{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:56Z","timestamp":1785545096213,"version":"3.56.0"},"reference-count":17,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Cardio"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Hypertension is a leading cause of cardiovascular disease and premature death worldwide, and it puts a heavy burden on the healthcare system. Therefore, \n \n it is\n very important to detect and evaluate hypertension and related cardiovascular events \n to enable early prevention, detection, and management. Hypertension can be detected in a timely manner with cardiac signals, such as through an electrocardiogram (ECG) and photoplethysmogram (PPG) ,\n \n \n \n \n \n \n \n \n which can be observed via wearable sensors. Most previous studies predicted hypertension from ECG and PPG signals with extracted features that are correlated with hypertension. However, correlation is sometimes unreliable and may be affected by confounding factors\n .<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The aim of this study was to investigate the feasibility of predicting the risk of hypertension by exploring features that are causally related to hypertension via causal inference methods. Additionally, we paid special attention to and verified the reliability and effectiveness of causality compared to correlation.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We used a large public dataset from the Aurora Project\n , which was conducted by Microsoft Research. The dataset included diverse individuals who were balanced in terms of gender, age, and the condition of hypertension, with their ECG and PPG signals simultaneously acquired with wrist\n -worn wearable devices. We first extracted 205 features from the ECG and PPG signals, calculated \n 6 statistical metrics for these 205 features, and selected some valuable features out of the 205 features under each statistical metric. Then, \n 6 causal graphs of the selected features for each kind of statistical metric and hypertension were constructed with the equivalent greedy search algorithm. We further fused the \n 6 causal graphs into \n 1 causal graph and identified features that were causally related to hypertension from the causal graph\n .\n \n \n Finally, we\n \n used these features to detect hypertension via machine learning algorithms.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n We validated the proposed method on 405 subjects. \n We identified\n \n 24 causal features \n that were\n \n associated with hypertension. The causal features \n could detect hypertension with an accuracy of 89%, precision of 92\n % ,\n and recall of 82%, which outperformed detection with correlation features (accuracy of 85%, precision of 88\n % ,\n and recall of 77%).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The results indicated that the causal inference\n \u2013based approach can potentially clarify the mechanism of hypertension detection with noninvasive signals and effectively detect hypertension. It also reveal\n ed that causality can be more reliable and effective than correlation for hypertension detection and other application scenarios.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/60238","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T15:33:56Z","timestamp":1729524836000},"page":"e60238-e60238","source":"Crossref","is-referenced-by-count":1,"title":["Causal Inference for Hypertension Prediction \n With Wearable E\n lectrocardiogram and P\n hotoplethysmogram Signals: Feasibility Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8467-6062","authenticated-orcid":false,"given":"Ke","family":"Gon\ng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2776-9456","authenticated-orcid":false,"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9921-3410","authenticated-orcid":false,"given":"Xinyue","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0742-1130","authenticated-orcid":false,"given":"Zhizhong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3269-2852","authenticated-orcid":false,"given":"Xiaorong","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,1,23]]},"reference":[{"issue":"33","key":"R1","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.1093\/eurheartj\/ehy339","article-title":"ESC\/ESH Guidelines for the management of arterial hypertension: The Task Force for the management of arterial hypertension of the European Society of Cardiology (ESC) and the European Society of Hypertension (ESH)","volume":"39","author":"Williams","journal-title":"Eur Heart J"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100479","article-title":"A two-stage deep CNN architecture for the classification of low-risk and high-risk hypertension classes using multi-lead ECG signals","volume":"21","author":"Jain","journal-title":"Inform Med Unlocked"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/s41581-019-0244-2","article-title":"The global epidemiology of hypertension","volume":"16","author":"Mills","journal-title":"Nat Rev Nephrol"},{"issue":"12","key":"R4","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1097\/HJH.0000000000003480","article-title":"ESH Guidelines for the management of arterial hypertension. The Task Force for the management of arterial hypertension of the European Society of Hypertension: endorsed by the International Society of Hypertension (ISH) and the European Renal Association (ERA)","volume":"41","author":"Mancia","journal-title":"J Hypertens"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1161\/HYPERTENSIONAHA.120.14591","article-title":"Ambulatory blood pressure monitoring to diagnose and manage hypertension","volume":"77","author":"Huang","journal-title":"Hypertension"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103648","article-title":"An hybrid ECG-based deep network for the early identification of high-risk to major cardiovascular events for hypertension patients","volume":"113","author":"Paragliola","journal-title":"J Biomed Inform"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0136-7","article-title":"The use of photoplethysmography for assessing hypertension","volume":"2","author":"Elgendi","journal-title":"NPJ Digit Med"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3033004","article-title":"Predicting hypertensive patients with higher risk of developing vascular events using heart rate variability and machine learning","volume":"8","author":"Alkhodari","journal-title":"IEEE Access"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103924","article-title":"Automated detection of severity of hypertension ECG signals using an optimal bi-orthogonal wavelet filter bank","volume":"123","author":"Rajput","journal-title":"Comput Biol Med"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Pearl J \n. \nComment: Understanding Simpson\u2019s Paradox\n. \nIn\n: \nProbabilistic and Causal Inference: The Works of Judea Pearl\n. \n2022\n:\n399\n-\n412\n. [\ndoi\n: \n10.1145\/3501714.3501738\n]","DOI":"10.1145\/3501714.3501738"},{"issue":"5","key":"R11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3444944","article-title":"A survey on causal inference","volume":"15","author":"Yao","journal-title":"ACM Trans Knowl Discov Data"},{"issue":"7","key":"R12","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1109\/JBHI.2022.3153259","article-title":"A comparison of wearable tonometry, photoplethysmography, and electrocardiography for cuffless measurement of blood pressure in an ambulatory setting","volume":"26","author":"Mieloszyk","journal-title":"IEEE J Biomed Health Inform"},{"key":"R13","unstructured":"Ding X Yan BP Zhang YT et al\n. \nFeature exploration for knowledge-guided and data-driven approach based cuffless blood pressure measurement\n. \narXiv\n. \nPreprint posted online on\n\nAug\n\n27\n, \n2019\n. \nURL\n: \nhttps:\/\/arxiv.org\/abs\/1908.10245\n [\nAccessed\n\n03-12-2024\n\n\n\n\n]"},{"issue":"Nov","key":"R14","doi-asserted-by":"publisher","first-page":"507554","DOI":"10.1162\/153244303321897717","article-title":"Optimal structure identification with greedy search","volume":"3","author":"Chickering","journal-title":"J Mach Learn Res"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220104","article-title":"Generalized score functions for causal discovery","volume":"2018","author":"Huang","journal-title":"KDD"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Gong K Chen Y Ding X \n. \nCausal inference for hypertension prediction\n. \nPresented at\n: \n2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)\n; \n\nJul\n24-27,2023\n\n; \nSydney, Australia\n. \n2023\n.[\ndoi\n: \n10.1109\/EMBC40787.2023.10341021\n]","DOI":"10.1109\/EMBC40787.2023.10341021"},{"key":"R17","unstructured":"Aurora\n. \nMicrosoft\n. \nURL\n: \nhttps:\/\/www.microsoft.com\/en-us\/research\/project\/aurora\/\n [\nAccessed\n\n07-01-2025\n\n\n\n\n]"}],"container-title":["JMIR Cardio"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cardio.jmir.org\/2025\/1\/e60238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:31:58Z","timestamp":1785537118000},"score":1,"resource":{"primary":{"URL":"https:\/\/cardio.jmir.org\/2025\/1\/e60238"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,23]]},"references-count":17,"URL":"https:\/\/doi.org\/10.2196\/60238","relation":{},"ISSN":["2561-1011"],"issn-type":[{"value":"2561-1011","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,23]]},"article-number":"v9i33e60238"}}