Estimating Blood Pressure from the Electrocardiogram: Findings of a Large-Scale Negative Results Study

ObjectiveElectrocardiography and blood pressure (BP) measurement are two widely used tools for diagnosis and monitoring cardiovascular diseases. While the electrocardiogram (ECG) and BP have been considered complementary modalities, there are also systematic relationships between them. Therefore, advancements in portable and wearable ECG devices, along with promising results in cuff-less BP measurement using a combination of ECG and other bio-signals have led researchers to hypothesize the possibility of estimating BP using only ECG. However, the literature is divided on this topic: some studies support this hypothesis, while others reject it. ApproachIn this study, machine-learning (ML) models were developed to explore this hypothesis by estimating BP from 30-second ECGs using an extensive dataset from AliveCor Inc., which includes 124,427 records from 7,412 subjects. The ECG and BP recordings were asynchronous with variable counts and time lags. Therefore, a 3.5-minute time window before and after each ECG recording was used to calculate the mean BP measurement. Main ResultsSex-aware ML models were trained using a comprehensive feature vector comprising 280 features: 128 explainable ECG features developed by the research team and 150 ECG features extracted by the Black Swan team, one of the top-performing teams in the PhysioNet Challenge 2017. Additionally, the average time gap between each ECG and the corresponding BP measurement, along with the subjects age, were included as two supplementary features. SignificanceOur best ML models achieved a mean absolute error (MAE) of 12.59 mmHg for systolic blood pressure (SBP) and 7.43 mmHg for diastolic blood pressure (DBP), with correlation coefficients of 0.35 and 0.38 between the predicted and actual values, respectively. Therefore, the results indicate no significant relationship between BP and ECG. In conclusion, ML models cannot correctly estimate BP values from ECGs, rejecting the proposed hypothesis.