Ntsekhe, Mpiko

Abstract Aims Rheumatic heart disease (RHD) remains the most prevalent acquired cardiovascular disease among young adults in developing countries, and there is a critical need for an efficient, affordable, and available screening strategy to detect RHD in these resource-limited areas. The 12-lead electrocardiogram (ECG) is a ubiquitous, inexpensive diagnostic tool, and application of artificial intelligence to the ECG (AI-ECG) has allowed for screening of various cardiovascular pathologies. Methods and results Patients aged >18 years with severe RHD with at least one transthoracic echocardiogram and one standard 12-lead ECG performed at Groote Schuur Hospital, Cape Town, within 180 days of each other were eligible. A total of 920 RHD patients were identified, with 2199 corresponding controls from the same medical centre. Patients were allocated to derivation (80%), validation (10%), and testing (10%) groups, respectively. The AI-ECG to detect RHD from a standard 12-lead ECG was built using the Keras framework under Tensorflow backend. In the test group, the AI-ECG for RHD exhibited strong algorithm performance with an AUC of 0.890 (95% Confidence Interval 0.848–0.940) and an accuracy of 83.8%. The algorithm remained robust between RHD presentation: mitral valve alone (AUC 0.913) and mixed mitral and aortic valve disease (AUC 0.858). There were minor performance differences in the subgroup analysis of patient sex, age, and ECG characteristics. Conclusion In this study, an AI-ECG algorithm was successfully developed to screen for advanced RHD from a standard 12-lead ECG, and the AI-ECG performance remained acceptable across most subgroups, including RHD manifestation, patient sex, age <70 years, and ECG characteristics.

Objective The prevalence, predictors and outcome of myopericarditis in patients with tuberculous (TB) pericarditis are unknown. Methods Eighty-one patients (mean age±SD, 36.1±13.3 years; 54 (66.7%) men; 58 (71.6%) HIV seropositive) with TB pericarditis were recruited between January 2006 and September 2008. Myopericarditis was defined as echocardiographic LV systolic dysfunction (immediately after pericardiocentesis), elevated peripheral blood troponin T (>0.03 ng/mL), or elevated peripheral blood creatine kinase (CK >174 IU/L) with a CK:CK-myocardial band (MB) mass ratio of >6%. The outcome measure was case fatality rate at 6 months of follow-up. Results Myopericarditis was present in 43 (53.1%) patients. Patients with myopericarditis, as compared with those without, were more likely to be HIV seropositive (35 (81.4%) vs 23 (60.5%) respectively, p=0.038) and have lower peripheral CD4 count (median (IQR) 98 (54–290) vs 177 (104–429), p=0.026). Electrocardiographic ST segment elevation was more common in myopericarditis (15 (36.6%) vs 4 (10.8%), p=0.008) and predicted myopericarditis independently of CD4 count on multiple logistic regression analysis (OR 4.36, 95% CI 1.34 to 17.34, p=0.0132). At 6 months, 14 (18%) patients had died with no significant difference between those with or without myopericarditis (6/42 (14%) vs 8/36 (22%), respectively (p=0.363)). Conclusions Myopericarditis is common in TB pericardial effusion and associated with HIV-related immunosuppression. It can be identified by electrocardiographic ST-elevation, particularly when peripheral CD4 count is low. There was no significant difference in case fatality rate in those with or without myopericarditis.