Improvement of electrocardiographic diagnostic accuracy of left ventricular hypertrophy using a Machine Learning approach.

The electrocardiogram (ECG) is the most common tool used to predict left ventricular hypertrophy (LVH). However, it is limited by its low accuracy (<60%) and sensitivity (30%). We set forth the hypothesis that the Machine Learning (ML) C5.

Diagnostic utility of the electrocardiographic left ventricular hypertrophy criteria in specific populations.

Background: Several electrocardiographic (ECG) criteria have been validated for the diagnosis of left ventricular hypertrophy (LVH); the majority in Caucasian subjects from Europe and North America. Diagnostic utility of ECG criteria to detect LVH has never been established in our population; nonetheless they are frequently used.

Objective: To evaluate the diagnostic utility of different LVH ECG criteria in a Northern Mexican population and to determine the effect of gender, age, body mass index (BMI), hypertension and ischaemic heart disease (IHD) on their performance.