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 - Takeaways - MDSpire

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

  • By

  • Li Wang

  • Ji Song

  • Yingzhu Xie

  • Yaqi Liu

  • Liangbang Zeng

  • July 15, 2026

Share

  • 1

    Coronary heart disease (CHD) is a leading cause of morbidity and mortality, necessitating early identification of high-risk hypertensive patients.

  • 2

    The study developed a deep neural network model using 1,026 patients to forecast CHD risk based on 24-hour ambulatory blood pressure monitoring.

  • 3

    The model achieved an AUC of 0.822 in the training cohort and 0.796 in the validation cohort, indicating strong predictive performance.

  • 4

    Nine predictors were identified, including diabetes mellitus and time in target range of systolic blood pressure, which influenced model predictions.

  • 5

    The study highlights the potential of machine learning methods to improve risk stratification for CHD in hypertensive patients using routine clinical data.

Original Source(s)

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

  • by Li Wang, Ji Song, Yingzhu Xie, Yaqi Liu, Liangbang Zeng

  • July 15, 2026

Related Content

Prolonged Sleep Restriction May Increase Body Weight

In a pooled analysis of two randomized crossover trials, reducing nightly sleep by about 1.5 hours for 6 weeks was associated with modest increases in body weight and waist circumference without measurable changes in body composition.

Editorial: introducing special collection on cancer and cardiovascular disorders

One Pill to Rule Them All: The Role of Single-Pill Combinations in Optimizing Blood Pressure Control