Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients

Shinichi Goto, Mai Kimura, Yoshinori Katsumata, Shinya Goto, Takashi Kamatani, Genki Ichihara, Seien Ko, Junichi Sasaki, Keiichi Fukuda, Motoaki Sano

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background :Patient with acute coronary syndrome benefits from early revascularization. However, methods for the selection of patients who require urgent revascularization from a variety of patients visiting the emergency room with chest symptoms is not fully established. Electrocardiogram is an easy and rapid procedure, but may contain crucial information not recognized even by well-trained physicians. Objective: To make a prediction model for the needs for urgent revascularization from 12-lead electrocardiogram recorded in the emergency room. Method: We developed an artificial intelligence model enabling the detection of hidden information from a 12-lead electrocardiogram recorded in the emergency room. Electrocardiograms obtained from consecutive patients visiting the emergency room at Keio University Hospital from January 2012 to April 2018 with chest discomfort was collected. These data were splitted into validation and derivation dataset with no duplication in each dataset. The artificial intelligence model was constructed to select patients who require urgent revascularization within 48 hours. The model was trained with the derivation dataset and tested using the validation dataset. Results: Of the consecutive 39,619 patients visiting the emergency room with chest discomfort, 362 underwent urgent revascularization. Of them, 249 were included in the derivation dataset and the remaining 113 were included in validation dataset. For the control, 300 were randomly selected as derivation dataset and another 130 patients were randomly selected for validation dataset from the 39,317 who did not undergo urgent revascularization. On validation, our artificial intelligence model had predictive value of the c-statistics 0.88 (95% CI 0.84-0.93) for detecting patients who required urgent revascularization. Conclusions: Our artificial intelligence model provides information to select patients who need urgent revascularization from only 12-leads electrocardiogram in those visiting the emergency room with chest discomfort.

Original languageEnglish
Article number0210103
JournalPLoS One
Volume14
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Emergency rooms
artificial intelligence
Artificial Intelligence
electrocardiography
Electrocardiography
Artificial intelligence
Emergencies
Hospital Emergency Service
chest
Thorax
Lead
Datasets
Acute Coronary Syndrome
Statistics
selection methods
Patient Selection
physicians
signs and symptoms (animals and humans)
statistics
Physicians

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients. / Goto, Shinichi; Kimura, Mai; Katsumata, Yoshinori; Goto, Shinya; Kamatani, Takashi; Ichihara, Genki; Ko, Seien; Sasaki, Junichi; Fukuda, Keiichi; Sano, Motoaki.

In: PLoS One, Vol. 14, No. 1, 0210103, 01.01.2019.

Research output: Contribution to journalArticle

Goto, Shinichi ; Kimura, Mai ; Katsumata, Yoshinori ; Goto, Shinya ; Kamatani, Takashi ; Ichihara, Genki ; Ko, Seien ; Sasaki, Junichi ; Fukuda, Keiichi ; Sano, Motoaki. / Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients. In: PLoS One. 2019 ; Vol. 14, No. 1.
@article{5410ea6ad8174f858ee207a41c7acc94,
title = "Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients",
abstract = "Background :Patient with acute coronary syndrome benefits from early revascularization. However, methods for the selection of patients who require urgent revascularization from a variety of patients visiting the emergency room with chest symptoms is not fully established. Electrocardiogram is an easy and rapid procedure, but may contain crucial information not recognized even by well-trained physicians. Objective: To make a prediction model for the needs for urgent revascularization from 12-lead electrocardiogram recorded in the emergency room. Method: We developed an artificial intelligence model enabling the detection of hidden information from a 12-lead electrocardiogram recorded in the emergency room. Electrocardiograms obtained from consecutive patients visiting the emergency room at Keio University Hospital from January 2012 to April 2018 with chest discomfort was collected. These data were splitted into validation and derivation dataset with no duplication in each dataset. The artificial intelligence model was constructed to select patients who require urgent revascularization within 48 hours. The model was trained with the derivation dataset and tested using the validation dataset. Results: Of the consecutive 39,619 patients visiting the emergency room with chest discomfort, 362 underwent urgent revascularization. Of them, 249 were included in the derivation dataset and the remaining 113 were included in validation dataset. For the control, 300 were randomly selected as derivation dataset and another 130 patients were randomly selected for validation dataset from the 39,317 who did not undergo urgent revascularization. On validation, our artificial intelligence model had predictive value of the c-statistics 0.88 (95{\%} CI 0.84-0.93) for detecting patients who required urgent revascularization. Conclusions: Our artificial intelligence model provides information to select patients who need urgent revascularization from only 12-leads electrocardiogram in those visiting the emergency room with chest discomfort.",
author = "Shinichi Goto and Mai Kimura and Yoshinori Katsumata and Shinya Goto and Takashi Kamatani and Genki Ichihara and Seien Ko and Junichi Sasaki and Keiichi Fukuda and Motoaki Sano",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0210103",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

TY - JOUR

T1 - Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients

AU - Goto, Shinichi

AU - Kimura, Mai

AU - Katsumata, Yoshinori

AU - Goto, Shinya

AU - Kamatani, Takashi

AU - Ichihara, Genki

AU - Ko, Seien

AU - Sasaki, Junichi

AU - Fukuda, Keiichi

AU - Sano, Motoaki

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background :Patient with acute coronary syndrome benefits from early revascularization. However, methods for the selection of patients who require urgent revascularization from a variety of patients visiting the emergency room with chest symptoms is not fully established. Electrocardiogram is an easy and rapid procedure, but may contain crucial information not recognized even by well-trained physicians. Objective: To make a prediction model for the needs for urgent revascularization from 12-lead electrocardiogram recorded in the emergency room. Method: We developed an artificial intelligence model enabling the detection of hidden information from a 12-lead electrocardiogram recorded in the emergency room. Electrocardiograms obtained from consecutive patients visiting the emergency room at Keio University Hospital from January 2012 to April 2018 with chest discomfort was collected. These data were splitted into validation and derivation dataset with no duplication in each dataset. The artificial intelligence model was constructed to select patients who require urgent revascularization within 48 hours. The model was trained with the derivation dataset and tested using the validation dataset. Results: Of the consecutive 39,619 patients visiting the emergency room with chest discomfort, 362 underwent urgent revascularization. Of them, 249 were included in the derivation dataset and the remaining 113 were included in validation dataset. For the control, 300 were randomly selected as derivation dataset and another 130 patients were randomly selected for validation dataset from the 39,317 who did not undergo urgent revascularization. On validation, our artificial intelligence model had predictive value of the c-statistics 0.88 (95% CI 0.84-0.93) for detecting patients who required urgent revascularization. Conclusions: Our artificial intelligence model provides information to select patients who need urgent revascularization from only 12-leads electrocardiogram in those visiting the emergency room with chest discomfort.

AB - Background :Patient with acute coronary syndrome benefits from early revascularization. However, methods for the selection of patients who require urgent revascularization from a variety of patients visiting the emergency room with chest symptoms is not fully established. Electrocardiogram is an easy and rapid procedure, but may contain crucial information not recognized even by well-trained physicians. Objective: To make a prediction model for the needs for urgent revascularization from 12-lead electrocardiogram recorded in the emergency room. Method: We developed an artificial intelligence model enabling the detection of hidden information from a 12-lead electrocardiogram recorded in the emergency room. Electrocardiograms obtained from consecutive patients visiting the emergency room at Keio University Hospital from January 2012 to April 2018 with chest discomfort was collected. These data were splitted into validation and derivation dataset with no duplication in each dataset. The artificial intelligence model was constructed to select patients who require urgent revascularization within 48 hours. The model was trained with the derivation dataset and tested using the validation dataset. Results: Of the consecutive 39,619 patients visiting the emergency room with chest discomfort, 362 underwent urgent revascularization. Of them, 249 were included in the derivation dataset and the remaining 113 were included in validation dataset. For the control, 300 were randomly selected as derivation dataset and another 130 patients were randomly selected for validation dataset from the 39,317 who did not undergo urgent revascularization. On validation, our artificial intelligence model had predictive value of the c-statistics 0.88 (95% CI 0.84-0.93) for detecting patients who required urgent revascularization. Conclusions: Our artificial intelligence model provides information to select patients who need urgent revascularization from only 12-leads electrocardiogram in those visiting the emergency room with chest discomfort.

UR - http://www.scopus.com/inward/record.url?scp=85059797493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059797493&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0210103

DO - 10.1371/journal.pone.0210103

M3 - Article

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 1

M1 - 0210103

ER -