{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T18:07:35Z","timestamp":1779386855651,"version":"3.53.1"},"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Advanced preventive strategies are needed to decrease the burden of cardiovascular disease (CVD). We aimed to develop a predictive tool to identify individuals at higher CVD risk and facilitate proactive interventions to improve clinical outcomes. This single-center retrospective study enrolled consecutive hypertensive subjects free of CVD at baseline and followed them up for a mean of 8.3 years. The primary outcome was new-onset CVD (ischemic heart disease, stroke or hospitalization due to heart failure). The 155-variable dataset was enriched by creating trend variables using statistical measures, Principal Component Analysis (PCA) and Latent Class Analysis (LCA). Then, an artificial intelligence (AI) XGBoost prediction algorithm was trained on 70% of the dataset and validated on the remaining 30%. XGBoost-based risk stratification was compared with risk stratification according to SCORE2. The 3,588 consecutive patients enrolled had a mean age of 54.2\u2009\u00b1\u200914 years, 53% were women. The incidence rate of new-onset CVD was 1.93 (95% CI: 1.78-2.09) per 100 patient-years. The XGBoost model incorporated 30 variables and achieved 86% ROC AUC, 81% sensitivity, and 78% specificity for predicting CVD. The number of antihypertensive drugs had the strongest predictive power within the model. SCORE2 classified at baseline only 32% of participants with a CV event in the follow-up as high or very-high risk, whereas the XGBoost model correctly identified 81% of them. AI-based modeling outperformed SCORE2 in predicting new-onset CVD in patients with hypertension, identifying the number of antihypertensive drugs as a key predictor and supporting the role of AI risk stratification in clinical practice to implement precision medicine.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001441","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:22:46Z","timestamp":1779384166000},"page":"e0001441","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimization of artificial intelligence models for prediction of new-onset cardiovascular disease in patients with arterial hypertension"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3669-4270","authenticated-orcid":true,"given":"Enrique","family":"Rodilla","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2803-9930","authenticated-orcid":true,"given":"Olast","family":"Arrizibita-Iriarte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Blanca","family":"Miranda-Serrano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luis-Miguel","family":"Ruilope-Urioste","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4653-7982","authenticated-orcid":true,"given":"Germ\u00e1n","family":"Sedano-Gil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9805-9523","authenticated-orcid":true,"given":"Alberto","family":"Ortiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6455-0050","authenticated-orcid":true,"given":"Jos\u00e9-Antonio","family":"Costa-Mu\u00f1oz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8009-0020","authenticated-orcid":true,"given":"Jos\u00e9","family":"Chord\u00e1-Ribelles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5504-8885","authenticated-orcid":true,"given":"Maialen","family":"Zabalza-Zudaire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2931-1326","authenticated-orcid":true,"given":"Onintza","family":"Sayar-Beristain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"pdig.0001441.ref001","unstructured":"World Health Organization. Cardiovascular diseases (CVDs). https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds). 2021."},{"issue":"1","key":"pdig.0001441.ref002","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"A Esteva","year":"2019","journal-title":"Nat Med"},{"issue":"14","key":"pdig.0001441.ref003","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1056\/NEJMoa2206916","article-title":"Global Effect of Modifiable Risk Factors on Cardiovascular Disease and Mortality","volume":"389","author":"Global Cardiovascular Risk Consortium","year":"2023","journal-title":"N Engl J Med"},{"issue":"12","key":"pdig.0001441.ref004","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1097\/HJH.0000000000003480","article-title":"2023 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":"G Mancia","year":"2023","journal-title":"J Hypertens"},{"issue":"1","key":"pdig.0001441.ref005","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"AY Hannun","year":"2019","journal-title":"Nat Med"},{"issue":"22","key":"pdig.0001441.ref006","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"12","key":"pdig.0001441.ref007","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s12170-023-00731-4","article-title":"Artificial Intelligence for Risk Assessment on Primary Prevention of Coronary Artery Disease","volume":"17","author":"S-F Chen","year":"2023","journal-title":"Curr Cardiovasc Risk Rep"},{"issue":"1","key":"pdig.0001441.ref008","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1161\/HYPERTENSIONAHA.123.21638","article-title":"Vascular age assessed from an uncalibrated, noninvasive pressure waveform by using a deep learning approach: the AI-vascularage model","volume":"81","author":"GF Mitchell","year":"2024","journal-title":"Hypertension"},{"issue":"22","key":"pdig.0001441.ref009","doi-asserted-by":"crossref","first-page":"6677","DOI":"10.3390\/jcm11226677","article-title":"Deep Learning Improves Prediction of Cardiovascular Disease-Related Mortality and Admission in Patients with Hypertension: Analysis of the Korean National Health Information Database","volume":"11","author":"S-J Lee","year":"2022","journal-title":"J Clin Med"},{"issue":"4","key":"pdig.0001441.ref010","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.acvd.2025.09.005","article-title":"Explainable machine-learning-based cardiovascular disease prediction in patients with hypertension: Algorithm comparison and SHapley Additive exPlanations (SHAP) analysis","volume":"119","author":"M Wang","year":"2026","journal-title":"Arch Cardiovasc Dis"},{"issue":"1","key":"pdig.0001441.ref011","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1186\/s12874-022-01814-3","article-title":"Personalized prediction of incident hospitalization for cardiovascular disease in patients with hypertension using machine learning","volume":"22","author":"Y Feng","year":"2022","journal-title":"BMC Med Res Methodol"},{"issue":"9","key":"pdig.0001441.ref012","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.medcli.2016.06.032","article-title":"Hipertensi\u00f3n arterial y prediabetes","volume":"147","author":"P Ombuena","year":"2016","journal-title":"Med Clin (Barc)"},{"issue":"1","key":"pdig.0001441.ref013","doi-asserted-by":"crossref","first-page":"4419","DOI":"10.1038\/s41598-025-34441-1","article-title":"XGBoost based machine learning prediction model for major adverse cardiovascular events after PCI in STEMI patients","volume":"16","author":"N Zhang","year":"2026","journal-title":"Sci Rep"},{"issue":"20","key":"pdig.0001441.ref014","doi-asserted-by":"crossref","first-page":"6061","DOI":"10.3390\/jcm11206061","article-title":"A Machine Learning Model to Predict Cardiovascular Events during Exercise Evaluation in Patients with Coronary Heart Disease","volume":"11","author":"T Shen","year":"2022","journal-title":"J Clin Med"},{"key":"pdig.0001441.ref015","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","volume-title":"XGBoost: A Scalable Tree Boosting System","author":"T Chen","year":"2016"},{"issue":"1","key":"pdig.0001441.ref016","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From Local Explanations to Global Understanding with Explainable AI for Trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"pdig.0001441.ref017","doi-asserted-by":"crossref","first-page":"103609","DOI":"10.1016\/j.gerinurse.2025.103609","article-title":"XGBoost machine learning algorithm for predicting unplanned readmission in elderly patients with coronary heart disease","volume":"66","author":"X Song","year":"2025","journal-title":"Geriatr Nurs"},{"issue":"4","key":"pdig.0001441.ref018","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.3390\/biomedinformatics4040118","article-title":"Impact of Data Pre-Processing Techniques on XGBoost Model Performance for Predicting All-Cause Readmission and Mortality Among Patients with Heart Failure","volume":"4","author":"QA Hidayaturrohman","year":"2024","journal-title":"BioMedInformatics"},{"key":"pdig.0001441.ref019","article-title":"XGBoost-based prediction of ICU mortality in sepsis-associated acute kidney injury patients using MIMIC-IV database with validation from eICU database","author":"E Chen","year":"2025","journal-title":"medRxiv"},{"issue":"1","key":"pdig.0001441.ref020","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s12911-025-02894-z","article-title":"Improving stroke risk prediction by integrating XGBoost, optimized principal component analysis, and explainable artificial intelligence","volume":"25","author":"L Mochurad","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"issue":"11","key":"pdig.0001441.ref021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0335676","article-title":"Classifying complex multimorbidity using latent class analysis and machine learning to generate insights into clustering of mental and cardiometabolic conditions","volume":"20","author":"M Mukherjee","year":"2025","journal-title":"PLoS One"},{"key":"pdig.0001441.ref022","article-title":"Identification of risk groups for and factors affecting metabolic syndrome in South Korean single-person households using latent class analysis and machine learning techniques: Secondary analysis study","author":"JS Lee","year":"2023","journal-title":"JMIR Form Res"},{"issue":"1","key":"pdig.0001441.ref023","first-page":"27","article-title":"Cardiovascular disease prediction through machine learning: A comparative study of ensemble techniques","volume":"1","year":"2026","journal-title":"Revolutionary Advances in Computing and Electronics: An International Journal"},{"key":"pdig.0001441.ref024","first-page":"158","article-title":"Comparative analysis of machine learning techniques for classifying the risk of cardiovascular diseases","volume-title":"Emerging advancements in AI and big data technologies in business and society","author":"BA Ng","year":"2024"},{"key":"pdig.0001441.ref025","doi-asserted-by":"crossref","first-page":"4","DOI":"10.2105\/AJPH.47.4_Pt_2.4","article-title":"Coronary heart disease in the Framingham study","volume":"47","author":"TR Dawber","year":"1957","journal-title":"Am J Public Health Nations Health"},{"issue":"9921","key":"pdig.0001441.ref026","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1016\/S0140-6736(13)61752-3","article-title":"The Framingham Heart Study and the Epidemiology of Cardiovascular Diseases: A Historical Perspective","volume":"383","year":"2014","journal-title":"Lancet"},{"issue":"11","key":"pdig.0001441.ref027","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1016\/S0195-668X(03)00114-3","article-title":"Estimation of ten-year risk of fatal cardiovascular disease in Europe: the SCORE project","volume":"24","author":"RM Conroy","year":"2003","journal-title":"Eur Heart J"},{"issue":"25","key":"pdig.0001441.ref028","doi-asserted-by":"crossref","first-page":"2439","DOI":"10.1093\/eurheartj\/ehab309","article-title":"SCORE2 risk prediction algorithms: new models to estimate 10-year risk of cardiovascular disease in Europe","volume":"42","author":"SCORE2 working group and ESC Cardiovascular risk collaboration","year":"2021","journal-title":"Eur Heart J"},{"issue":"25","key":"pdig.0001441.ref029","doi-asserted-by":"crossref","first-page":"2455","DOI":"10.1093\/eurheartj\/ehab312","article-title":"SCORE2-OP risk prediction algorithms: estimating incident cardiovascular event risk in older persons in four geographical risk regions","volume":"42","author":"SCORE2-OP working group and ESC Cardiovascular risk collaboration","year":"2021","journal-title":"Eur Heart J"},{"key":"pdig.0001441.ref030","doi-asserted-by":"crossref","first-page":"2544","DOI":"10.1093\/eurheartj\/ehad260","article-title":"30 SCORE2-Diabetes: 10-year cardiovascular risk estimation in type 2 diabetes in Europe","volume":"44","author":"SCORE2-Diabetes Working Group","year":"2023","journal-title":"European Heart Journal"},{"key":"pdig.0001441.ref031","unstructured":"Score2 Diabetes Calculator. https:\/\/www.mdcalc.com\/calc\/10510\/score2-diabetes"},{"issue":"9","key":"pdig.0001441.ref032","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1016\/S0735-1097(03)00187-6","article-title":"Preventing myocardial infarction in the young adult in the first place: how do the National Cholesterol Education Panel III guidelines perform?","volume":"41","author":"KO Akosah","year":"2003","journal-title":"J Am Coll Cardiol"},{"issue":"4","key":"pdig.0001441.ref033","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.medcli.2011.05.018","article-title":"S\u00edndrome metab\u00f3lico y complicaciones cardiovasculares en el paciente hipertenso","volume":"139","author":"JA Costa","year":"2012","journal-title":"Med Clin (Barc)"},{"issue":"14","key":"pdig.0001441.ref034","doi-asserted-by":"crossref","DOI":"10.1161\/CIR.0000000000001201","volume":"149","author":"AA Armoundas","year":"2024","journal-title":"Circulation"},{"issue":"6","key":"pdig.0001441.ref035","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1007\/s10278-022-00674-z","article-title":"Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study","volume":"35","author":"JT-Y Wu","year":"2022","journal-title":"J Digit Imaging"},{"issue":"12","key":"pdig.0001441.ref036","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1016\/j.hlc.2021.05.101","article-title":"Machine Learning Outperforms Existing Clinical Scoring Tools in the Prediction of Postoperative Atrial Fibrillation During Intensive Care Unit Admission After Cardiac Surgery","volume":"30","author":"R Karri","year":"2021","journal-title":"Heart Lung Circ"},{"issue":"23","key":"pdig.0001441.ref037","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.121.023222","article-title":"Real-Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks","volume":"10","author":"SC Bollepalli","year":"2021","journal-title":"J Am Heart Assoc"},{"issue":"8","key":"pdig.0001441.ref038","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1038\/s41569-021-00522-7","article-title":"Smart wearable devices in cardiovascular care: where we are and how to move forward","volume":"18","author":"K Bayoumy","year":"2021","journal-title":"Nat Rev Cardiol"},{"issue":"3","key":"pdig.0001441.ref039","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.ajhg.2009.01.026","article-title":"Diverse genome-wide association studies associate the IL12\/IL23 pathway with Crohn Disease","volume":"84","author":"K Wang","year":"2009","journal-title":"Am J Hum Genet"},{"issue":"1","key":"pdig.0001441.ref040","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/S2213-2600(14)70239-5","article-title":"Mortality prediction in intensive care units with the Super ICU Learner Algorithm (SICULA): a population-based study","volume":"3","author":"R Pirracchio","year":"2015","journal-title":"Lancet Respir Med"},{"key":"pdig.0001441.ref041","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s40560-019-0393-1","article-title":"Artificial neural networks improve and simplify intensive care mortality prognostication: a national cohort study of 217,289 first-time intensive care unit admissions","volume":"7","author":"G Holmgren","year":"2019","journal-title":"J Intensive Care"},{"issue":"1","key":"pdig.0001441.ref042","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1186\/s12873-021-00501-8","article-title":"A machine learning model to predict critical care outcomes in patient with chest pain visiting the emergency department","volume":"21","author":"TT Wu","year":"2021","journal-title":"BMC Emerg Med"},{"issue":"1","key":"pdig.0001441.ref043","article-title":"Prediction of Incident Hypertension Within the Next Year: Prospective Study Using Statewide Electronic Health Records and Machine Learning","volume":"20","author":"C Ye","year":"2018","journal-title":"J Med Internet Res"},{"issue":"1","key":"pdig.0001441.ref044","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1038\/s41598-018-36745-x","article-title":"Learning from Longitudinal Data in Electronic Health Record and Genetic Data to Improve Cardiovascular Event Prediction","volume":"9","author":"J Zhao","year":"2019","journal-title":"Sci Rep"},{"issue":"22","key":"pdig.0001441.ref045","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.118.009476","volume":"7","author":"IA Kakadiaris","year":"2018","journal-title":"J Am Heart Assoc"},{"key":"pdig.0001441.ref046","doi-asserted-by":"crossref","first-page":"923549","DOI":"10.3389\/fcvm.2022.923549","article-title":"Prediction and Risk Stratification of Cardiovascular Disease in Diabetic Kidney Disease Patients","volume":"9","author":"J Ren","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"pdig.0001441.ref047","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.annepidem.2022.03.010","article-title":"Epidemiological predictive modeling: lessons learned from the Kuopio ischemic heart disease risk factor study","volume":"70","author":"C Brester","year":"2022","journal-title":"Ann Epidemiol"},{"issue":"11","key":"pdig.0001441.ref048","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s11906-022-01212-6","article-title":"Machine Learning for Hypertension Prediction: a Systematic Review","volume":"24","author":"GFS Silva","year":"2022","journal-title":"Curr Hypertens Rep"},{"issue":"12","key":"pdig.0001441.ref049","doi-asserted-by":"crossref","DOI":"10.1161\/JAHA.119.012129","article-title":"Long-Term Exposure to Elevated Systolic Blood Pressure in Predicting Incident Cardiovascular Disease: Evidence From Large-Scale Routine Electronic Health Records","volume":"8","author":"JR Ayala Solares","year":"2019","journal-title":"J Am Heart Assoc"},{"issue":"11","key":"pdig.0001441.ref050","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1001\/jamacardio.2018.2763","article-title":"Use of Long-term Cumulative Blood Pressure in Cardiovascular Risk Prediction Models","volume":"3","author":"LR Pool","year":"2018","journal-title":"JAMA Cardiol"},{"issue":"8","key":"pdig.0001441.ref051","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1038\/jhh.2017.20","article-title":"Blood pressure trajectories in relation to cardiovascular mortality: The Rancho Bernardo Study","volume":"31","author":"SMAJ Tielemans","year":"2017","journal-title":"J Hum Hypertens"},{"key":"pdig.0001441.ref052","article-title":"Heritability and risks associated with early onset hypertension: multigenerational, prospective analysis in the Framingham Heart Study","volume":"357","author":"TJ Niiranen","year":"2017","journal-title":"BMJ"},{"key":"pdig.0001441.ref053","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1080\/07853890.2020.1733648","article-title":"Longitudinal blood pressure patterns and cardiovascular disease risk","volume":"52","author":"J Nuotio","year":"2020","journal-title":"Ann Med"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:22:56Z","timestamp":1779384176000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001441"}},"subtitle":[],"editor":[{"given":"Chenxi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":53,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001441","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]}}}