PlumX Metrics
Embed PlumX Metrics

Development of a machine learning model using electrocardiogram signals to improve acute pulmonary embolism screening

European Heart Journal - Digital Health, ISSN: 2634-3916, Vol: 3, Issue: 1, Page: 56-66
2022
  • 12
    Citations
  • 0
    Usage
  • 28
    Captures
  • 5
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Most Recent News

Mount Sinai Hospital: Could EKGs Help Doctors Use AI to Detect Pulmonary Embolisms?

(TNSJou) -- Mount Sinai Hospital issued the following news release: Pulmonary embolisms are dangerous, lung-clogging blot clots. In a pilot study, scientists at the Icahn

Article 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.

Bibliographic Details

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

Oxford University Press (OUP)

Medicine

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know