Artificial Intelligence-Enabled Electrocardiogram Improves the Diagnosis and Prediction of Mortality in Patients With Pulmonary Hypertension

Liu, Chih-Min; Shih, Edward S.C.; Chen, Jhih-Yu; Huang, Chih-Han; Wu, I-Chien; Chen, Pei-Fen; Higa, Satoshi; Yagi, Nobumori; Hu, Yu Feng; Hwang, Ming‐Jing; Chen, Shih‐Ann

doi:10.1016/j.jacasi.2022.02.008

Cited by 18 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their 2022 work, they utilized a deep learning model with 10-fold cross-validation neural network, taking advantage of 41,097 patient data. Results show that AUC was 0.88 with 81.0% sensitivity and 79.6% specificity [ 20 ].…”

Section: Resultsmentioning

confidence: 99%

Diagnostic AI and Cardiac Diseases

Ozsahin

Ozgocmen²,

Balcioglu³

et al. 2022

Diagnostics

View full text Add to dashboard Cite

(1) Background: The purpose of this study is to review and highlight recent advances in diagnostic uses of artificial intelligence (AI) for cardiac diseases, in order to emphasize expected benefits to both patients and healthcare specialists; (2) Methods: We focused on four key search terms (Cardiac Disease, diagnosis, artificial intelligence, machine learning) across three different databases (Pubmed, European Heart Journal, Science Direct) between 2017–2022 in order to reach relatively more recent developments in the field. Our review was structured in order to clearly differentiate publications according to the disease they aim to diagnose (coronary artery disease, electrophysiological and structural heart diseases); (3) Results: Each study had different levels of success, where declared sensitivity, specificity, precision, accuracy, area under curve and F1 scores were reported for every article reviewed; (4) Conclusions: the number and quality of AI-assisted cardiac disease diagnosis publications will continue to increase through each year. We believe AI-based diagnosis should only be viewed as an additional tool assisting doctors’ own judgement, where the end goal is to provide better quality of healthcare and to make getting medical help more affordable and more accessible, for everyone, everywhere.

show abstract

Section: Resultsmentioning

confidence: 99%

Diagnostic AI and Cardiac Diseases

Ozsahin

Ozgocmen²,

Balcioglu³

et al. 2022

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Recent reports suggest that PH and PAH fingerprint may be detected by AI in QRST complexes long before it is detectable by resting RHC. 41,42 Spectacular visualization of flow vortices in central pulmonary arteries offered by 4D MR may indicate an early increase of pulmonary input impedance. 43,44 Quantitative analysis of CT, now possible with digital imaging methods, eliminates human errors due to subjective visual assessment.…”

Section: Final Comments and Future Perspectivesmentioning

confidence: 99%

The Diagnostic Approach to Pulmonary Hypertension

Torbicki¹,

Kurzyna²

2023

Semin Respir Crit Care Med

View full text Add to dashboard Cite

The clinical presentation of pulmonary hypertension (PH) is nonspecific, resulting in significant delays in its detection. In the majority of cases, PH is a marker of the severity of other cardiopulmonary diseases. Differential diagnosis aimed at the early identification of patients with pulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) who do require specific and complex therapies is as important as PH detection itself. Despite all efforts aimed at the noninvasive assessment of pulmonary arterial pressure, the formal confirmation of PH still requires catheterization of the right heart and pulmonary artery. The current document will give an overview of strategies aimed at the early diagnosis of PAH and CTEPH, while avoiding their overdiagnosis. It is not intended to be a replica of the recently published European Society of Cardiology (ESC) and European Respiratory Society (ERS) Guidelines on Diagnosis and Treatment of Pulmonary Hypertension, freely available at the Web sites of both societies. While promoting guidelines' recommendations, including those on new definitions of PH, we will try to bring them closer to everyday clinical practice, benefiting from our personal experience in managing patients with suspected PH.

show abstract

“…The standard 12-lead (S12) is still the gold standard for diagnosis, so a blend of the diagnostic specificity of the multi-lead STM and the sensitivity of long recording durations of the LTM is desired. Notably, the putatively best-performing Artificial Intelligence-based methods for diagnostics based on ECG require S12 as the input to achieve high performance [ 16 , 17 , 18 , 19 , 20 , 21 ].…”

Section: Introductionmentioning

confidence: 99%

Personalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6

Kumar

Ramasamy

Kallur

et al. 2023

Sensors

View full text Add to dashboard Cite

Background and Objective: The prevalence of chronic cardiovascular diseases (CVDs) has risen globally, nearly doubling from 1990 to 2019. ECG is a simple, non-invasive measurement that can help identify CVDs at an early and treatable stage. A multi-lead ECG, up to 15 leads in a wearable form factor, is desirable. We seek to derive multiple ECG leads from a select subset of leads so that the number of electrodes can be reduced in line with a patient-friendly wearable device. We further compare personalized derivations to generalized derivations. Methods: Long-Short Term Memory (LSTM) networks using Lead II, V2, and V6 as input are trained to obtain generalized models using Bayesian Optimization for hyperparameter tuning for all patients and personalized models for each patient by applying transfer learning to the generalized models. We compare quantitatively using error metrics Root Mean Square Error (RMSE), R2, and Pearson correlation (ρ). We compare qualitatively by matching ECG interpretations of board-certified cardiologists. Results: ECG interpretations from personalized models, when corrected for an intra-observer variance, were identical to the original ECGs, whereas generalized models led to errors. Mean performance values for generalized and personalized models were (RMSE-74.31 µV, R2-72.05, ρ-0.88) and (RMSE-26.27 µV, R2-96.38, ρ-0.98), respectively. Conclusions: Diagnostic accuracy based on derived ECG is the most critical validation of ECG derivation methods. Personalized transformation should be sought to derive ECGs. Performing a personalized calibration step to wearable ECG systems and LSTM networks could yield ambulatory 15-lead ECGs with accuracy comparable to clinical ECGs.

show abstract

Artificial Intelligence-Enabled Electrocardiogram Improves the Diagnosis and Prediction of Mortality in Patients With Pulmonary Hypertension

Cited by 18 publications

References 32 publications

Diagnostic AI and Cardiac Diseases

Diagnostic AI and Cardiac Diseases

The Diagnostic Approach to Pulmonary Hypertension

Personalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6

Contact Info

Product

Resources

About