{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:15:31Z","timestamp":1774556131883,"version":"3.50.1"},"reference-count":19,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"11","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["Hypertension"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>Artificial intelligence (AI) applications in hypertension diagnosis and management are described as promising despite limited evidence of safety and efficacy. This perspective examines the substantial risks of premature AI implementation in hypertension care. We reviewed the current evidence base for AI approaches in hypertension, analyzed data quality issues in electronic health records, examined regulatory frameworks, and considered the readiness of health care systems and stakeholders. AI approaches for hypertension lack demonstrated efficacy and safety from randomized clinical trials. Training data from electronic health records suffer from poor quality control, with blood pressure measurements differing from true resting values. Clinicians routinely disregard recorded measurements, obtaining supplemental data inaccessible to algorithms. The Microsoft Aurora-Blood Pressure study, the most comprehensive evaluation of cuffless blood pressure technology, failed to meet accuracy standards except in highly constrained circumstances. Current regulatory frameworks struggle with AI\u2019s evolving nature, and informed consent becomes meaningless when clinicians cannot explain algorithmic decision-making. Accountability for AI-generated errors remains unclear, creating new patient safety risks. Infrastructure barriers prevent implementation in low-resource settings where AI could theoretically address personnel shortages. While AI may eventually transform hypertension care, current evidence does not support widespread adoption. The substantial risks\u2014including poor data quality, regulatory gaps, accountability concerns, and potential skill atrophy among clinicians\u2014outweigh unproven benefits. We recommend moving slowly and requiring rigorous clinical trial evidence before implementing AI systems in hypertension diagnosis and management.<\/jats:p>","DOI":"10.1161\/hypertensionaha.125.23626","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T09:00:23Z","timestamp":1758704423000},"page":"1789-1793","update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Controversy in Hypertension: Con-side of the argument using AI for HTN diagnosis and management"],"prefix":"10.1161","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7951-5458","authenticated-orcid":true,"given":"Isaac","family":"Sekitoleko","sequence":"first","affiliation":[{"name":"Medical Research Council\/Uganda Virus Research Institute and London School of Hygiene and Tropical Medicine Uganda Research Unit, Entebbe (I.S.)."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0509-3520","authenticated-orcid":true,"given":"James Brian","family":"Byrd","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Medicine, Department of Internal Medicine, University of Michigan Medical School, Ann Arbor (J.B.B.)."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","reference":[{"key":"e_1_3_3_2_2","unstructured":"Kuka V. The story of AI winters and what it teaches us today (history of LLMs bonus). 2023. Accessed June 21 2025. https:\/\/www.turingpost.com\/p\/aiwinters"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(22)02034-7"},{"key":"e_1_3_3_4_2","unstructured":"Tekturna (aliskiren) tablets [prescribing information]. East Hanover NJ: Novartis Pharmaceuticals Corporation; 2012."},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjcard.2020.05.011"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.0592"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1161\/HYPERTENSIONAHA.120.16164"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1097\/HJH.0000000000001197"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.17175"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1093\/ajh\/hpab095"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1161\/HYPERTENSIONAHA.122.20410"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1161\/HYPERTENSIONAHA.117.10237"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3153259"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMx210003"},{"key":"e_1_3_3_15_2","unstructured":"US Food and Drug Administration. Predetermined change control plans for medical devices: draft guidance for industry and FDA staff. Silver Spring MD:FDA; 2024."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1511939"},{"key":"e_1_3_3_17_2","unstructured":"Quora. How well does Apple's directly responsible individual (DRI) model work in practice? Forbes. 2012. Accessed June 24 2025. https:\/\/www.forbes.com\/sites\/quora\/2012\/10\/02\/how-well-does-apples-directly-responsible-individual-dri-model-work-in-practice\/#4d83402d194c"},{"key":"e_1_3_3_18_2","unstructured":"GitLab. Directly Responsible Individuals (DRI). In: The GitLab Handbook [Internet]. GitLab Inc.; 2025. Accessed June 21 2025. https:\/\/handbook.gitlab.com\/handbook\/people-group\/directly-responsible-individuals\/"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-119"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0138991"}],"container-title":["Hypertension"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/HYPERTENSIONAHA.125.23626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T18:01:10Z","timestamp":1760551270000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/HYPERTENSIONAHA.125.23626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":19,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1161\/HYPERTENSIONAHA.125.23626"],"URL":"https:\/\/doi.org\/10.1161\/hypertensionaha.125.23626","relation":{},"ISSN":["0194-911X","1524-4563"],"issn-type":[{"value":"0194-911X","type":"print"},{"value":"1524-4563","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]},"assertion":[{"value":"2025-09-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}