EUVIMEDEUVIMED entdecken
Open Access

Prediction of 24‐Hour Urinary Sodium Excretion Using Machine‐Learning Algorithms

Rikuta Hamaya iD, Molin Wang iD, Stephen P Juraschek iD, Kenneth J Mukamal iD, JoAnn E Manson iD, Deirdre K Tobias iD, Qi Sun iD, Gary C Curhan iD, Walter C Willett iD, Eric B Rimm iD, Nancy R Cook iD

Journal of the American Heart Association · 2024

DOI: 10.1161/jaha.123.034310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Heart Association, 2024. Verfasst von Rikuta Hamaya und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Epidemiology Harvard T. H. Chan School of Public Health Boston MA USA. Hauptthemen laut MEDLINE: Machine Learning, Hypertension. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NHLBI NIH HHS, NICHD NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate quantification of sodium intake based on self‐reported dietary assessments has been a persistent challenge. We aimed to apply machine‐learning (ML) algorithms to predict 24‐hour urinary sodium excretion from self‐reported questionnaire information. Methods and Results We analyzed 3454 participants from the NHS (Nurses' Health Study), NHS‐II (Nurses' Health Study II), and HPFS (Health Professionals Follow‐Up Study), with repeated measures of 24‐hour urinary sodium excretion over 1 year. We used an ensemble approach to predict averaged 24‐hour urinary sodium excretion using 36 characteristics. The TOHP‐I (Trial of Hypertension Prevention I) was used for the external validation. The final ML algorithms were applied to 167 920 nonhypertensive adults with 30‐year follow‐up to estimate confounder‐adjusted hazard ratio (HR) of incident hypertension for predicted sodium. Averaged 24‐hour urinary sodium excretion was better predicted and calibrated with ML compared with the food frequency questionnaire (Spearman correlation coefficient, 0.51 [95% CI, 0.49–0.54] with ML; 0.19 [95% CI, 0.16–0.23] with the food frequency questionnaire; 0.46 [95% CI, 0.42–0.50] in the TOHP‐I). However, the prediction heavily depended on body size, and the prediction of energy‐adjusted 24‐hour sodium excretion was modestly better using ML. ML‐predicted sodium was modestly more strongly associated than food frequency questionnaire‐based sodium in the NHS‐II (HR comparing Q5 versus Q1, 1.48 [95% CI, 1.40–1.56] with ML; 1.04 [95% CI, 0.99–1.08] with the food frequency questionnaire), but no material differences were observed in the NHS or HPFS.

Conclusions

The present ML algorithm improved prediction of participants' absolute 24‐hour urinary sodium excretion. The present algorithms may be a generalizable approach for predicting absolute sodium intake but do not substantially reduce the bias stemming from measurement error in disease associations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningHypertensionHumansFemaleMaleMiddle AgedAdultSodiumAgedSodium, DietaryAlgorithmsPredictive Value of TestsSelf ReportTime FactorsReproducibility of ResultsUnited StatesUrinalysis

Stichwörter der Autor:innen

dietary sodiumfood frequency questionnairehypertensionmachine learningmeasurement error

Substanzen

SodiumSodium, Dietary

Autor:innen und Institutionen

  • Department of Epidemiology Harvard T. H. Chan School of Public Health Boston MA USA.
  • Division of Preventive Medicine, Department of Medicine Brigham and Women's Hospital and Harvard Medical School Boston MA USA.
  • Department of Biostatistics Harvard T. H. Chan School of Public Health Boston MA USA.
  • Channing Division of Network Medicine, Department of Medicine Brigham and Women's Hospital and Harvard Medical School Boston MA USA.
  • Department of Medicine, Beth Israel Deaconess Medical Center Harvard Medical School Boston MA USA.
  • Mary Horrigan Connors Center for Women's Health and Gender Biology Brigham and Women's Hospital and Harvard Medical School Boston MA USA.

ORCID-Profile: Rikuta Hamaya, Molin Wang, Stephen P Juraschek, Kenneth J Mukamal, JoAnn E Manson, Deirdre K Tobias, Qi Sun, Gary C Curhan, Walter C Willett, Eric B Rimm, Nancy R Cook

Förderung

  • NCI NIH HHS
  • NHLBI NIH HHS
  • NICHD NIH HHS

Zitieren

APA

Hamaya, R., Wang, M., Juraschek, S. P., Mukamal, K. J., Manson, J. E., Tobias, D. K., Sun, Q., Curhan, G. C., Willett, W. C., Rimm, E. B., & Cook, N. R. (2024). Prediction of 24‐Hour Urinary Sodium Excretion Using Machine‐Learning Algorithms. Journal of the American Heart Association. https://doi.org/10.1161/jaha.123.034310

Vancouver

Hamaya R, Wang M, Juraschek SP, Mukamal KJ, Manson JE, Tobias DK, et al. Prediction of 24‐Hour Urinary Sodium Excretion Using Machine‐Learning Algorithms. Journal of the American Heart Association. 2024. doi:10.1161/jaha.123.034310

BibTeX
@article{Hamaya2024,
  author = {Hamaya, Rikuta and Wang, Molin and Juraschek, Stephen P and Mukamal, Kenneth J and Manson, JoAnn E and Tobias, Deirdre K and Sun, Qi and Curhan, Gary C and Willett, Walter C and Rimm, Eric B and Cook, Nancy R},
  title = {Prediction of 24‐Hour Urinary Sodium Excretion Using Machine‐Learning Algorithms},
  journal = {Journal of the American Heart Association},
  year = {2024},
  doi = {10.1161/jaha.123.034310}
}
Kostenlos starten →