{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:05:47Z","timestamp":1784091947544,"version":"3.55.0"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Coronary heart disease (CHD) remains a leading cause of morbidity and mortality worldwide. Early identification of high-risk hypertensive patients is crucial for preventing cardiovascular events. While traditional risk scores rely on static clinical measurements, 24-h ambulatory blood pressure monitoring (ABPM)-derived time in target range (TTR) captures dynamic blood pressure control patterns that may improve risk stratification. Machine learning methods, particularly deep neural networks, offer an enhanced capability to model complex non-linear relationships in high-dimensional clinical data, compared with conventional statistical approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This single-center retrospective cohort study included 1,026 patients admitted between January 2023 and December 2024, with 718 patients allocated to model development and 308 to internal validation. A deep neural network model with three hidden layers was developed and compared against eight conventional machine learning algorithms (logistic regression, na\u00efve Bayes, k-nearest neighbors, random forest, support vector machine, XGBoost, LightGBM, and CatBoost). Thirty-two variables spanning demographics, clinical data, laboratory results, echocardiographic measures, and blood pressure indices were evaluated. Continuous variables were discretized into quartile-based categories to enhance clinical interpretability. Feature selection employed a two-step process combining the Boruta algorithm and least absolute shrinkage and selection operator (LASSO) regression, with variance inflation factor analysis confirming the absence of collinearity. Model selection prioritized balanced performance across discrimination (AUC), calibration (Brier score), and clinical utility (decision curve analysis) in the independent validation cohort. Interpretability was evaluated using SHAP (SHapley Additive exPlanations) values.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The deep neural network model achieved optimal balanced performance with an AUC of 0.822 (95% CI: 0.793\u20130.850) in the training cohort and 0.796 (95% CI: 0.749\u20130.846) in the validation cohort, accompanied by the lowest Brier score (0.172), indicating superior calibration. Nine predictors were retained: diabetes mellitus, mean systolic blood pressure, time in target range of systolic blood pressure, left atrial diameter, left ventricular end-systolic diameter, left ventricular ejection fraction, use of antihypertensive medications, calcium channel blockers, and\n                      <jats:italic>\u03b2<\/jats:italic>\n                      -blockers. SHAP analysis identified TTR and blood pressure control parameters as the primary drivers of model predictions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The developed deep neural network model enables early identification of high-risk CHD patients with hypertension through interpretable, routinely available clinical variables. Prospective multicenter external validation is warranted to confirm its generalizability across diverse populations and clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1860785","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:22:09Z","timestamp":1784089329000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a deep neural network for predicting coronary heart disease in hypertensive patients using 24-hour ambulatory blood pressure monitoring: a retrospective study"],"prefix":"10.3389","volume":"13","author":[{"given":"Li","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Cardiology, Chengfei Hospital, General Medical Services Corporation","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Chengfei Hospital, General Medical Services Corporation","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingzhu","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Chengfei Hospital, General Medical Services Corporation","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Chengfei Hospital, General Medical Services Corporation","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangbang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Chengfei Hospital, General Medical Services Corporation","place":["Chengdu, Sichuan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e93","DOI":"10.1161\/CIR.0000000000001123","article-title":"Heart disease and stroke Statistics-2023 update: a report from the American Heart Association","volume":"147","author":"Tsao","year":"2023","journal-title":"Circulation"},{"key":"ref2","doi-asserted-by":"crossref","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":"Brunstr\u00f6m","year":"2023","journal-title":"J Hypertens"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1016\/j.jacc.2021.01.014","article-title":"Systolic blood pressure time in target range and cardiovascular outcomes in patients with hypertension","volume":"77","author":"Fatani","year":"2021","journal-title":"J Am Coll Cardiol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e007131","DOI":"10.1161\/JAHA.117.007131","article-title":"Time in therapeutic range, as a determinant of all-cause mortality in patients with hypertension","volume":"6","author":"Doumas","year":"2017","journal-title":"J Am Heart Assoc"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1161\/HYPERTENSIONAHA.121.17873","article-title":"Effect of a physician\/pharmacist collaborative care model on time in target range for systolic blood pressure: post hoc analysis of the CAPTION trial","volume":"78","author":"Dixon","year":"1979","journal-title":"Hypertension (Dallas, Tex: 1979)"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e022765","DOI":"10.1161\/JAHA.121.022765","article-title":"Time in target range for systolic blood pressure and cardiovascular outcomes in patients with heart failure with preserved ejection fraction","volume":"11","author":"Huang","year":"2022","journal-title":"J Am Heart Assoc"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1161\/HYPERTENSIONAHA.122.20141","article-title":"Systolic blood pressure time in target range and major adverse kidney and cardiovascular events","volume":"80","author":"Buckley","year":"2023","journal-title":"Hypertension (Dallas, Tex: 1979)"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1628","DOI":"10.1161\/hypertensionaha.122.20711","article-title":"Systolic blood pressure time in target range and cognitive outcomes: insights from the SPRINT MIND trial","volume":"80","author":"Li","year":"1979","journal-title":"Hypertension"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1111\/jgs.18641","article-title":"Time in target range of systolic blood pressure and cognitive outcomes in patients with hypertension","volume":"72","author":"Huang","year":"2024","journal-title":"J Am Geriatr Soc"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1161\/HYPERTENSIONAHA.123.21651","article-title":"Systolic blood pressure time in target range and incident atrial fibrillation in patients with hypertension: insights from the SPRINT trial","volume":"80","author":"Wang","year":"1979","journal-title":"Hypertension (Dallas, Tex: 1979)"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41440-024-01840-2","article-title":"Systolic blood pressure time in target range within 24 h and incident heart failure: insights from the real-world setting","volume":"48","author":"Tian","year":"2025","journal-title":"Hypertens Res"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"101342","DOI":"10.1016\/j.ajpc.2025.101342","article-title":"Comparing the accuracy of continuous blood pressure monitoring using wearable cuffless devices with conventional 24-h ambulatory blood pressure monitoring: a systematic review and meta-analysis","volume":"24","author":"Lee","year":"2025","journal-title":"Am J Prev Cardiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"e35","DOI":"10.1161\/HYP.0000000000000087","article-title":"Measurement of blood pressure in humans: a scientific statement from the American Heart Association","volume":"73","author":"Muntner","year":"2019","journal-title":"Hypertension"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"110281","DOI":"10.1016\/j.isci.2024.110281","article-title":"Explainable machine learning for predicting 30-day readmission in acute heart failure patients","volume":"27","author":"Zhang","year":"2024","journal-title":"iScience"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1186\/s12933-025-02654-3","article-title":"Relationship between atherogenic index of plasma and length of stay in critically ill patients with atherosclerotic cardiovascular disease: a retrospective cohort study and predictive modeling based on machine learning","volume":"24","author":"Guo","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1186\/s12889-025-21609-7","article-title":"Characterisation of cardiovascular disease (CVD) incidence and machine learning risk prediction in middle-aged and elderly populations: data from the China health and retirement longitudinal study (CHARLS)","volume":"25","author":"Huang","year":"2025","journal-title":"BMC Public Health"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"3969","DOI":"10.1111\/dom.15745","article-title":"Development and validation of 10-year risk prediction models of cardiovascular disease in Chinese type 2 diabetes mellitus patients in primary care using interpretable machine learning-based methods","volume":"26","author":"Dong","year":"2024","journal-title":"Diabetes Obes Metab"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"ref19","volume-title":"Deep medicine: how artificial Intelligence can make Healthcare human again","author":"Topol","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1007\/s00592-025-02496-1","article-title":"Machine learning-based models to predict type 2 diabetes combined with coronary heart disease and feature analysis-based on interpretable SHAP","volume":"62","author":"Ji","year":"2025","journal-title":"Acta Diabetol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"104813","DOI":"10.1016\/j.compbiomed.2021.104813","article-title":"Interpretable prediction of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease based on machine learning and SHAP","volume":"137","author":"Wang","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref22","doi-asserted-by":"publisher","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":"Lundberg","year":"2020","journal-title":"Nature machine intelligence"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip Rev"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1177\/0962280218784726","article-title":"Sample size for binary logistic prediction models: beyond events per variable criteria","volume":"28","author":"van Smeden","year":"2019","journal-title":"Stat Methods Med Res"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1186\/s12872-025-04906-2","article-title":"Association between novel immune-inflammatory markers and hypertension patients with coronary heart disease: a cross-sectional study based on NHANES (2005-2016)","volume":"25","author":"Li","year":"2025","journal-title":"BMC Cardiovasc Disord"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"200253","DOI":"10.1016\/j.ijcrp.2024.200253","article-title":"Premature coronary heart disease complicated with hypertension in hospitalized patients: incidence, risk factors, cardiovascular-related comorbidities and prognosis, 2008-2018","volume":"21","author":"Li","year":"2024","journal-title":"Int J Cardiology Cardiovascular Risk Prevention"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1001\/jamainternmed.2024.0892","article-title":"Time- vs step-based physical activity metrics for health","volume":"184","author":"Hamaya","year":"2024","journal-title":"JAMA Intern Med"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s12933-024-02265-4","article-title":"Association between the stress hyperglycemia ratio and 28-day all-cause mortality in critically ill patients with sepsis: a retrospective cohort study and predictive model establishment based on machine learning","volume":"23","author":"Yan","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"120520","DOI":"10.1016\/j.jad.2025.120520","article-title":"Screening for depression risk in asthma patients: development and external validation of a machine learning-based predictive model","volume":"394","author":"Wan","year":"2026","journal-title":"J Affect Disord"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TNSRE.2025.3568325","article-title":"Identification of subtypes of post-stroke and Neurotypical gait behaviors using neural network analysis of gait cycle kinematics","volume":"33","author":"Kuch","year":"2025","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1016\/j.acra.2024.12.037","article-title":"Neural network and logistic regression models based on ultrasound Radiomics and clinical-pathological features to predict occult level II lymph node metastasis in papillary thyroid carcinoma","volume":"32","author":"Feng","year":"2025","journal-title":"Acad Radiol"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"11868","DOI":"10.1038\/s41598-020-68657-0","article-title":"Structure equation model and neural network analyses to predict coronary artery lesions in Kawasaki disease: a single-Centre retrospective study","volume":"10","author":"Azuma","year":"2020","journal-title":"Sci Rep"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1002\/lt.26442","article-title":"Use of neural network models to predict liver transplantation waitlist mortality","volume":"28","author":"Nagai","year":"2022","journal-title":"Liver transplantation"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.2147\/RMHP.S374339","article-title":"Development and validation of a coronary heart disease risk prediction model in snorers with hypertension: a retrospective observed study","volume":"15","author":"Wang","year":"2022","journal-title":"Risk Manag Healthcare Policy"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"e17257","DOI":"10.2196\/17257","article-title":"Accurate prediction of coronary heart disease for patients with hypertension from electronic health records with big data and machine-learning methods: model development and performance evaluation","volume":"8","author":"Du","year":"2020","journal-title":"JMIR Med Inform"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1025705","DOI":"10.3389\/fcvm.2022.1025705","article-title":"Machine learning outperforms traditional logistic regression and offers new possibilities for cardiovascular risk prediction: a study involving 143,043 Chinese patients with hypertension","volume":"9","author":"Xi","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/8285111","article-title":"Predicting coupled herbs for the treatment of hypertension complicated with coronary heart disease in real-world data based on a complex network and machine learning","volume":"2022","author":"Huan","year":"2022","journal-title":"Evid Based Complement Alternat Med"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.2147\/RMHP.S472398","article-title":"Application of the unbalanced ensemble algorithm for prognostic prediction outcomes of all-cause mortality in coronary heart disease patients comorbid with hypertension","volume":"17","author":"Zan","year":"2024","journal-title":"Risk Manage Healthcare Policy"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1186\/s12872-025-05479-w","article-title":"Development of a risk assessment model for multimorbidity of diabetes, hypertension, and coronary heart disease with XGBoost in primary care in Shanghai, China: a retrospective study","volume":"26","author":"Chen","year":"2026","journal-title":"BMC Cardiovasc Disord"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"7003","DOI":"10.1038\/s41598-025-85692-x","article-title":"Construction of a prediction model for coronary heart disease in type 2 diabetes mellitus: a cross-sectional study","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci Rep"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.2337\/dc20-2375","article-title":"Associations of type 2 diabetes onset age with cardiovascular disease and mortality: the Kailuan study","volume":"44","author":"Zhao","year":"2021","journal-title":"Diabetes Care"},{"key":"ref42","first-page":"13310","article-title":"Hemodynamic characteristics and early warnings in very old patients","volume":"13","author":"Lian","year":"2021","journal-title":"Am J Transl Res"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"8366","DOI":"10.12998\/wjcc.v9.i28.8366","article-title":"Ultrasonographic assessment of cardiac function and disease severity in coronary heart disease","volume":"9","author":"Zhang","year":"2021","journal-title":"World J Clin Cases"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1563692","DOI":"10.3389\/fnut.2025.1563692","article-title":"Relationships between vitamin C intake and COPD assessed by machine learning approaches from the NHANES (2017-2023)","volume":"12","author":"Tao","year":"2025","journal-title":"Front Nutr"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.1016\/s0140-6736(17)32478-9","article-title":"Prevalence, awareness, treatment, and control of hypertension in China: data from 1\u00b77 million adults in a population-based screening study (China PEACE million persons project)","volume":"390","author":"Lu","year":"2017","journal-title":"Lancet"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.amjcard.2022.06.045","article-title":"Impact of systolic blood pressure time in target range on adverse events in patients with Nonvalvular atrial fibrillation (from the J-RHYTHM registry)","volume":"180","author":"Kodani","year":"2022","journal-title":"Am J Cardiol"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1111\/jch.13515","article-title":"Sustained blood pressure control and coronary heart disease, stroke, heart failure, and mortality: an observational analysis of ALLHAT","volume":"21","author":"Bowling","year":"2019","journal-title":"J Clin Hypertens (Greenwich)"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/j.jchf.2022.01.010","article-title":"Prognostic value of time in blood pressure target range among patients with heart failure","volume":"10","author":"Chen","year":"2022","journal-title":"JACC Heart Failure"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1097\/HJH.0b013e328363e964","article-title":"European Society of Hypertension position paper on ambulatory blood pressure monitoring","volume":"31","author":"O'Brien","year":"2013","journal-title":"J Hypertens"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1860785\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:22:11Z","timestamp":1784089331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1860785\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":49,"alternative-id":["10.3389\/fmed.2026.1860785"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1860785","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1860785"}}