Despite the wide literature on R-wave detection algorithms for ECG Holter recordings, the long-term monitoring applications are bringing new requirements, and it is not clear that the existing methods can be straightforwardly used in those scenarios. Our aim in this work was twofold: First, we scrutinized the scope and limitations of existing methods for Holter monitoring when moving to long-term monitoring; Second, we proposed and benchmarked a beat detection method with adequate accuracy and usefulness in long-term scenarios. A longitudinal study was made with the most widely used waveform analysis algorithms, which allowed us to tune the free parameters of the required blocks, and a transversal study analyzed how these parameters change when moving to different databases. With all the above, the extension to long-term monitoring in a database of 7-day Holter monitoring was proposed and analyzed, by using an optimized simultaneous-multilead processing. We considered both own and public databases. In this new scenario, the noise-avoid mechanisms are more important due to the amount of noise that exists in these recordings, moreover, the computational efficiency is a key parameter in order to export the algorithm to the clinical practice. The method based on a Polling function outperformed the others in terms of accuracy and computational efficiency, yielding 99.48% sensitivity, 99.54% specificity, 99.69% positive predictive value, 99.46% accuracy, and 0.85% error for MIT-BIH arrhythmia database. We conclude that the method can be used in long-term Holter monitoring systems.

In the past few years, the presence of fragmentation in the QRS complex has been demonstrated to be related to diseases such as myocardial fibrosis, cardiac sarcoidosis, arrythmogenic cardiopathies, acute coronary syndrome, and Brugada syndrome, among others. The detection of fragmentation in the QRS is usually carried out manually, which represents a subjective pattern recognition task that demands an effort by the clinician, increasing with the number of patients. These problems have made the process of fragmentation detection a good candidate to its automatization. In this work, we used a database with over six-thousand 12-lead ECG from Hospital Virgen de la Arrixaca de Murcia (Spain), which where digitally recorded with GE MAC5000. Affected and non-affected patients records were extracted for computerized analysis. Clinical supervision was performed for gold-standard development and for signal classification. Fragmentation detection algorithms were developed using first and second derivatives calculation in the pre-qualified segments of the signal, after fiducial point detection. The obtained results were 96.88% sensitivity , 72.92% specificity, and 82.50% accuracy. These results confirm that it is possible to automatically detect fragmentation, constituting a relevant tool to pre-qualify patients for further diagnostic-tests, and it also opens new opportunities for computerized diagnosis.