Advances in the Analysis of Electrocardiogram in Context of Mass Screening: Technological Trends and Application of AI Anomaly Detection
Advances in Non-Invasive Biomedical Signal Sensing and Processing with Machine Learning, Page: 107-132
2023
- 2Citations
- 3Captures
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Book Chapter Description
Electrocardiography is still the most wide-spread method of functional diagnosis. The chapter has been targeted towards the debate on evolution and current attitude on the heart failure screening electrocardiography, reviewing the clinical practices of applying remote electrocardiogram (ECG) recording gadgets, the quantity and origin of data possible to be collected with ECG gadgets having various number of sensors using different modern methods of mathematical transformation of ECG signal, i.e. fourth generation ECG analysis. Accent has been made towards the application of the modern machine learning method – anomaly detection to heart activity analysis. Anomaly detection is one of the machine learning methods which identifies the data samples who deviate from some concept of normality. Such samples represent novelty, or outliers in the dataset, and often carry important information. As an example of application of anomaly detection in biomedical signal analysis, the problem of identifying the subtle deviations from the population norm based on the ECG is presented. The time-magnitude features derived from six leads of Signal Averaged ECG are used in the Isolation Forest anomaly (IFA) detector to quantify the distance of the single ECG from the cluster of normal controls. Input data to the IFA technique consists of diverse tree amounts as well as several pollution factors. For comparison, five different groups were examined: patients with proven coronary artery diseases, military personnel with mine-explosive injuries, COVID-19 survivors, and two subgroups involving participants of widespread-screening in one of the countryside areas in Ukraine.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85173342102&origin=inward; http://dx.doi.org/10.1007/978-3-031-23239-8_5; https://link.springer.com/10.1007/978-3-031-23239-8_5; https://dx.doi.org/10.1007/978-3-031-23239-8_5; https://link.springer.com/chapter/10.1007/978-3-031-23239-8_5
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know