Smartphone AI vs. Medical Experts: A Comparative Study in Prehospital STEMI Diagnosis
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Purpose: Prehospital telecardiology facilitates early ST-elevation myocardial infarction (STEMI) detection, yet its widespread im plementation remains challenging. Extracting digital STEMI biomarkers from printed electrocardiograms (ECGs) using phone cameras could offer an affordable and scalable solution. This study assessed the feasibility of this approach with real-world pre hospital ECGs. Materials and Methods: Patients suspected of having STEMI by emergency medical technicians (EMTs) were identified from a policy research dataset. A deep learning-based ECG analyzer (QCGTM analyzer) extracted a STEMI biomarker (qSTEMI) from prehos pital ECGs. The biomarker was compared to a group of human experts, including five emergency medical service directors (board certified emergency physicians) and three interventional cardiologists based on their consensus score (number of participants an swering “yes” for STEMI). Non-inferiority of the biomarker was tested using a 0.100 margin of difference in sensitivity and specificity. Results: Among 53 analyzed patients (24 STEMI, 45.3%), the area under the receiver operating characteristic curve of qSTEMI and consensus score were 0.815 (0.691–0.938) and 0.736 (0.594–0.879), respectively (p=0.081). Sensitivity, specificity, positive pre dictive value (PPV), and negative predictive value (NPV) of qSTEMI were 0.750 (0.583–0.917), 0.862 (0.690–0.966), 0.826 (0.679–0.955), and 0.813 (0.714–0.929), respectively. For the consensus score, sensitivity, specificity, PPV, and NPV were 0.708 (0.500–0.875), 0.793 (0.655–0.966), 0.750 (0.600–0.941), and 0.760 (0.655–0.880), respectively. The 95% confidence interval of sensitivity and specificity differences between qSTEMI and consensus score were 0.042 (-0.099–0.182) and 0.103 (-0.043–0.250), respectively, confirming qSTEMI’s non-inferiority. Conclusion: The digital STEMI biomarker, derived from printed prehospital ECGs, demonstrated non-inferiority to expert con sensus, indicating a promising approach for enhancing prehospital telecardiology.
Abstract
Purpose: Prehospital telecardiology facilitates early ST-elevation myocardial infarction (STEMI) detection, yet its widespread im plementation remains challenging. Extracting digital STEMI biomarkers from printed electrocardiograms (ECGs) using phone cameras could offer an affordable and scalable solution. This study assessed the feasibility of this approach with real-world pre hospital ECGs. Materials and Methods: Patients suspected of having STEMI by emergency medical technicians (EMTs) were identified from a policy research dataset. A deep learning-based ECG analyzer (QCGTM analyzer) extracted a STEMI biomarker (qSTEMI) from prehos pital ECGs. The biomarker was compared to a group of human experts, including five emergency medical service directors (board certified emergency physicians) and three interventional cardiologists based on their consensus score (number of participants an swering “yes” for STEMI). Non-inferiority of the biomarker was tested using a 0.100 margin of difference in sensitivity and specificity. Results: Among 53 analyzed patients (24 STEMI, 45.3%), the area under the receiver operating characteristic curve of qSTEMI and consensus score were 0.815 (0.691–0.938) and 0.736 (0.594–0.879), respectively (p=0.081). Sensitivity, specificity, positive pre dictive value (PPV), and negative predictive value (NPV) of qSTEMI were 0.750 (0.583–0.917), 0.862 (0.690–0.966), 0.826 (0.679–0.955), and 0.813 (0.714–0.929), respectively. For the consensus score, sensitivity, specificity, PPV, and NPV were 0.708 (0.500–0.875), 0.793 (0.655–0.966), 0.750 (0.600–0.941), and 0.760 (0.655–0.880), respectively. The 95% confidence interval of sensitivity and specificity differences between qSTEMI and consensus score were 0.042 (-0.099–0.182) and 0.103 (-0.043–0.250), respectively, confirming qSTEMI’s non-inferiority. Conclusion: The digital STEMI biomarker, derived from printed prehospital ECGs, demonstrated non-inferiority to expert con sensus, indicating a promising approach for enhancing prehospital telecardiology.
참고문헌 (17)
- Ibanez B, "2017 ESC guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation : the task force for the management of acute myocardial infarction in patients presenting with ST-segment elevation of the European Society of Cardiology(ESC)", Eur Heart J, 39, pp.119~177 (2018)
- Lawton JS, "2021 ACC", AHA, American Heart Association Joint Committee on clinical practice guidelines, pp.Circulation, 2022[DOI]
- Stiermaier T, "Reperfusion strategies in ST-segment elevation myocardial infarction", Minerva Med, 104, pp.391~411 (2013)
- Bosson N, "The utility of prehospital ECG transmission in a large EMS system", Prehosp Emerg Care, 19, pp.496~503 (2015)
- Attia ZI, "Application of artificial intelligence to the electrocardiogram", Eur Heart J, 42, pp.4717~4730 (2021)
- Kim D, "A retrospective clinical evaluation of an artificial intelligence screening method for early detection of STEMI in the emergency department", J Korean Med Sci, 37, pp.e81~ (2022)
- Al-Zaiti S, "Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram", Nat Commun, 11, pp.3966~ (2020)
- Siontis KC, "Artificial intelligence-enhanced electrocardiography in cardiovascular disease management", Nat Rev Cardiol, 18, pp.465~478 (2021)
- Choi YJ, "Artificial intelligence versus physicians on interpretation of printed ECG images : diagnostic performance of ST-elevation myocardial infarction on electrocardiography", Int J Cardiol, 363, pp.6~10 (2022)
- Lee SH, "Effects of a designated ambulance team response on prehospital return of spontaneous circulation and advanced cardiac life support of out-of-hospital cardiac arrest : a nationwide natural experimental study", Prehosp Emerg Care, 27, pp.736~743 (2023)
- Perkins NJ, "The inconsistency of"optimal"cutpoints obtained using two criteria based on the receiver operating characteristic curve", Am J Epidemiol, 163, pp.670~675 (2006)
- Altman DG, "Practical statistics for medical research" (1991), Chapman & Hall
- Saberian P, "The effect of prehospital telecardiology on the mortality and morbidity of ST-segment elevated myocardial infarction patients undergoing primary percutaneous coronary intervention : a cross-sectional study", Turk J Emerg Med, 20, pp.28~34 (2020)
- Mohammadzadeh N, "Telecardiology interventions for patients with cardiovascular disease : a systematic review on characteristics and effects", Int J Med Inform, 158, pp.104663~ (2021)
- Attia ZI, "Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram", Nat Med, 25, pp.70~74 (2019)
- Yao X, "Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction : a pragmatic, randomized clinical trial", Nat Med, 27, pp.815~819 (2021)
- Chen SW, "Review of ECG detection and classification based on deep learning : coherent taxonomy, motivation, open challenges and recommendations", Biomed Signal Process Control, 74, pp.103493~ (2022)