Performance of a computer model to detect misplaced V1 and V2 electrodes on the 12-lead ECG for three dfifferent types of patients

Khaled Rjoob, RR Bond, D Finlay, V. E. McGilligan, Stephen Leslie, Aleeha Iftikhar, Daniel Gueldenring, Charles Knoery, Ali Rababah, Aaron Peace

Research output: Contribution to journalMeeting Abstract

Abstract

Introduction Electrode misplacement can adversely affect Electrocardiogram (ECG) morphology and as a consequence, it can affect interpretation and patient diagnosis. Lead misplacement in ECG acquisition can occur in 40% to 60% of the time; which can result. in false positives (Type-I errors) and false negatives (Type-II errors). V1 and V2 electrodes are commonly misplaced high and wide of their correct positions. Vertically misplaced leads V1 and V2 can conceal real STEMI (ST Elevation Myocardial Infarction) events or emulate a false positive. Lead misplacement detection plays an important role to improve ECG data quality and clinical decision making in cardiac care. The aim of the current work was to develop a computer model using deep learning to detect misplacement of leads V1 and V2 for three different types of patients: 1) old Myocardial Infarction (MI) patients, 2) Left Ventricular Hypertrophy (LVH) Patients and 3) normal sinus rhythm patients, and to find in which patient type the ‘general’ patient-type-agnostic computer model achieves the highest performance.

Methods 12-lead ECGs for 453 subjects, (normal n=151, LVH n=151, MI n=151) were extracted from body surface potential maps. V1 and V2 leads acquired from the second intercostal space (ICS) are considered as incorrect placement and leads from the fourth (IC) are considered as correct. The computer model was developed using deep learning algorithm (bidirectional long short-term memory network (BLSTM)) to detect V1 and V2 misplacement. The computer model was trained on three datasets together and tested on each dataset separately. In each dataset, data were divided into 67% for training and 33% for testing. The prevalence was 50% for correct and incorrect leads.

Results Computer model accuracy using BLSTM of V1 and V2 misplacement detection was 93.0% in normal dataset, 93.0% in MI dataset while the accuracy was 91.0% in LVH dataset.

Conclusion Computer model got a high performance to detect V1 and V2 misplacement in normal and MI ECGs datasets, while the performance decreased in LVH dataset to 91.0%. In future we need to consider MI infarct sites such as anterior, inferior etc to increase accuracy.

Fingerprint

Computer Simulation
Electrocardiography
Electrodes
Myocardial Infarction
Left Ventricular Hypertrophy
Long-Term Memory
Short-Term Memory
Learning
Lead
Datasets

Keywords

  • Machine learning
  • AI
  • cardiology
  • electrode misplacment
  • lead misplacement
  • ECG

Cite this

@article{a95a7e71df0d47cbbdf2bd96a4c698d1,
title = "Performance of a computer model to detect misplaced V1 and V2 electrodes on the 12-lead ECG for three dfifferent types of patients",
abstract = "Introduction Electrode misplacement can adversely affect Electrocardiogram (ECG) morphology and as a consequence, it can affect interpretation and patient diagnosis. Lead misplacement in ECG acquisition can occur in 40{\%} to 60{\%} of the time; which can result. in false positives (Type-I errors) and false negatives (Type-II errors). V1 and V2 electrodes are commonly misplaced high and wide of their correct positions. Vertically misplaced leads V1 and V2 can conceal real STEMI (ST Elevation Myocardial Infarction) events or emulate a false positive. Lead misplacement detection plays an important role to improve ECG data quality and clinical decision making in cardiac care. The aim of the current work was to develop a computer model using deep learning to detect misplacement of leads V1 and V2 for three different types of patients: 1) old Myocardial Infarction (MI) patients, 2) Left Ventricular Hypertrophy (LVH) Patients and 3) normal sinus rhythm patients, and to find in which patient type the ‘general’ patient-type-agnostic computer model achieves the highest performance.Methods 12-lead ECGs for 453 subjects, (normal n=151, LVH n=151, MI n=151) were extracted from body surface potential maps. V1 and V2 leads acquired from the second intercostal space (ICS) are considered as incorrect placement and leads from the fourth (IC) are considered as correct. The computer model was developed using deep learning algorithm (bidirectional long short-term memory network (BLSTM)) to detect V1 and V2 misplacement. The computer model was trained on three datasets together and tested on each dataset separately. In each dataset, data were divided into 67{\%} for training and 33{\%} for testing. The prevalence was 50{\%} for correct and incorrect leads.Results Computer model accuracy using BLSTM of V1 and V2 misplacement detection was 93.0{\%} in normal dataset, 93.0{\%} in MI dataset while the accuracy was 91.0{\%} in LVH dataset.Conclusion Computer model got a high performance to detect V1 and V2 misplacement in normal and MI ECGs datasets, while the performance decreased in LVH dataset to 91.0{\%}. In future we need to consider MI infarct sites such as anterior, inferior etc to increase accuracy.",
keywords = "Machine learning, AI, cardiology, electrode misplacment, lead misplacement, ECG",
author = "Khaled Rjoob and RR Bond and D Finlay and McGilligan, {V. E.} and Stephen Leslie and Aleeha Iftikhar and Daniel Gueldenring and Charles Knoery and Ali Rababah and Aaron Peace",
year = "2019",
month = "10",
day = "16",
doi = "10.1136/heartjnl-2019-ICS.39",
language = "English",
volume = "105",
pages = "A31--A32",
journal = "Heart",
issn = "1355-6037",
number = "7",

}

Performance of a computer model to detect misplaced V1 and V2 electrodes on the 12-lead ECG for three dfifferent types of patients. / Rjoob, Khaled; Bond, RR; Finlay, D; McGilligan, V. E.; Leslie, Stephen; Iftikhar, Aleeha; Gueldenring, Daniel; Knoery, Charles; Rababah, Ali; Peace, Aaron.

In: Heart, Vol. 105, No. 7, 16.10.2019, p. A31-A32.

Research output: Contribution to journalMeeting Abstract

TY - JOUR

T1 - Performance of a computer model to detect misplaced V1 and V2 electrodes on the 12-lead ECG for three dfifferent types of patients

AU - Rjoob, Khaled

AU - Bond, RR

AU - Finlay, D

AU - McGilligan, V. E.

AU - Leslie, Stephen

AU - Iftikhar, Aleeha

AU - Gueldenring, Daniel

AU - Knoery, Charles

AU - Rababah, Ali

AU - Peace, Aaron

PY - 2019/10/16

Y1 - 2019/10/16

N2 - Introduction Electrode misplacement can adversely affect Electrocardiogram (ECG) morphology and as a consequence, it can affect interpretation and patient diagnosis. Lead misplacement in ECG acquisition can occur in 40% to 60% of the time; which can result. in false positives (Type-I errors) and false negatives (Type-II errors). V1 and V2 electrodes are commonly misplaced high and wide of their correct positions. Vertically misplaced leads V1 and V2 can conceal real STEMI (ST Elevation Myocardial Infarction) events or emulate a false positive. Lead misplacement detection plays an important role to improve ECG data quality and clinical decision making in cardiac care. The aim of the current work was to develop a computer model using deep learning to detect misplacement of leads V1 and V2 for three different types of patients: 1) old Myocardial Infarction (MI) patients, 2) Left Ventricular Hypertrophy (LVH) Patients and 3) normal sinus rhythm patients, and to find in which patient type the ‘general’ patient-type-agnostic computer model achieves the highest performance.Methods 12-lead ECGs for 453 subjects, (normal n=151, LVH n=151, MI n=151) were extracted from body surface potential maps. V1 and V2 leads acquired from the second intercostal space (ICS) are considered as incorrect placement and leads from the fourth (IC) are considered as correct. The computer model was developed using deep learning algorithm (bidirectional long short-term memory network (BLSTM)) to detect V1 and V2 misplacement. The computer model was trained on three datasets together and tested on each dataset separately. In each dataset, data were divided into 67% for training and 33% for testing. The prevalence was 50% for correct and incorrect leads.Results Computer model accuracy using BLSTM of V1 and V2 misplacement detection was 93.0% in normal dataset, 93.0% in MI dataset while the accuracy was 91.0% in LVH dataset.Conclusion Computer model got a high performance to detect V1 and V2 misplacement in normal and MI ECGs datasets, while the performance decreased in LVH dataset to 91.0%. In future we need to consider MI infarct sites such as anterior, inferior etc to increase accuracy.

AB - Introduction Electrode misplacement can adversely affect Electrocardiogram (ECG) morphology and as a consequence, it can affect interpretation and patient diagnosis. Lead misplacement in ECG acquisition can occur in 40% to 60% of the time; which can result. in false positives (Type-I errors) and false negatives (Type-II errors). V1 and V2 electrodes are commonly misplaced high and wide of their correct positions. Vertically misplaced leads V1 and V2 can conceal real STEMI (ST Elevation Myocardial Infarction) events or emulate a false positive. Lead misplacement detection plays an important role to improve ECG data quality and clinical decision making in cardiac care. The aim of the current work was to develop a computer model using deep learning to detect misplacement of leads V1 and V2 for three different types of patients: 1) old Myocardial Infarction (MI) patients, 2) Left Ventricular Hypertrophy (LVH) Patients and 3) normal sinus rhythm patients, and to find in which patient type the ‘general’ patient-type-agnostic computer model achieves the highest performance.Methods 12-lead ECGs for 453 subjects, (normal n=151, LVH n=151, MI n=151) were extracted from body surface potential maps. V1 and V2 leads acquired from the second intercostal space (ICS) are considered as incorrect placement and leads from the fourth (IC) are considered as correct. The computer model was developed using deep learning algorithm (bidirectional long short-term memory network (BLSTM)) to detect V1 and V2 misplacement. The computer model was trained on three datasets together and tested on each dataset separately. In each dataset, data were divided into 67% for training and 33% for testing. The prevalence was 50% for correct and incorrect leads.Results Computer model accuracy using BLSTM of V1 and V2 misplacement detection was 93.0% in normal dataset, 93.0% in MI dataset while the accuracy was 91.0% in LVH dataset.Conclusion Computer model got a high performance to detect V1 and V2 misplacement in normal and MI ECGs datasets, while the performance decreased in LVH dataset to 91.0%. In future we need to consider MI infarct sites such as anterior, inferior etc to increase accuracy.

KW - Machine learning

KW - AI

KW - cardiology

KW - electrode misplacment

KW - lead misplacement

KW - ECG

UR - https://heart.bmj.com/content/105/Suppl_7/A31.3.abstract

U2 - 10.1136/heartjnl-2019-ICS.39

DO - 10.1136/heartjnl-2019-ICS.39

M3 - Meeting Abstract

VL - 105

SP - A31-A32

JO - Heart

T2 - Heart

JF - Heart

SN - 1355-6037

IS - 7

ER -