The Relevance of Calibration in Machine Learning-Based Hypertension Risk Assessment Combining Photoplethysmography and Electrocardiography

被引:7
|
作者
Cano, Jesus [1 ]
Facila, Lorenzo [2 ]
Gracia-Baena, Juan M. [3 ]
Zangroniz, Roberto [4 ]
Alcaraz, Raul [4 ]
Rieta, Jose J. [1 ]
机构
[1] Univ Politecn Valencia, Elect Engn Dept, BioMITorg, Valencia 46022, Spain
[2] Gen Univ Hosp Consortium Valencia, Cardiol Dept, Valencia 46014, Spain
[3] Hosp Clin Univ Valencia, Cardiovasc Surg Dept, Valencia 46010, Spain
[4] Univ Castilla La Mancha, Res Grp Elect Biomed & Telecommun Engn, Cuenca 16071, Spain
来源
BIOSENSORS-BASEL | 2022年 / 12卷 / 05期
关键词
high blood pressure; hypertension; photoplethysmography; electrocardiography; calibration; classification models; machine learning; BLOOD-PRESSURE ESTIMATION; CLASSIFICATION; STIFFNESS; CUFFLESS;
D O I
10.3390/bios12050289
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The detection of hypertension (HT) is of great importance for the early diagnosis of cardiovascular diseases (CVDs), as subjects with high blood pressure (BP) are asymptomatic until advanced stages of the disease. The present study proposes a classification model to discriminate between normotensive (NTS) and hypertensive (HTS) subjects employing electrocardiographic (ECG) and photoplethysmographic (PPG) recordings as an alternative to traditional cuff-based methods. A total of 913 ECG, PPG and BP recordings from 69 subjects were analyzed. Then, signal preprocessing, fiducial points extraction and feature selection were performed, providing 17 discriminatory features, such as pulse arrival and transit times, that fed machine-learning-based classifiers. The main innovation proposed in this research uncovers the relevance of previous calibration to obtain accurate HT risk assessment. This aspect has been assessed using both close and distant time test measurements with respect to calibration. The k-nearest neighbors-classifier provided the best outcomes with an accuracy for new subjects before calibration of 51.48%. The inclusion of just one calibration measurement into the model improved classification accuracy by 30%, reaching gradually more than 96% with more than six calibration measurements. Accuracy decreased with distance to calibration, but remained outstanding even days after calibration. Thus, the use of PPG and ECG recordings combined with previous subject calibration can significantly improve discrimination between NTS and HTS individuals. This strategy could be implemented in wearable devices for HT risk assessment as well as to prevent CVDs.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Photoplethysmography and Machine Learning for the Hypertension Risk Stratification
    Sannino, Giovanna
    De Falco, Ivanoe
    De Pietro, Giuseppe
    [J]. 2020 IEEE GLOBECOM WORKSHOPS (GC WKSHPS), 2020,
  • [2] Importance of calibration assessment in machine learning-based predictive analytics
    Staartjes, Victor E.
    Kernbach, Julius M.
    [J]. JOURNAL OF NEUROSURGERY-SPINE, 2020, 32 (06) : 985 - 986
  • [3] A Machine Learning-based Method for Cyber Risk Assessment
    Rafaiani, Giulia
    Battaglioni, Massimo
    Compagnoni, Simone
    Senigagliesi, Linda
    Chiaraluce, Franco
    Baldi, Marco
    [J]. 2023 IEEE 36TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, CBMS, 2023, : 263 - 268
  • [4] Improved Hypertension Risk Assessment with Photoplethysmographic Recordings Combining Deep Learning and Calibration
    Cano, Jesus
    Bertomeu-Gonzalez, Vicente
    Facila, Lorenzo
    Hornero, Fernando
    Alcaraz, Raul
    Rieta, Jose J.
    [J]. BIOENGINEERING-BASEL, 2023, 10 (12):
  • [5] Importance of calibration assessment in machine learning-based predictive analytics Response
    Hopkins, Benjamin S.
    Dahdaleh, Nader S.
    [J]. JOURNAL OF NEUROSURGERY-SPINE, 2020, 32 (06) : 986 - 987
  • [6] Machine Learning-Based Classification of Hypertension using CnD Features from Acceleration Photoplethysmography and Clinical Parameters
    Abdullah, Saad
    Hafid, Abdelakram
    Linden, Maria
    Folke, Mia
    Kristofeersson, Annica
    [J]. 2023 IEEE 36TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, CBMS, 2023, : 923 - 924
  • [7] A Machine Learning-Based Fall Risk Assessment Model for Inpatients
    Liu, Chia-Hui
    Hu, Ya-Han
    Lin, Yu-Hsiu
    [J]. CIN-COMPUTERS INFORMATICS NURSING, 2021, 39 (08) : 450 - 459
  • [8] Machine learning-based prediction of diabetes risk by combining exposome and electrocardiographic predictors
    Shahbazi, Zeinab
    Camacho, Marina
    Ruiz, Esmeralda
    Atehortua, Angelica
    Lekadir, Karim
    [J]. 18TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, 2023, 12567
  • [9] A machine learning approach for hypertension detection based on photoplethysmography and clinical data
    Martinez-Rios, Erick
    Montesinos, Luis
    Alfaro-Ponce, Mariel
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 145
  • [10] Machine Learning-Based Fast Seismic Risk Assessment of Building Structures
    Tang, Qi
    Dang, Ji
    Cui, Yao
    Wang, Xin
    Jia, Jinqing
    [J]. JOURNAL OF EARTHQUAKE ENGINEERING, 2022, 26 (15) : 8041 - 8062