Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques
Hypertension is a potentially unsafe health ailment, which can be indicated directly from the blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. T...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/11/3127 |
| _version_ | 1797566420607827968 |
|---|---|
| author | Moajjem Hossain Chowdhury Md Nazmul Islam Shuzan Muhammad E.H. Chowdhury Zaid B. Mahbub M. Monir Uddin Amith Khandakar Mamun Bin Ibne Reaz |
| author_facet | Moajjem Hossain Chowdhury Md Nazmul Islam Shuzan Muhammad E.H. Chowdhury Zaid B. Mahbub M. Monir Uddin Amith Khandakar Mamun Bin Ibne Reaz |
| author_sort | Moajjem Hossain Chowdhury |
| collection | DOAJ |
| description | Hypertension is a potentially unsafe health ailment, which can be indicated directly from the blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. To address this need, a cuff-less, continuous, and noninvasive BP measurement system is proposed using the photoplethysmograph (PPG) signal and demographic features using machine learning (ML) algorithms. PPG signals were acquired from 219 subjects, which undergo preprocessing and feature extraction steps. Time, frequency, and time-frequency domain features were extracted from the PPG and their derivative signals. Feature selection techniques were used to reduce the computational complexity and to decrease the chance of over-fitting the ML algorithms. The features were then used to train and evaluate ML algorithms. The best regression models were selected for systolic BP (SBP) and diastolic BP (DBP) estimation individually. Gaussian process regression (GPR) along with the ReliefF feature selection algorithm outperforms other algorithms in estimating SBP and DBP with a root mean square error (RMSE) of 6.74 and 3.59, respectively. This ML model can be implemented in hardware systems to continuously monitor BP and avoid any critical health conditions due to sudden changes. |
| first_indexed | 2024-03-10T19:26:34Z |
| format | Article |
| id | doaj.art-3c790ee8c76c415b8bf1f5dd44f26cab |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:26:34Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3c790ee8c76c415b8bf1f5dd44f26cab2023-11-20T02:29:58ZengMDPI AGSensors1424-82202020-06-012011312710.3390/s20113127Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning TechniquesMoajjem Hossain Chowdhury0Md Nazmul Islam Shuzan1Muhammad E.H. Chowdhury2Zaid B. Mahbub3M. Monir Uddin4Amith Khandakar5Mamun Bin Ibne Reaz6Department of Electrical and Computer Engineering, North South University, Dhaka 1229, BangladeshDepartment of Electrical and Computer Engineering, North South University, Dhaka 1229, BangladeshDepartment of Electrical Engineering, Qatar University, Doha 2713, QatarDepartment of Mathematics and Physics, North South University, Dhaka 1229, BangladeshDepartment of Mathematics and Physics, North South University, Dhaka 1229, BangladeshDepartment of Electrical Engineering, Qatar University, Doha 2713, QatarDepartment of Electrical, Electronic & Systems Engineering, Universiti Kebangsaan Malaysia, Bangi Selangor 43600, MalaysiaHypertension is a potentially unsafe health ailment, which can be indicated directly from the blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. To address this need, a cuff-less, continuous, and noninvasive BP measurement system is proposed using the photoplethysmograph (PPG) signal and demographic features using machine learning (ML) algorithms. PPG signals were acquired from 219 subjects, which undergo preprocessing and feature extraction steps. Time, frequency, and time-frequency domain features were extracted from the PPG and their derivative signals. Feature selection techniques were used to reduce the computational complexity and to decrease the chance of over-fitting the ML algorithms. The features were then used to train and evaluate ML algorithms. The best regression models were selected for systolic BP (SBP) and diastolic BP (DBP) estimation individually. Gaussian process regression (GPR) along with the ReliefF feature selection algorithm outperforms other algorithms in estimating SBP and DBP with a root mean square error (RMSE) of 6.74 and 3.59, respectively. This ML model can be implemented in hardware systems to continuously monitor BP and avoid any critical health conditions due to sudden changes.https://www.mdpi.com/1424-8220/20/11/3127blood pressurephotoplethysmographfeature selection algorithmmachine learning |
| spellingShingle | Moajjem Hossain Chowdhury Md Nazmul Islam Shuzan Muhammad E.H. Chowdhury Zaid B. Mahbub M. Monir Uddin Amith Khandakar Mamun Bin Ibne Reaz Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques Sensors blood pressure photoplethysmograph feature selection algorithm machine learning |
| title | Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques |
| title_full | Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques |
| title_fullStr | Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques |
| title_full_unstemmed | Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques |
| title_short | Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques |
| title_sort | estimating blood pressure from the photoplethysmogram signal and demographic features using machine learning techniques |
| topic | blood pressure photoplethysmograph feature selection algorithm machine learning |
| url | https://www.mdpi.com/1424-8220/20/11/3127 |
| work_keys_str_mv | AT moajjemhossainchowdhury estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT mdnazmulislamshuzan estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT muhammadehchowdhury estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT zaidbmahbub estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT mmoniruddin estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT amithkhandakar estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques AT mamunbinibnereaz estimatingbloodpressurefromthephotoplethysmogramsignalanddemographicfeaturesusingmachinelearningtechniques |