Merging Digital Medicine and Economics: Two Moving Averages Unlock Biosignals for Better Health
Abstract
:1. Introduction
2. Simplicity: A Moving Average
3. Economic Concept: Two Moving Averages
4. Analogy Application between Two Disciplines
- (1)
- QRS complexes in ECG signals: The two moving averages obtained a sensitivity (SE) of 99.29% and a positive predictivity (+P) of 98.11% over the first lead of the validation databases (10 databases with a total of 1,179,812 beats). When applied to the well-known MIT-BIH Arrhythmia Database, an SE of 99.78% and a +P of 99.87% were scored [4] and the improved version accomplished a SE of 99.90% and +P of 99.84% [5]. This simple approach outperformed most of the well-known QRS detectors, such as Pan–Tompkins [6] (SE of 90.95% and +P of 99.56%) and Hamilton–Tompkins [7] (SE of 99.69% and +P of 99.77%), which are more complex algorithms in terms of implementation and processing time.
- (2)
- T waves in ECG signals: Over the MIT-BIH Arrhythmia Database, the two moving averages were able to achieve a SE of 99.86% and a +P of 99.65% [8]. Unfortunately we cannot compare the performance with any other methods on the same dataset as the annotation of T-waves was published in 2015. However, the results are very promising, as the overall accuracy on arrhythmic ECG signals is more than 99.7% [9].
- (3)
- Systolic waves in PPG signals: The two moving averages were able to detect systolic waves in 40 subjects measured at rest and after three heat stress simulations containing 5071 heartbeats, with an overall SE of 99.89% and +P of 99.84% [10]. This simple approach slightly outperformed existing algorithms, such as Billauer’s [10] (SE of 99.88% and +P of 98.69%), Li’s [10] (SE of 97.9% and +P of 99.93%) and Zong’s [10] (SE of 99.69% and +P of 99.71%).
- (4)
- a and b waves in APG signals: The two moving averages demonstrated an overall SE of 99.78% and a +P of 100% for detecting a waves and overall SE of 99.78% and +P of 99.95% for detecting b waves [11]. There are no a and b waves detectors to compare the algorithm with, as it is a new area of investigation in the field of PPG signal analysis. However, the results are very promising and the accuracy is more than 98%.
- (5)
- c, d and e wave detection in APG signals: The performance of the two moving averages was tested on 27 PPG records collected during rest and after 2 h of exercise, resulting in 97.39% SE and 99.82% +P [12]. The proposed algorithm was not compared to other algorithms, as it is a new area of investigation in the field of PPG signal analysis. However, the results are very promising, as the overall accuracy achieved is more than 97%.
- (6)
- First and second heart sounds: The SE and +P of the two moving averages detectors were 70% and 68%, respectively, for heart sounds collected from children with pulmonary artery hypertension [13]. Again, the proposed algorithm outperformed existing algorithms, such as Liang’s [13] (SE of 59% and +P of 42%), Kumar’s [13] (SE of 19% and +P of 12%), Wang’s [13] (SE of 50% and +P of 45%) and Zhong [13] (SE of 43% and +P of 53%).
5. Conclusions
Conflicts of Interest
References
- Elgendi, M. TERMA Framework for Biomedical Signal Analysis: An Economic-Inspired Approach. Biosensors 2016, 6, 55. [Google Scholar] [CrossRef] [PubMed]
- Hausfather, Z.; Cowtan, K.; Clarke, D.C.; Jacobs, P.; Richardson, M.; Rohde, R. Assessing recent warming using instrumentally homogeneous sea surface temperature records. Sci. Adv. 2017, 3. [Google Scholar] [CrossRef] [PubMed]
- Cai, J.; Townsend, J.P.; Dodson, T.C.; Heiney, P.A.; Sweeney, A.M. Eye patches: Protein assembly of index-gradient squid lenses. Science 2017, 357, 564–569. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M. Fast QRS detection with an optimized knowledge-based method Evaluation on 11 standard ECG databases. PLoS ONE 2013, 8, 73557. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M.; Mohamed, A.; Ward, R. Efficient ECG Compression and QRS Detection for E-Health Applications. Sci. Rep. 2017, 7, 459. [Google Scholar] [CrossRef] [PubMed]
- Pan, J.; Tompkins, W. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 1985, 32, 230–236. [Google Scholar] [CrossRef] [PubMed]
- Hamilton, P.S.; Tompkins, W.J. Quantitative investigation of QRS detection rules using the MIT/BIH arrhythmiac database. IEEE Trans. Biomed. Eng. 1986, 33, 1157–1165. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M.; Eskofier, B.; Abbott, D. Fast T Wave Detection Calibrated by Clinical Knowledge with Annotation of P and T Waves. Sensors 2015, 15, 17693–17714. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M.; Meo, M.; Abbott, D. A proof-of-concept study: Simple and effective detection of P and T waves in arrhythmic ECG signals. Bioengineering 2016, 3, 26. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M.; Norton, I.; Brearley, M.; Abbott, D.; Schuurmans, D. Systolic peak detection in acceleration photoplethysmograms measured from emergency responders in tropical conditions. PLoS ONE 2013, 8, 76585. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Elgendi, M.; Norton, I.; Brearley, M.; Abbott, D.; Schuurmans, D. Detection of a and b waves in the acceleration photoplethysmogram. Biomed. Eng. Online 2014, 13, 139. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M. Detection of c, d, and e waves in the acceleration photoplethysmogram. Comput. Methods Progr. Biomed. 2014, 117, 125–136. [Google Scholar] [CrossRef] [PubMed]
- Elgendi, M.; Kumar, S.; Guo, L.; Rutledge, J.; Coe, J.Y.; Zemp, R.; Schuurmans, D.; Adatia, I. Detection of Heart Sounds in Children with and without Pulmonary Arterial Hypertension―Daubechies Wavelets Approach. PLoS ONE 2015, 10, e0143146. [Google Scholar] [CrossRef] [PubMed]
© 2018 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Elgendi, M. Merging Digital Medicine and Economics: Two Moving Averages Unlock Biosignals for Better Health. Diseases 2018, 6, 6. https://doi.org/10.3390/diseases6010006
Elgendi M. Merging Digital Medicine and Economics: Two Moving Averages Unlock Biosignals for Better Health. Diseases. 2018; 6(1):6. https://doi.org/10.3390/diseases6010006
Chicago/Turabian StyleElgendi, Mohamed. 2018. "Merging Digital Medicine and Economics: Two Moving Averages Unlock Biosignals for Better Health" Diseases 6, no. 1: 6. https://doi.org/10.3390/diseases6010006