Key result
Dual-stage PPG machine learning cuts systolic BP estimation error by ~64% versus existing methods.
Why the study?
Hypertension, an associated factor of cardiovascular diseases, requires continuous monitoring to track rapid blood pressure changes.
Does a dual-stage blood pressure estimation approach using Photoplethysmogram and machine learning improve BP estimation accuracy compared to existing methods in medical records from the MIMIC-III database?
Does a dual-stage blood pressure estimation approach using Photoplethysmogram and machine learning improve BP estimation accuracy compared to existing methods in medical records from the MIMIC-III database?
Effect estimate: Relative improvement in MAE and RMSE by 64.4% and 36.37% for SBP and 40.1% and 22.9% for DBP
A novel dual-stage machine learning approach using photoplethysmogram data significantly improves the accuracy of continuous cuffless blood pressure estimation.
May improve cuffless BP estimation; hypothesis-generating and requires prospective validation before clinical use.
Hypertension, being one of the associated factors of cardiovascular diseases needs to be monitored on the continuous manner to track the rapid BP changes. The paper proposes a dual-stage blood pressure estimation approach using the suitable features from Photoplethysmogram and machine learning models. The method initially classifies the given data among 4 classes given by British Hypertension Society (BHS). Further, the classified data is predicted from one of the four models. The 105 medical records consisting of clinical and digitalized signal data of 125 Hz are taken from the MIMIC-III database for the process. The dual-stage approach for the classification and estimation of BP outperforms the existing method by relative improvement in the MAE and RMSE by 64.4% and 36.37 % for systolic BP and 40.1% and 22.9% for diastolic BP respectively.
No takes yet. Share an insight, caveat, or question.
Sree Niranjanaa Bose S (2020) studied Hypertension (n=105). Dual-stage blood pressure estimation approach using PPG and machine learning models vs. Existing method was evaluated on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for systolic and diastolic BP (Relative improvement in MAE and RMSE by 64.4% and 36.37% for SBP and 40.1% and 22.9% for DBP). A dual-stage learning approach using PPG and machine learning models improved MAE and RMSE for systolic BP by 64.4% and 36.37%, and for diastolic BP by 40.1% and 22.9%, compared to existing methods.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: