M Findeis | PubMed Health

PubMed1999

Artifact processing during exercise testing.

In signal processing of exercise electrocardiograms (ECGs), artifacts are a recurring problem. It is still difficult to discriminate the ECG curves from artifacts, especially in exercise ECGs and particularly in the high exercise phase. We focused on the artifact problem and worked on two new topics: the Finite Impulse Response Residual Filtering (FRF) algorithm and the Intelligent Lead Switch algorithm. The FRF algorithm reduces the baseline wander and muscle noise in the ECG stream, with much less distortion of the QRS complexes. It subtracts a continuously updated median beat from the current ECG, filters the residual signal with a high-pass and a low-pass filter, and adds the median beat to the filtered residual signal. The Intelligent Lead Switch algorithm takes advantage of the redundancy of a multilead system (eg, standard leads), which is nowadays used during exercise testing. It selects the best leads for QRS detection and thus improves the heart rate calculation, ST segment evaluation, and arrhythmia classification.

Algorithms↗

PubMed1996

Automatic learning of rules. A practical example of using artificial intelligence to improve computer-based detection of myocardial infarction and left ventricular hypertrophy in the 12-lead ECG.

The authors developed a computer program that detects myocardial infarction (MI) and left ventricular hypertrophy (LVH) in two steps: (1) by extracting parameter values from a 10-second, 12-lead electrocardiogram, and (2) by classifying the extracted parameter values with rule sets. Every disease has its dedicated set of rules. Hence, there are separate rule sets for anterior MI, inferior MI, and LVH. If at least one rule is satisfied, the disease is said to be detected. The computer program automatically develops these rule sets. A database (learning set) of healthy subjects and patients with MI, LVH, and mixed MI+LVH was used. After defining the rule type, initial limits, and expected quality of the rules (positive predictive value, minimum number of patients), the program creates a set of rules by varying the limits. The general rule type is defined as: disease = lim1l < p1 < or = lim1u and lim2l < p2 < or = lim2u and ... limnl < pn < or = limnu. When defining the rule types, only the parameters (p1 ... pn) that are known as clinical electrocardiographic criteria (amplitudes [mV] of Q, R, and T waves and ST-segment; duration [ms] of Q wave; frontal angle [degrees]) were used. This allowed for submitting the learned rule sets to an independent investigator for medical verification. It also allowed the creation of explanatory texts with the rules. These advantages are not offered by the neurons of a neural network. The learned rules were checked against a test set and the following results were obtained: MI: sensitivity 76.2%, positive predictive value 98.6%; LVH: sensitivity 72.3%, positive predictive value 90.9%. The specificity ratings for MI are better than 98%; for LVH, better than 90%.

Adolescent↗