Key result
Artificial neural network models incorporating a pulse wave velocity index, clinical factors, and carotid plaque achieved a diagnostic accuracy of 0.63 to 0.93 for predicting coronary heart disease.
Why the study?
Coronary heart disease is not entirely predicted by classic risk factors, prompting the development of novel predictive methods.
Does an artificial neural networks-based diagnostic model including aortic pulse wave velocity index accurately predict coronary heart disease risk?
Population
437 patients (99 CHD and 338 non-CHD patients)
Comparison
Patients with CHD vs non-CHD patients
Design
Diagnostic model development study
Authors
Loading...
May support non-invasive CHD risk prediction via ANNs with PWV; hypothesis-generating and requires prospective validation before clinical use.
Observational (n=437)
Does an artificial neural networks-based diagnostic model including aortic pulse wave velocity index accurately predict coronary heart disease risk?
Effect estimate: Accuracy 0.63-0.93
An artificial neural network model incorporating clinical factors, carotid plaque, and aortic pulse wave velocity index can accurately predict coronary heart disease risk non-invasively.
Vallée et al. (2019) conducted an observational in Coronary heart disease (n=437). Artificial neural networks (ANNs) diagnostic model including PWV index was evaluated on Accuracy of CHD risk prediction (Accuracy 0.63-0.93). Artificial neural network models incorporating a pulse wave velocity index, clinical factors, and carotid plaque achieved a diagnostic accuracy of 0.63 to 0.93 for predicting coronary heart disease.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: