathepsin L) and FURIN (furin, paired basic amino acid cleaving enzyme), were expressed in the adult heart at a similar level to that in the lung, which may compensate for TMPRSS2, mediating cardiac involvement in COVID-19. CONCLUSION: Compared with the lung, ACE2 is relatively more highly expressed in the human heart, while the key S protein priming protease, TMPRSS2, is rarely expressed. The low percentage of ACE2+/TMPRSS2+ cells reduced heart vulnerability to SARS-CoV-2 to some degree. CTSL and FURIN may compensate for S protein priming to mediate SARS-CoV-2 infection of the heart.
Assuntos
Betacoronavirus/patogenicidade , Infecções por Coronavirus/metabolismo , Miocárdio/enzimologia , Peptidil Dipeptidase A/metabolismo , Pneumonia Viral/metabolismo , Análise de Célula Única , Glicoproteína da Espícula de Coronavírus/metabolismo , Enzima de Conversão de Angiotensina 2 , COVID-19 , Humanos , Pulmão/metabolismo , Pulmão/virologia , Pandemias , Peptídeo Hidrolases/metabolismo , Proteólise , SARS-CoV-2RESUMO
Direct stenting (DS) without pre-dilatation of the culprit lesion might improve myocardial perfusion and prognosis in patients undergoing percutaneous coronary intervention for ST-elevation myocardial infarction (STEMI); however, some studies report conflicting results. We investigated whether DS provides incremental myocardial benefits over conventional stenting (CS) in STEMI patients based on cardiac magnetic resonance imaging (CMR) measures. Reperfused patients who underwent CMR examinations within 1 week of STEMI onset were selected from a multicenter CMR registry of STEMI (NCT: 03768453). Patients were stratified into either a DS or CS group. Each group comprised 137 patients after 1:1 propensity score matching. Major adverse events (MACEs), including death, myocardial re-infarction, re-admission for heart failure, and stroke were noted during a median period of 44 months (interquartile range 32-58 months). DS was associated with larger (p = 0.007) and shorter (p = 0.005) stent sizes than CS. DS and CS achieved comparable angiographic TIMI-3 flow grades (p = 0.86) and myocardial blush grades (p = 0.70). There were no group differences regarding the incidence of CMR manifestations of microvascular dysfunction, including microvascular obstruction (MVO) (p = 0.89) and intramyocardial hemorrhage (p = 0.47), the extent of MVO (p = 0.21), infarction size (p = 0.83), or left ventricular ejection fraction (p = 0.57). Kaplan-Meier analysis revealed similar risks of MACEs (log rank p = 0.909), which occurred in 23.4% of DS and 26.3% of CS patients (p = 0.576). DS did not show any incremental benefits over CS on myocardial impairments as evaluated using CMR.Clinical Trial Registration: Clinicaltrials.gov, NCT: 03768453.