{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:37:28Z","timestamp":1791567448916,"version":"4.3.4"},"reference-count":45,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Science Foundation (NSF)","award":["1648451"],"award-info":[{"award-number":["1648451"]}]},{"name":"the National Science Foundation (NSF)","award":["2412500"],"award-info":[{"award-number":["2412500"]}]},{"name":"the Precise Advanced Technologies and Health Systems for Underserved Populations Engineering Research Center (PATHS-UP ERC)","award":["1648451"],"award-info":[{"award-number":["1648451"]}]},{"name":"the Precise Advanced Technologies and Health Systems for Underserved Populations Engineering Research Center (PATHS-UP ERC)","award":["2412500"],"award-info":[{"award-number":["2412500"]}]},{"name":"AccelNet-Implementation: Broadening Carbon Ring","award":["1648451"],"award-info":[{"award-number":["1648451"]}]},{"name":"AccelNet-Implementation: Broadening Carbon Ring","award":["2412500"],"award-info":[{"award-number":["2412500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Continuous blood pressure (BP) monitoring provides valuable insight into the body\u2019s dynamic cardiovascular regulation across various physiological states such as physical activity, emotional stress, postural changes, and sleep. Continuous BP monitoring captures different variations in systolic and diastolic pressures, reflecting autonomic nervous system activity, vascular compliance, and circadian rhythms. This enables early identification of abnormal BP trends and allows for timely diagnosis and interventions to reduce the risk of cardiovascular diseases (CVDs) such as hypertension, stroke, heart failure, and chronic kidney disease as well as chronic stress or anxiety disorders. To facilitate continuous BP monitoring, we propose an AI-powered estimation framework. The proposed framework first uses an expert-driven feature engineering approach that systematically extracts physiological features from photoplethysmogram (PPG)-based arterial pulse waveforms (APWs). Extracted features include pulse rate, ascending\/descending times, pulse width, slopes, intensity variations, and waveform areas. These features are fused with demographic data (age, gender, height, weight, BMI) to enhance model robustness and accuracy across diverse populations. The framework utilizes a Tab-Transformer to learn rich feature embeddings, which are then processed through an ensemble machine learning framework consisting of CatBoost, XGBoost, and LightGBM. Evaluated on a dataset of 1000 subjects, the model achieves Mean Absolute Errors (MAE) of 3.87 mmHg (SBP) and 2.50 mmHg (DBP), meeting British Hypertension Society (BHS) Grade A and Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed architecture advances non-invasive, AI-driven solutions for dynamic cardiovascular health monitoring.<\/jats:p>","DOI":"10.3390\/s25154574","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T10:28:09Z","timestamp":1753352889000},"page":"4574","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["An Ensemble-Based AI Approach for Continuous Blood Pressure Estimation in Health Monitoring Applications"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5788-9192","authenticated-orcid":false,"given":"Rafita","family":"Haque","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, Florida International University, Miami, FL 33174, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2574-7314","authenticated-orcid":false,"given":"Chunlei","family":"Wang","sequence":"additional","affiliation":[{"name":"Mechanical and Aerospace Engineering Department, University of Miami, Miami, FL 33136, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6136-9811","authenticated-orcid":false,"given":"Nezih","family":"Pala","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, Florida International University, Miami, FL 33174, USA"},{"name":"Terabrum LLC, Fort Lauderdale, FL 33331, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"ref_1","unstructured":"(2025, July 19). World Health Organization; 2018. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovasculardiseases-(cvds)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1161\/CIRCRESAHA.116.303755","article-title":"Clinical value of ambulatory blood pressure: Evidence and limits","volume":"116","author":"Mancia","year":"2015","journal-title":"Circ. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"482","DOI":"10.3389\/fendo.2019.00482","article-title":"Hypertension in thyroid disorders","volume":"10","author":"Berta","year":"2019","journal-title":"Front. Endocrinol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/S0301-2115(00)00383-3","article-title":"Management and monitoring of severe preeclampsia","volume":"96","author":"Bolte","year":"2001","journal-title":"Eur. J. Obstet. Gynecol. Reprod. Biol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1080\/07420528.2016.1181078","article-title":"Sleep-time ambulatory blood pressure as a prognostic marker of vascular and other risks and therapeutic target for prevention by hypertension chronotherapy: Rationale and design of the Hygia Project","volume":"33","author":"Hermida","year":"2016","journal-title":"Chronobiol. Int."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/s12938-022-00985-w","article-title":"Association between mental illness and blood pressure variability: A systematic review","volume":"21","author":"Shahimi","year":"2022","journal-title":"Biomed. Eng. Online"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s12559-023-10200-0","article-title":"State-of-the-art of stress prediction from heart rate variability using artificial intelligence","volume":"16","author":"Haque","year":"2024","journal-title":"Cogn. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Hsu, Y.C., Li, Y.H., Chang, C.C., and Harfiya, L.N. (2020). Generalized deep neural network model for cuffless blood pressure estimation with photoplethysmogram signal only. Sensors, 20.","DOI":"10.3390\/s20195668"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1136\/bmj.322.7285.531","article-title":"Blood pressure measuring devices: Recommendations of the European Society of Hypertension","volume":"322","author":"Waeber","year":"2001","journal-title":"BMJ"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1097\/00004872-199007000-00004","article-title":"The British Hypertension Society protocol for the evaluation of automated and semi-automated blood pressure measuring devices with special reference to ambulatory systems","volume":"8","author":"Petrie","year":"1990","journal-title":"J. Hypertens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Li, Y.H., Harfiya, L.N., Purwandari, K., and Lin, Y.D. (2020). Real-time cuffless continuous blood pressure estimation using deep learning model. Sensors, 20.","DOI":"10.3390\/s20195606"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kachuee, M., Kiani, M.M., Mohammadzade, H., and Shabany, M. (2015, January 24\u201327). Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time. Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, Portugal.","DOI":"10.1109\/ISCAS.2015.7168806"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1109\/TBME.2016.2580904","article-title":"Cuffless blood pressure estimation algorithms for continuous health-care monitoring","volume":"64","author":"Kachuee","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"100085","DOI":"10.1016\/j.nbas.2023.100085","article-title":"Short-term blood pressure variability is inversely related to regional amplitude of low frequency fluctuations in older and younger adults","volume":"4","author":"Sible","year":"2023","journal-title":"Aging Brain"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"779","DOI":"10.3389\/fphys.2020.00779","article-title":"Heart rate variability (HRV) and pulse rate variability (PRV) for the assessment of autonomic responses","volume":"11","author":"Budidha","year":"2020","journal-title":"Front. Physiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13534-022-00247-7","article-title":"Exploiting moving slope features of PPG derivatives for estimation of mean arterial pressure","volume":"13","author":"Gupta","year":"2023","journal-title":"Biomed. Eng. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Hossain Chowdhury, M., Nazmul Islam Shuzan, M., Chowdhury, M.E., Mahbub, Z.B., Monir Uddin, M., Khandakar, A., and Ibne Reaz, M.B. (2020). Estimating Blood Pressure from Photoplethysmogram Signal and Demographic Features using Machine Learning Techniques. arXiv.","DOI":"10.3390\/s20113127"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s12938-025-01365-w","article-title":"A finger on the pulse of cardiovascular health: Estimating blood pressure with smartphone photoplethysmography-based pulse waveform analysis","volume":"24","author":"Liu","year":"2025","journal-title":"BioMedical Eng. OnLine"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1090854","DOI":"10.3389\/fdgth.2022.1090854","article-title":"PulseDB: A large, cleaned dataset based on MIMIC-III and VitalDB for benchmarking cuff-less blood pressure estimation methods","volume":"4","author":"Wang","year":"2023","journal-title":"Front. Digit. Health"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lee, J., Yang, S., Lee, S., and Kim, H.C. (2019). Analysis of pulse arrival time as an indicator of blood pressure in a large surgical biosignal database: Recommendations for developing ubiquitous blood pressure monitoring methods. J. Clin. Med., 8.","DOI":"10.3390\/jcm8111773"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s13040-023-00342-0","article-title":"STAR_outliers: A python package that separates univariate outliers from non-normal distributions","volume":"16","author":"Gregg","year":"2023","journal-title":"BioData Min."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Amri, T.C., Sarno, R., Abdillah, R., Haq, F.A., Septiyanto, A.F., and Sunaryono, D. (2023, January 20\u201323). Filter Validation for Detecting Outliers of Photoplethysmograph Data. Proceedings of the 2023 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Bali, Indonesia.","DOI":"10.1109\/ICAIIC57133.2023.10067110"},{"key":"ref_23","unstructured":"Walker, M. (2020). Python Data Cleaning Cookbook: Modern Techniques and Python Tools to Detect and Remove Dirty Data and Extract Key Insights, Packt Publishing Ltd."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"044003","DOI":"10.1088\/1361-6579\/ab7d78","article-title":"Investigating the physiological mechanisms of the photoplethysmogram features for blood pressure estimation","volume":"41","author":"Lin","year":"2020","journal-title":"Physiol. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2096","DOI":"10.1109\/JBHI.2021.3128229","article-title":"Continuous PPG-based blood pressure monitoring using multi-linear regression","volume":"26","author":"Haddad","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","unstructured":"Huang, X., Khetan, A., Cvitkovic, M., and Karnin, Z. (2020). Tabtransformer: Tabular data modeling using contextual embeddings. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"28","DOI":"10.47611\/jsrhs.v12i1.3935","article-title":"Analyzing the performance of TabTransformer in brain stroke prediction","volume":"12","author":"Xia","year":"2023","journal-title":"J. Stud. Res"},{"key":"ref_28","unstructured":"Cholakov, R., and Kolev, T. (2022). The GatedTabTransformer. An enhanced deep learning architecture for tabular modeling. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"32423","DOI":"10.1109\/ACCESS.2019.2902217","article-title":"Health data driven on continuous blood pressure prediction based on gradient boosting decision tree algorithm","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3882","DOI":"10.1109\/JBHI.2024.3395445","article-title":"HGCTNet: Handcrafted feature-guided CNN and transformer network for wearable cuffless blood pressure measurement","volume":"28","author":"Liu","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"511","DOI":"10.3390\/electronics13030511","article-title":"Single-cycle pulse signal recognition based on one-dimensional deep convolutional neural network","volume":"13","author":"Chen","year":"2024","journal-title":"Electronics"},{"key":"ref_32","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume":"31","author":"Prokhorenkova","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_34","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017, January 4\u20139). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Mousavi, S.S., Hemmati, M., Charmi, M., Moghadam, M., Firouzmand, M., and Ghorbani, Y. (2018, January 25\u201326). Cuff-Less blood pressure estimation using only the ecg signal in frequency domain. Proceedings of the 2018 8th International Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, Iran.","DOI":"10.1109\/ICCKE.2018.8566583"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhang, Y., and Feng, Z. (2017, January 24\u201326). A SVM method for continuous blood pressure estimation from a PPG signal. Proceedings of the 9th International Conference on Machine Learning and Computing, Singapore.","DOI":"10.1145\/3055635.3056634"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"102328","DOI":"10.1016\/j.bspc.2020.102328","article-title":"A blood pressure prediction method based on imaging photoplethysmography in combination with machine learning","volume":"64","author":"Rong","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Figini, V., Galici, S., Russo, D., Centonze, I., Visintin, M., and Pagana, G. (2022). Improving cuff-less continuous blood pressure estimation with linear regression analysis. Electronics, 11.","DOI":"10.3390\/electronics11091442"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Fati, S.M., Muneer, A., Akbar, N.A., and Taib, S.M. (2021). A continuous cuffless blood pressure estimation using tree-based pipeline optimization tool. Symmetry, 13.","DOI":"10.3390\/sym13040686"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Slapni\u010dar, G., Mlakar, N., and Lu\u0161trek, M. (2019). Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network. Sensors, 19.","DOI":"10.3390\/s19153420"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1038\/s41597-024-04041-1","article-title":"MIMIC-BP: A curated dataset for blood pressure estimation","volume":"11","author":"Sanches","year":"2024","journal-title":"Sci. Data"},{"key":"ref_43","unstructured":"Ibtehaz, N., Mahmud, S., Chowdhury, M.E., Khandakar, A., Ayari, M.A., Tahir, A., and Rahman, M.S. (2020). Ppg2abp: Translating photoplethysmogram (ppg) signals to arterial blood pressure (abp) waveforms using fully convolutional neural networks. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"102984","DOI":"10.1016\/j.bspc.2021.102984","article-title":"Cuffless blood pressure estimation from PPG signals and its derivatives using deep learning models","volume":"70","author":"Kyriacou","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3697","DOI":"10.1109\/JBHI.2022.3172514","article-title":"Deepcnap: A deep learning approach for continuous noninvasive arterial blood pressure monitoring using photoplethysmography","volume":"26","author":"Kim","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/15\/4574\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:15:12Z","timestamp":1760033712000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/15\/4574"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":45,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["s25154574"],"URL":"https:\/\/doi.org\/10.3390\/s25154574","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]}}}