Automated Diagnostic Reports from Images of Electrocardiograms at the Point-of-Care
Timely and accurate assessment of electrocardiograms (ECGs) is crucial for diagnosing, triaging, and clinically managing patients. Current workflows rely on a computerized ECG interpretation using rule-based tools built into the ECG signal acquisition systems with limited accuracy and flexibility. In low-resource settings, specialists must review every single ECG for such decisions, as these computerized interpretations are not available. Additionally, high-quality interpretations are even more essential in such low-resource settings as there is a higher burden of accuracy for automated reads when access to experts is limited. Artificial Intelligence (AI)-based systems have the prospect of greater accuracy yet are frequently limited to a narrow range of conditions and do not replicate the full diagnostic range. Moreover, these models often require raw signal data, which are unavailable to physicians and necessitate costly technical integrations that are currently limited. To overcome these challenges, we developed and validated a format-independent vision encoder-decoder model - ECG-GPT - that can generate free-text, expert-level diagnosis statements directly from ECG images. The model shows robust performance, validated on 2.6 million ECGs across 6 geographically distinct health settings: (1) 2 large and diverse US health systems- Yale-New Haven and Mount Sinai Health Systems, (2) a consecutive ECG dataset from a central ECG repository from Minas Gerais, Brazil, (3) the prospective cohort study, UK Biobank, (4) a Germany-based, publicly available repository, PTB-XL, and (5) a community hospital in Missouri. The model demonstrated consistently high performance (AUROC≥0.81) across a wide range of rhythm and conduction disorders. This can be easily accessed via a web-based application capable of receiving ECG images and represents a scalable and accessible strategy for generating accurate, expert-level reports from images of ECGs, enabling accurate triage of patients globally, especially in low-resource settings.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - year:2024 |
|---|---|
| Enthalten in: |
medRxiv : the preprint server for health sciences - (2024) vom: 18. Feb. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Khunte, Akshay [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Revised 04.03.2024 published: Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1101/2024.02.17.24302976 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM368957500 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM368957500 | ||
| 003 | DE-627 | ||
| 005 | 20240304232632.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240229s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/2024.02.17.24302976 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1316.xml |
| 035 | |a (DE-627)NLM368957500 | ||
| 035 | |a (NLM)38405776 | ||
| 035 | |a (PII)2024.02.17.24302976 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Khunte, Akshay |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Automated Diagnostic Reports from Images of Electrocardiograms at the Point-of-Care |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 04.03.2024 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Timely and accurate assessment of electrocardiograms (ECGs) is crucial for diagnosing, triaging, and clinically managing patients. Current workflows rely on a computerized ECG interpretation using rule-based tools built into the ECG signal acquisition systems with limited accuracy and flexibility. In low-resource settings, specialists must review every single ECG for such decisions, as these computerized interpretations are not available. Additionally, high-quality interpretations are even more essential in such low-resource settings as there is a higher burden of accuracy for automated reads when access to experts is limited. Artificial Intelligence (AI)-based systems have the prospect of greater accuracy yet are frequently limited to a narrow range of conditions and do not replicate the full diagnostic range. Moreover, these models often require raw signal data, which are unavailable to physicians and necessitate costly technical integrations that are currently limited. To overcome these challenges, we developed and validated a format-independent vision encoder-decoder model - ECG-GPT - that can generate free-text, expert-level diagnosis statements directly from ECG images. The model shows robust performance, validated on 2.6 million ECGs across 6 geographically distinct health settings: (1) 2 large and diverse US health systems- Yale-New Haven and Mount Sinai Health Systems, (2) a consecutive ECG dataset from a central ECG repository from Minas Gerais, Brazil, (3) the prospective cohort study, UK Biobank, (4) a Germany-based, publicly available repository, PTB-XL, and (5) a community hospital in Missouri. The model demonstrated consistently high performance (AUROC≥0.81) across a wide range of rhythm and conduction disorders. This can be easily accessed via a web-based application capable of receiving ECG images and represents a scalable and accessible strategy for generating accurate, expert-level reports from images of ECGs, enabling accurate triage of patients globally, especially in low-resource settings | ||
| 650 | 4 | |a Preprint | |
| 700 | 1 | |a Sangha, Veer |e verfasserin |4 aut | |
| 700 | 1 | |a Oikonomou, Evangelos K |e verfasserin |4 aut | |
| 700 | 1 | |a Dhingra, Lovedeep S |e verfasserin |4 aut | |
| 700 | 1 | |a Aminorroaya, Arya |e verfasserin |4 aut | |
| 700 | 1 | |a Coppi, Andreas |e verfasserin |4 aut | |
| 700 | 1 | |a Shankar, Sumukh Vasisht |e verfasserin |4 aut | |
| 700 | 1 | |a Mortazavi, Bobak J |e verfasserin |4 aut | |
| 700 | 1 | |a Bhatt, Deepak L |e verfasserin |4 aut | |
| 700 | 1 | |a Krumholz, Harlan M |e verfasserin |4 aut | |
| 700 | 1 | |a Nadkarni, Girish N |e verfasserin |4 aut | |
| 700 | 1 | |a Vaid, Akhil |e verfasserin |4 aut | |
| 700 | 1 | |a Khera, Rohan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t medRxiv : the preprint server for health sciences |d 2020 |g (2024) vom: 18. Feb. |w (DE-627)NLM310900166 |7 nnns |
| 773 | 1 | 8 | |g year:2024 |g day:18 |g month:02 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/2024.02.17.24302976 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 18 |c 02 | ||