The recognition accuracy of electrocardiographic electrodes misplacement by an artificial intelligence system compared to medical experts

Background: еlectrocardiographic electrodes misplacement represents one of the most common recording technique errors. Aim: to compare the accuracy of an artificial intelligence software in recognizing misplacement of electrocardiographic electrodes with human analysis by medical experts. Materials and methods: the work was carried out in 3 stages: 1) two electrocardiography datasets with correctly and erroneously positioned electrodes were generated: the training sample (262 electrocardiograms of 27 patients) and the test sample (59 electrocardiograms of 6 patients); 2) artificial intelligence system was trained to correctly annotate electrodes misplacement; 3) testing an artificial intelligence and comparison of its results with the indicators of analysis by doctors-specialists in the field of cardiology. Results: compared to the doctors, the artificial intelligence algorithm functioned more precise and stable in recognizing incorrect electrodes positioning (area under ROC-curve: >0.81 vs 0.58). It also discriminated more error classes (5 of 9 vs. 3 of 9). Doctors and the artificial intelligence system The error classes that were shown to be better determined by the doctors differed from those that were better determined by the algorithm. Conclusion: according to the obtained results, the capability of recognizing incorrect electrode placement demonstrated by the artificial intelligence system is comparable to the diagnostic accuracy of medical analysis. In general, the algorithm’s operation is characterized by greater specificity and stability. It is advisable to improve the algorithm and conduct further research.

1. Martinez M., Bouchut S., Thevenon M., et al. Improvement of electrocardiograms implementation quality by emergency nurses with short training // Ann French Emerg Med. 2015. Vol. 5, N 2. P. 85–89. doi: 10.1007/s13341-015-0509-8.

2. Pearce A. Examining the causes and effects of electrode misplacement during electrocardiography: a literature review // British Journal of Cardiac Nursing. 2019. Vol. 14, N 7. P. 1–15. doi: 10.12968/bjca.2019.0010.

3. Ramrakha P., Hill J. Oxford handbook of cardiology. 2nd edn. Oxford : Oxford University Press, 2012.

4. Medani S.A., Hensey M., Caples N., Owens P. Accuracy in precordial ECG lead placement: improving through a peer-led educational intervention // J Electrocardiol. 2018. Vol. 51, N 1. P. 50–54. doi: 10.1016/j.jelectrocard.2017.04.018.

5. Kania M., Rix H., Fereniec M. The effect of precordial lead displacement on ECG morphology // Med Biol Eng Comput. 2014. Vol. 52, N 2. P. 109–19. doi: 10.1007/s11517-013-1115-9.

6. Advanced life support. 6th edn. London : Resuscitation Council (UK), 2011.

7. Дроздов Д.В., Макаров Л.М., Баркан В.С., и др. Регистрация электрокардиограммы покоя в 12 общепринятых отведениях взрослым и детям 2023. Методические рекомендации. Российский кардиологический журнал. 2023. Т. 28, № 10. С. 105–130. EDN: JAVUJL doi: 10.15829/1560-4071-2023-5631. Drozdov DV, Makarov LM, Barkan VS, et al. Resting 12-lead electrocardiography for adults and children. 2023 Guidelines. Russian Journal of Cardiology. 2023;28(10):105–130. EDN: JAVUJL doi: 10.15829/1560-4071-2023-5631.

8. Abdollah H., Milliken J.A. Recognition of electrocardiographic left arm/left leg lead reversal // Am. J. Cardiol. 1997. Vol. 80. P. 1247–1249. doi: 10.1016/s0002-9149(97)00656-5.

9. Hedén B., Ohlsson M., Holst H. Detection of frequently overlooked electrocardiographic lead reversals using artificial neural networks // Am. J. Cardiol. 1996. Vol. 78. P. 600–604. doi: 10.1016/s0002-9149(96)00377-3.

10. Hoffman I. A Flatline electrocardiogram in lead II is a marker for right arm/right leg electrode switch // J. Electrocardiol. 2007. Vol. 40. P. 226–227. doi: 10.1016/j.jelectrocard.2006.06.003.

11. Han C., Gregg R., Babaeizadeh S. Automatic Detection of ECG Lead-wire Interchange for Conventional and Mason-Likar Lead Systems // Comput. Cardiol. 2014. Vol. 41. P. 145–148.

12. Krishnan R., Ramesh M. QRS axis based classification of electrode interchange in wearable ECG devices. EAI Endorsed Trans // Future Intell. Educ. Env. 2015. doi: 10.4108/eai.14-10-2015.2261647.

13. Ho R.T., Mukherji L., Evans G.T. Simple diagnosis of limb-lead reversals by predictable changes in QRS axis // Pacing Clin. Electrophysiol. 2006. Vol. 29. P. 272–277. doi: 10.1111/j.1540-8159.2006.00333.x.

14. De Bie J., Mortara D.W., Clark T.F. The development and validation of an early warning system to prevent the acquisition of 12-lead resting ECGs with interchanged electrode positions // J. Electrocardiol. 2014. Vol. 47. P. 794–797. doi: 10.1016/j.jelectrocard.2014.08.015

15. Ho K.K.L., Ho S.K. Use of the sinus P wave in diagnosing electrocardiographic limb lead misplacement not involving the right leg (ground) lead // J. Electrocardiol. 2001. Vol. 34. P. 161–171. doi: 10.1054/jelc.2001.23927

16. Kors J.A., van Herpen G. Accurate automatic detection of electrode interchange in the electrocardiogram // Am. J. Cardiol. 2001. Vol. 88. P. 396–399. doi: 10.1016/S0002-9149(01)01686-1.

17. Han C., Gregg R.E., Field D.Q., Babaeizadeh S. Automatic detection of ECG cable interchange by analyzing both morphology and interlead relations // J. Electrocardiol. 2014. Vol. 47. P. 781–787. doi: 10.1016/j.jelectrocard.2014.08.006.

18. Gregg R., Hancock E.W., Babaeizadeh S. Detecting ECG limb lead-wire interchanges involving the right leg lead-wire // Comput. Cardiol. 2017. Vol. 44. doi: 10.22489/CinC.2017.014-061

19. Xia H., Garcia G.A., Zhao X. Automatic detection of ECG electrode misplacement: A tale of two algorithms // Physiol. Meas. 2012. Vol. 33. P. 1549–1561. doi: 10.1088/0967-3334/33/9/1549.

20. Dotsinsky I., Daskalov I., Iliev I. Detection of peripheral ECG electrodes misplacement // Proc. 7th Int. Conf. Electronics ET’98; 1998; Sozopol, Bulgaria. Режим доступа: http://ecad.tu-sofia.bg/et/1998/Statii%20ET98-II/Detection%20of%20Peripheral%20ECG%20Electrodes%20Misplacement.pdf

21. Kemp B., Olivan J. European data format ‘plus’ (EDF+), an EDF alike standard format for the exchange of physiological data // Clinical Neurophysiology. 2003. Vol. 114. P. 1755–1761 doi: 10.1016/S1388-2457(03)00123-8.

22. Морозов С.П., Владзимирский А.В., Кляшторный В.Г., и др. Клинические испытания программного обеспечения на основе интеллектуальных технологий (лучевая диагностика). Москва: Научно-практический клинический центр диагностики и телемедицинских технологий Департамента здравоохранения города Москвы, 2019. EDN: CBFYFL.

23. Morozov SP, Vladzimirskii AV, Klyashtornyi VG, et al. Clinical trials of software based on intelligent technology (radial diagnostics). Moscow: Nauchno-prakticheskii klinicheskii tsentr diagnostiki i telemeditsinskikh tekhnologii Departamenta zdravookhraneniya goroda Moskvy; 2019. (In Russ) EDN: CBFYFL.

24. Rajaganeshan R., Ludlam C.L., Francis D.P. Accuracy in ECG lead placement among technicians, nurses, general physicians and cardiologists // Int J Clin Pract. 2008. Vol. 62, N 1. P. 65–70. doi: 10.1111/j.1742-1241.2007.01390..x.

25. Garcia-Niebla J., Rodriguez-Morales M., Valle-Racero J.I., de Luna A.B. Negative P wave in V1 is the key to identifying high placement of V1-V2 electrodes in nonpathological subjects // Am J Med. 2012. Vol. 125, N 9. P. e9–e10. doi: 10.1016/j.amjmed.2011.12.024.

26. Rosen A.V., Koppikar S., Shaw C., Baranchuk A. Common ECG Lead Placement Errors. Part II: Precordial Misplacements // International Journal of Medical Students. 2014. Vol. 2, N 3. P. 99–103. doi: 10.5195/ijms.2014.96

27. Газашвили Т.М., Дроздов Д.В., Шутов Д.В., Шкода А.С. Создание набора данных с диспозицией и транспозицией наложения электрокардиографических электродов при записи электрокардиограммы в 12 отведениях // Digital Diagnostics. 2023. Т. 4, № 2. С. 133−141. doi: 10.17816/DD201870.

28. Gazashvili TM, Drozdov DV, Shutov DV, Shkoda AS. Creation of a training and test dataset with the disposition and transposition of overlaying electrocardiographic electrodes when recording electrocardiograms-12. Digital Diagnostics. 2023;4(2):133−141. doi: 10.17816/DD201870.