Cargando…
Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening
AIMS: Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can...
Autores principales: | , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946569/ https://www.ncbi.nlm.nih.gov/pubmed/35355847 http://dx.doi.org/10.1093/ehjdh/ztab101 |
_version_ | 1784674225295982592 |
---|---|
author | Somani, Sulaiman S Honarvar, Hossein Narula, Sukrit Landi, Isotta Lee, Shawn Khachatoorian, Yeraz Rehmani, Arsalan Kim, Andrew De Freitas, Jessica K Teng, Shelly Jaladanki, Suraj Kumar, Arvind Russak, Adam Zhao, Shan P Freeman, Robert Levin, Matthew A Nadkarni, Girish N Kagen, Alexander C Argulian, Edgar Glicksberg, Benjamin S |
author_facet | Somani, Sulaiman S Honarvar, Hossein Narula, Sukrit Landi, Isotta Lee, Shawn Khachatoorian, Yeraz Rehmani, Arsalan Kim, Andrew De Freitas, Jessica K Teng, Shelly Jaladanki, Suraj Kumar, Arvind Russak, Adam Zhao, Shan P Freeman, Robert Levin, Matthew A Nadkarni, Girish N Kagen, Alexander C Argulian, Edgar Glicksberg, Benjamin S |
author_sort | Somani, Sulaiman S |
collection | PubMed |
description | AIMS: Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection. METHODS AND RESULTS: We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells’ Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50–0.58, specificity 0.00–0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66–0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77–0.84) subgroups. CONCLUSION: Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE. |
format | Online Article Text |
id | pubmed-8946569 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-89465692022-03-28 Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening Somani, Sulaiman S Honarvar, Hossein Narula, Sukrit Landi, Isotta Lee, Shawn Khachatoorian, Yeraz Rehmani, Arsalan Kim, Andrew De Freitas, Jessica K Teng, Shelly Jaladanki, Suraj Kumar, Arvind Russak, Adam Zhao, Shan P Freeman, Robert Levin, Matthew A Nadkarni, Girish N Kagen, Alexander C Argulian, Edgar Glicksberg, Benjamin S Eur Heart J Digit Health Original Articles AIMS: Clinical scoring systems for pulmonary embolism (PE) screening have low specificity and contribute to computed tomography pulmonary angiogram (CTPA) overuse. We assessed whether deep learning models using an existing and routinely collected data modality, electrocardiogram (ECG) waveforms, can increase specificity for PE detection. METHODS AND RESULTS: We create a retrospective cohort of 21 183 patients at moderate- to high suspicion of PE and associate 23 793 CTPAs (10.0% PE-positive) with 320 746 ECGs and encounter-level clinical data (demographics, comorbidities, vital signs, and labs). We develop three machine learning models to predict PE likelihood: an ECG model using only ECG waveform data, an EHR model using tabular clinical data, and a Fusion model integrating clinical data and an embedded representation of the ECG waveform. We find that a Fusion model [area under the receiver-operating characteristic curve (AUROC) 0.81 ± 0.01] outperforms both the ECG model (AUROC 0.59 ± 0.01) and EHR model (AUROC 0.65 ± 0.01). On a sample of 100 patients from the test set, the Fusion model also achieves greater specificity (0.18) and performance (AUROC 0.84 ± 0.01) than four commonly evaluated clinical scores: Wells’ Criteria, Revised Geneva Score, Pulmonary Embolism Rule-Out Criteria, and 4-Level Pulmonary Embolism Clinical Probability Score (AUROC 0.50–0.58, specificity 0.00–0.05). The model is superior to these scores on feature sensitivity analyses (AUROC 0.66–0.84) and achieves comparable performance across sex (AUROC 0.81) and racial/ethnic (AUROC 0.77–0.84) subgroups. CONCLUSION: Synergistic deep learning of ECG waveforms with traditional clinical variables can increase the specificity of PE detection in patients at least at moderate suspicion for PE. Oxford University Press 2021-11-25 /pmc/articles/PMC8946569/ /pubmed/35355847 http://dx.doi.org/10.1093/ehjdh/ztab101 Text en © The Author(s) 2021. Published by Oxford University Press on behalf of the European Society of Cardiology. https://creativecommons.org/licenses/by-nc/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com |
spellingShingle | Original Articles Somani, Sulaiman S Honarvar, Hossein Narula, Sukrit Landi, Isotta Lee, Shawn Khachatoorian, Yeraz Rehmani, Arsalan Kim, Andrew De Freitas, Jessica K Teng, Shelly Jaladanki, Suraj Kumar, Arvind Russak, Adam Zhao, Shan P Freeman, Robert Levin, Matthew A Nadkarni, Girish N Kagen, Alexander C Argulian, Edgar Glicksberg, Benjamin S Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title | Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title_full | Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title_fullStr | Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title_full_unstemmed | Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title_short | Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
title_sort | development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening |
topic | Original Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946569/ https://www.ncbi.nlm.nih.gov/pubmed/35355847 http://dx.doi.org/10.1093/ehjdh/ztab101 |
work_keys_str_mv | AT somanisulaimans developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT honarvarhossein developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT narulasukrit developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT landiisotta developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT leeshawn developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT khachatoorianyeraz developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT rehmaniarsalan developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT kimandrew developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT defreitasjessicak developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT tengshelly developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT jaladankisuraj developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT kumararvind developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT russakadam developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT zhaoshanp developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT freemanrobert developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT levinmatthewa developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT nadkarnigirishn developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT kagenalexanderc developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT argulianedgar developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening AT glicksbergbenjamins developmentofamachinelearningmodelusingelectrocardiogramsignalstoimproveacutepulmonaryembolismscreening |