Automated Analysis of the 12-lead ECG in the Emergency Department

Tereshchenko, Larisa G.; Gatz, J. David; Feeny, Albert; Korley, Frederick K.

doi:10.1097/hpc.0000000000000006

Cited by 7 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an ancillary study of a prospective observational cohort study [7–9] of emergency department (ED) patients evaluated for ACS at the Johns Hopkins Hospital (JHH). The study was approved by the Institutional Review Board, and all participants provided written informed consent.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Patient:Specific Time:Varying Association between Spatial and Temporal Variability in Repolarization and High Sensitivity Troponin I

Tereshchenko

Feeny

2016

2016 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

“…Inclusion and exclusion criteria of the JHH ED prospective cohort study have been previously described [7–9]. Briefly, the original cohort [7] enrolled consecutive patients with suspected ACS of age 25 or older, who presented to the JHH ED with a non-diagnostic initial ECG.…”

Section: Methodsmentioning

confidence: 99%

Patient:Specific Time:Varying Association between Spatial and Temporal Variability in Repolarization and High Sensitivity Troponin I

Tereshchenko

Feeny

2016

2016 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…An overall picture of language models release and parameters size, with the publicly accessible GPT-4 [48] and recently reported PanGu-Σ [49] models highlighted. case of ECG, groundbreaking ECG technologies and devices, such as Universal ECG TM [40]- [44], can potentially benefit from obtaining a second-opinion of or an early analysis from an AI machine in particular in case of a junior medical doctor, under pressure emergency department practices, as part of a medical education program or in clinically challenging scenarios.…”

Section: Introductionmentioning

confidence: 99%

BioSignal Copilot: Leveraging the power of LLMs in drafting reports for biomedical signals

Liu

Kothur

et al. 2023

Preprint

View full text Add to dashboard Cite

Recent advances in Large Language Models (LLMs) have shown great potential in various domains, particularly in processing text-based data. However, their applicability to biomedical time-series signals (e.g. electrograms) remains largely unexplored due to the lack of a signal-to-text (sequence) engine to harness the power of LLMs. The application of biosignals has been growing due to the improvements in the reliability, noise and performance of front-end sensing, and back-end signal processing, despite lowering the number of sensing components (e.g. electrodes) needed for effective and long-term use (e.g. in wearable or implantable devices). One of the most reliable techniques used in clinical settings is producing a technical/clinical report on the quality and features of collected data and using that alongside a set of auxiliary or complementary data (e.g. imaging, blood tests, medical records). This work addresses the missing puzzle in implementing conversational artificial intelligence (AI), a reliable, technical and clinically relevant signal-to-text (Sig2Txt) engine. While medical foundation models can be expected, reports of Sig2Txt engine in large scale can be utilised in years to come to develop foundational models for a unified purpose. In this work, we propose a system (SignalGPT or BioSignal Copilot) that reduces medical signals to a freestyle or formatted clinical, technical report close to a brief clinical report capturing key features and characterisation of input signal. In its ideal form, this system provides the tool necessary to produce the technical input sequence necessary for LLMs as a step toward using AI in the medical and clinical domains as an assistant to clinicians and patients. To the best of our knowledge, this is the first system for bioSig2Txt generation, and the idea can be used in other domains as well to produce technical reports to harness the power of LLMs. This method also improves the interpretability and tracking (history) of information into and out of the AI models. We did implement this aspect through a buffer in our system. As a preliminary step, we verify the feasibility of the BioSignal Copilot (SignalGPT) using a clinical ECG dataset to demonstrate the advantages of the proposed system. In this feasibility study, we used prompts and fine-tuning to prevent fluctuations in response. The combination of biosignal processing and natural language processing offers a promising solution that improves the interpretability of the results obtained from AI, which also leverages the rapid growth of LLMs.

show abstract

“…5 Others have correlated a rise in CEB with a subsequent rise in serum troponin measurements. 6 We hypothesized that the Vectraplex CEB would increase the specificity of the diagnosis of STEMI while maintaining sensitivity.…”

mentioning

confidence: 99%

Sensitivity and specificity of the Vectraplex electrocardiogram system with a cardiac electric biomarker in the diagnosis of ST-elevation myocardial infarction

Mixon¹,

Hardegree²,

Shah³

et al. 2019

Baylor University Medical Center Proceedings

View full text Add to dashboard Cite

ST-elevation myocardial infarction (STEMI) is a clinical diagnosis based on a compatible history and characteristic electrocardiographic changes. In the current era, STEMI is treated emergently with angiography, leading to percutaneous coronary intervention. However, false-positive electrocardiograms (ECGs) occur, resulting in unnecessary emergent catheterizations. We hypothesized that the Vectraplex cardiac electrical biomarker (CEB) would increase the specificity for the diagnosis of STEMI. We studied 50 patients who were identified by standard of care (clinical history, physical exam, and 12-lead ECG) as suspected to have STEMI and tested the sensitivity and specificity of the Vectraplex ECG system. Using the final clinical diagnosis (based on history, ECGs, troponin values, and angiographic findings) as the gold standard, we found the CEB value to be quite dynamic, with a reasonable sensitivity and a good positive predictive value but generally poor specificity and negative predictive value. It offered only a 20% improvement compared to 50-50 performance on receiver operator curves.

show abstract

Automated Analysis of the 12-lead ECG in the Emergency Department

Cited by 7 publications

References 21 publications

Patient:Specific Time:Varying Association between Spatial and Temporal Variability in Repolarization and High Sensitivity Troponin I

Patient:Specific Time:Varying Association between Spatial and Temporal Variability in Repolarization and High Sensitivity Troponin I

BioSignal Copilot: Leveraging the power of LLMs in drafting reports for biomedical signals

Sensitivity and specificity of the Vectraplex electrocardiogram system with a cardiac electric biomarker in the diagnosis of ST-elevation myocardial infarction

Contact Info

Product

Resources

About