Unraveling diagnostic co-morbidity makeup of each HF category as characteristically derived by ECG- and ECHO-findings, a prevalence analysis

BackgroundEchocardiography (ECHO) is not widely available in primary care, the key structural (chamber enlargements) and functional abnormality are not easily available precluding the ability to diagnose HF other than through mainly symptomatic means. The opportunity for earlier detection of HF is lost. MethodsUsing a unique database, the etiology of HF is explored by prevalence analysis to unravel the diagnostic makeup of each HF category. Various relationships and patterns of comorbidities have been extracted between the Electrocardiogram (ECG) and ECHO parameters that contribute to HF, those relationships are then confirmed and categorized by a Principal Component Analysis (PCA). Finally, it was summarized what type of non-invasive ECG-like device should be used in primary care to better diagnose HF. ResultsThe sensitivity of abnormal ECHO reaches 92% over the abnormal ECG of 81% in the detection of HF. The first five PCA are discovered, which cover 49% of all the variance. Left atrial enlargement is the most representative finding in the overall comorbidity rate, which coincides with the probability direction of HF (3rd as input, 1st as finding in the coefficients), and reaches the highest (250%) prevalence increase in function of decreasing LVEF. ConclusionsThe core structural and functional abnormalities diagnosed by ECHO with the ECG interpretation provide sufficient information to diagnose "consider HF" in primary care. This paper overview of a novel bio-signal-based system supported by Artificial Intelligence, able to replicate Echo-findings, predict HF and indicates its phenotype, suitable for use in Primary Care.