An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction

(1) Background: While an artificial intelligence (AI)-based, cardiologist-level, deep-learning model for detecting acute myocardial infarction (AMI), based on a 12-lead electrocardiogram (ECG), has been established to have extraordinary capabilities, its real-world performance and clinical applicati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wen-Cheng Liu, Chin Lin, Chin-Sheng Lin, Min-Chien Tsai, Sy-Jou Chen, Shih-Hung Tsai, Wei-Shiang Lin, Chia-Cheng Lee, Tien-Ping Tsao, Cheng-Chung Cheng
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial intelligence acute myocardial infarction alarm system deep learning electrocardiogram Medicine R
Acceso en línea:	https://doaj.org/article/7475b099fb004dae88123a72e58c8ac3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7475b099fb004dae88123a72e58c8ac3
record_format	dspace
spelling	oai:doaj.org-article:7475b099fb004dae88123a72e58c8ac32021-11-25T18:07:34ZAn Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction10.3390/jpm111111492075-4426https://doaj.org/article/7475b099fb004dae88123a72e58c8ac32021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4426/11/11/1149https://doaj.org/toc/2075-4426(1) Background: While an artificial intelligence (AI)-based, cardiologist-level, deep-learning model for detecting acute myocardial infarction (AMI), based on a 12-lead electrocardiogram (ECG), has been established to have extraordinary capabilities, its real-world performance and clinical applications are currently unknown. (2) Methods and Results: To set up an artificial intelligence-based alarm strategy (AI-S) for detecting AMI, we assembled a strategy development cohort including 25,002 visits from August 2019 to April 2020 and a prospective validation cohort including 14,296 visits from May to August 2020 at an emergency department. The components of AI-S consisted of chest pain symptoms, a 12-lead ECG, and high-sensitivity troponin I. The primary endpoint was to assess the performance of AI-S in the prospective validation cohort by evaluating F-measure, precision, and recall. The secondary endpoint was to evaluate the impact on door-to-balloon (DtoB) time before and after AI-S implementation in STEMI patients treated with primary percutaneous coronary intervention (PPCI). Patients with STEMI were alerted precisely by AI-S (F-measure = 0.932, precision of 93.2%, recall of 93.2%). Strikingly, in comparison with pre-AI-S (N = 57) and post-AI-S (N = 32) implantation in STEMI protocol, the median ECG-to-cardiac catheterization laboratory activation (EtoCCLA) time was significantly reduced from 6.0 (IQR, 5.0–8.0 min) to 4.0 min (IQR, 3.0–5.0 min) (<i>p</i> < 0.01). The median DtoB time was shortened from 69 (IQR, 61.0–82.0 min) to 61 min (IQR, 56.8–73.2 min) (<i>p</i> = 0.037). (3) Conclusions: AI-S offers front-line physicians a timely and reliable diagnostic decision-support system, thereby significantly reducing EtoCCLA and DtoB time, and facilitating the PPCI process. Nevertheless, large-scale, multi-institute, prospective, or randomized control studies are necessary to further confirm its real-world performance.Wen-Cheng LiuChin LinChin-Sheng LinMin-Chien TsaiSy-Jou ChenShih-Hung TsaiWei-Shiang LinChia-Cheng LeeTien-Ping TsaoCheng-Chung ChengMDPI AGarticleartificial intelligenceacute myocardial infarctionalarm systemdeep learningelectrocardiogramMedicineRENJournal of Personalized Medicine, Vol 11, Iss 1149, p 1149 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence acute myocardial infarction alarm system deep learning electrocardiogram Medicine R
spellingShingle	artificial intelligence acute myocardial infarction alarm system deep learning electrocardiogram Medicine R Wen-Cheng Liu Chin Lin Chin-Sheng Lin Min-Chien Tsai Sy-Jou Chen Shih-Hung Tsai Wei-Shiang Lin Chia-Cheng Lee Tien-Ping Tsao Cheng-Chung Cheng An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
description	(1) Background: While an artificial intelligence (AI)-based, cardiologist-level, deep-learning model for detecting acute myocardial infarction (AMI), based on a 12-lead electrocardiogram (ECG), has been established to have extraordinary capabilities, its real-world performance and clinical applications are currently unknown. (2) Methods and Results: To set up an artificial intelligence-based alarm strategy (AI-S) for detecting AMI, we assembled a strategy development cohort including 25,002 visits from August 2019 to April 2020 and a prospective validation cohort including 14,296 visits from May to August 2020 at an emergency department. The components of AI-S consisted of chest pain symptoms, a 12-lead ECG, and high-sensitivity troponin I. The primary endpoint was to assess the performance of AI-S in the prospective validation cohort by evaluating F-measure, precision, and recall. The secondary endpoint was to evaluate the impact on door-to-balloon (DtoB) time before and after AI-S implementation in STEMI patients treated with primary percutaneous coronary intervention (PPCI). Patients with STEMI were alerted precisely by AI-S (F-measure = 0.932, precision of 93.2%, recall of 93.2%). Strikingly, in comparison with pre-AI-S (N = 57) and post-AI-S (N = 32) implantation in STEMI protocol, the median ECG-to-cardiac catheterization laboratory activation (EtoCCLA) time was significantly reduced from 6.0 (IQR, 5.0–8.0 min) to 4.0 min (IQR, 3.0–5.0 min) (<i>p</i> < 0.01). The median DtoB time was shortened from 69 (IQR, 61.0–82.0 min) to 61 min (IQR, 56.8–73.2 min) (<i>p</i> = 0.037). (3) Conclusions: AI-S offers front-line physicians a timely and reliable diagnostic decision-support system, thereby significantly reducing EtoCCLA and DtoB time, and facilitating the PPCI process. Nevertheless, large-scale, multi-institute, prospective, or randomized control studies are necessary to further confirm its real-world performance.
format	article
author	Wen-Cheng Liu Chin Lin Chin-Sheng Lin Min-Chien Tsai Sy-Jou Chen Shih-Hung Tsai Wei-Shiang Lin Chia-Cheng Lee Tien-Ping Tsao Cheng-Chung Cheng
author_facet	Wen-Cheng Liu Chin Lin Chin-Sheng Lin Min-Chien Tsai Sy-Jou Chen Shih-Hung Tsai Wei-Shiang Lin Chia-Cheng Lee Tien-Ping Tsao Cheng-Chung Cheng
author_sort	Wen-Cheng Liu
title	An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
title_short	An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
title_full	An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
title_fullStr	An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
title_full_unstemmed	An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction
title_sort	artificial intelligence-based alarm strategy facilitates management of acute myocardial infarction
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7475b099fb004dae88123a72e58c8ac3
work_keys_str_mv	AT wenchengliu anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chinlin anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chinshenglin anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT minchientsai anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT syjouchen anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT shihhungtsai anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT weishianglin anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chiachenglee anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT tienpingtsao anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chengchungcheng anartificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT wenchengliu artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chinlin artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chinshenglin artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT minchientsai artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT syjouchen artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT shihhungtsai artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT weishianglin artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chiachenglee artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT tienpingtsao artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction AT chengchungcheng artificialintelligencebasedalarmstrategyfacilitatesmanagementofacutemyocardialinfarction
_version_	1718411622647595008

An Artificial Intelligence-Based Alarm Strategy Facilitates Management of Acute Myocardial Infarction

Ejemplares similares