EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning–driven integration of 24-hour ambulatory blood pressure and its variability

Evangelos Ntalianis iD, Everton Jose Santana, Nicholas Cauwenberghs iD, Veronique Cornelissen, Tatiana Kuznetsova iD

PLOS Digital Health · 16.07.2026 · 5 (7) · e0001499

DOI: 10.1371/journal.pdig.0001499 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 16.07.2026. Verfasst von Evangelos Ntalianis und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiovascular Sciences, Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven, Leuven, Belgium. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fonds Wetenschappelijk Onderzoek, Onderzoeksraad, KU Leuven.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Twenty-four hour ambulatory blood pressure (BP) monitoring (24-hour ABPM) is considered the best out-of-office BP measurement to assess hypertension. Yet, the complexity of the obtained data, hinders their interpretation. Therefore, in this study, we investigated whether a clustering algorithm could facilitate the integrative interpretation of 24-hour ambulatory BP and its variability to construct distinctive clusters associated with cardiovascular (CV) outcomes. In 1344 community-dwelling individuals (mean age, 46.9 years; 50.6% women), we acquired 24-hour ABPM recordings, clinical data at baseline and we collected adverse outcomes (median follow-up time 19.4 years). We used dynamic time warping combined with the k-medoids clustering algorithm on the heart rate, systolic and diastolic BP recordings. Clinical characteristics and CV outcome were used to evaluate the validity of the derived clusters using the original cohort, while an external general population cohort (n = 1219) was used for further validation. We separated the dataset into 4 clusters. Cluster 1 showed the most favourable CV risk profile comprising younger individuals with the lowest 24-hour ABPM patterns. On the contrary, cluster 4 revealed the worst CV profile with older participants, higher office and 24-hour ABPM, higher medication intake and the highest BP variability. After adjusting for traditional risk factors, including office systolic BP cluster 4 had significantly higher risk of adverse CV events compared to cluster 1 (HR: 1.63; 95%CI:1.15-2.32; P = 0.006). Similar findings were made in the external validation cohort. Time series clustering of ABPM recordings may facilitate the integrative interpretation of 24-hour ambulatory BP and BP variability.

Autor:innen und Institutionen

  • Department of Cardiovascular Sciences, Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven, Leuven, Belgium.
  • Department of Rehabilitation Sciences, Rehabilitation in Internal Disorders, KU Leuven, Leuven, Belgium.

ORCID-Profile: Evangelos Ntalianis, Nicholas Cauwenberghs, Tatiana Kuznetsova

Förderung

  • Fonds Wetenschappelijk Onderzoek
  • Onderzoeksraad, KU Leuven

Zitieren

APA

Ntalianis, E., Santana, E. J., Cauwenberghs, N., Cornelissen, V., & Kuznetsova, T. (2026). Machine learning–driven integration of 24-hour ambulatory blood pressure and its variability. PLOS Digital Health, 5(7), e0001499. https://doi.org/10.1371/journal.pdig.0001499

Vancouver

Ntalianis E, Santana EJ, Cauwenberghs N, Cornelissen V, Kuznetsova T. Machine learning–driven integration of 24-hour ambulatory blood pressure and its variability. PLOS Digital Health. 2026;5(7):e0001499. doi:10.1371/journal.pdig.0001499

BibTeX
@article{Ntalianis2026,
  author = {Ntalianis, Evangelos and Santana, Everton Jose and Cauwenberghs, Nicholas and Cornelissen, Veronique and Kuznetsova, Tatiana},
  title = {Machine learning–driven integration of 24-hour ambulatory blood pressure and its variability},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {7},
  pages = {e0001499},
  doi = {10.1371/journal.pdig.0001499}
}
Kostenlos starten →