Digital Transformation of CPR Mannequins in Medical Education with Artificial Intelligence Classifier

Abstract

Medical education, including the management of simulation centers, has become another important area in the Industry 4.0 phenomenon in terms of digital transformation. In this study, data obtained by messaging a mechanical CardioPulmonary Resuscitation (CPR) first aid training manikin with modularly developed electronic devices were collected. These data are also processed through the developed software that enables them to communicate with both mobile devices and desktop computers, and the validity of the massage activity performed with the Artificial Intelligence (AI) algorithm is verified. The modular kit was developed in the Open Source Laboratory of the Department of Informatics (KOUOSL) with the support of the Kocaeli University Faculty of Medicine and the Department of Emergency Medicine. An ideal CPR massage interval is expressed as 100-120 compressions per minute and application to the chest at a depth of approximately 5-6 cm. In order to determine the validity and accuracy of the CPR in the study, based on the data collected from the sensors placed on the mannequin, feedback was given to the Observer Trainer whether an ideal massage was performed with an AI classifier. Thus, a more effective practical training application will be developed and provided by digitizing the mechanical mannequin.

Keywords

• CPR Manikin
• ANN
• Digital Transformation
• Classifier
• Medicine

Tıp Eğitiminde CPR Mankenlerinin Yapay Zeka Sınıflandırıcı ile Dijital Dönüşümü

Abstract

Medical education, including the management of simulation centers, has become another important area in the Industry 4.0 phenomenon in terms of digital transformation. In this study, data obtained by messaging a mechanical CardioPulmonary Resuscitation (CPR) first aid training manikin with modularly developed electronic devices were collected. These data are also processed via the developed software that enables them to communicate with both mobile devices and desktop computers, and the integrity of the massage activities performed with the Artificial Intelligence (AI) algorithm is confirmed. The modular kit was developed in the Open Source Laboratory of the Department of Informatics (KOUOSL) with the support of the Dean's office at the Kocaeli University Faculty of Medicine and the Department of Emergency Medicine. CPR massage is seen in the acceptable range if it is applied to the chest at 100-120 times per minute and applied at a depth of about 5-6 cm. In the study, feedback was given to the Observer Trainer on whether an ideal massage was performed by using an AI classifier that evaluates the data collected from the sensors placed on the mannequin to determine if the CPR is accurate and valid. Thus, a more effective practical training application will be developed and provided by digitizing the mechanical mannequin.

Keywords

• CPR Manikin
• ANN
• Digital Transformation
• Classifier
• Medicine

References

1. https://sorgundh.saglik.gov.tr/TR,260227/cpr-yasam-destegi-egitimi.html, (Visited Date: 18.04.2021)
2. American Heart Association. Part 4: Adult basic life support: American Heart Association guidelines for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation, 112(Supplement): IV–20–IV–34, 2005 K. Elissa, “Title of paper if known,” unpublished.
3. Fisher JM. The resuscitation greats. The earliest records. Resuscitation 2000; 4:79-80.
4. https://www.tkd.org.tr/ileri-kardiyak-yasam-destegi kursu/sayfa/CPR_ECC, (Visited Date: 26.03.2021).
5. https://www.resusitasyon.com/yetiskinlerde-temel-yasam-destegi-cpr-kalp-masaji-uygulamalari/, (Visited Date: 22.03.2021)
6. https://www.themt.co/blog/110-elektronik/344-nodemcu-bir-seyleri-wifi-ile-kolayca-baglayin, (Visited Date: 18.03.2021)
7. https://www.esit.com.tr/tr/yuk_hucresi_loadcell__nedir_nasil_calisir/blog/3, (Visited Date: 21.02.2021)
8. https://www.brainy-bits.com/load-cell-and-hx711-with-arduino/, (Visited Date: 12.03.2021)

9. https://maker.robotistan.com/kategori/arduino/, (Visited Date: 19.02.2021)
10. https://www.instructables.com/id/Tutorial-to-Interface-HX711-With-Load-Cell-Straigh/, (Visited date: 21.03.2021)
11. K. B. Arbogast, M. R. Maltese, V. M. Nadkarni, P. A. Steen, and J. B. Nysaether. Anterior-posterior thoracic force-deflection characteristics measured during cardiopulmonary resuscitation: Comparison to post- mortem human subject data. Stapp Car Crash Journal, 50:131–145, November 2006.
12. K. G. Gruben, A. D. Guerci, H. R. Halperin, A. S. Popel, and J. E. Tsit- lik. Sternal force-displacement relationship during cardiopulmonary resuscitation. Journal of Biomechanical Engineering, 115(2):195– 201, 1993