Prediction of 24‐Hour Urinary Sodium Excretion Using Machine‐Learning Algorithms-Reference-Cited by-同舟云学术

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

Published:2024-05-21 Issue:10 Volume:13 Page:
ISSN:2047-9980
Container-title:Journal of the American Heart Association
language:en
Short-container-title:JAHA

Author:

Hamaya Rikuta¹²^ORCID,Wang Molin¹³⁴^ORCID,Juraschek Stephen P.⁵^ORCID,Mukamal Kenneth J.⁵^ORCID,Manson JoAnn E.¹²⁶^ORCID,Tobias Deirdre K.²⁷^ORCID,Sun Qi⁵⁷^ORCID,Curhan Gary C.⁴⁸^ORCID,Willett Walter C.¹⁴⁷^ORCID,Rimm Eric B.¹⁴⁷^ORCID,Cook Nancy R.¹²^ORCID

Affiliation:

1. Department of Epidemiology Harvard T. H. Chan School of Public Health Boston MA USA

2. Division of Preventive Medicine, Department of Medicine Brigham and Women’s Hospital and Harvard Medical School Boston MA USA

3. Department of Biostatistics Harvard T. H. Chan School of Public Health Boston MA USA

4. Channing Division of Network Medicine, Department of Medicine Brigham and Women’s Hospital and Harvard Medical School Boston MA USA

5. Department of Medicine, Beth Israel Deaconess Medical Center Harvard Medical School Boston MA USA

6. Mary Horrigan Connors Center for Women’s Health and Gender Biology Brigham and Women’s Hospital and Harvard Medical School Boston MA USA

7. Department of Nutrition Harvard T. H. Chan School of Public Health Boston MA USA

8. Renal Division, Department of Medicine Brigham and Women’s Hospital Boston MA USA

Abstract

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.

Publisher

Ovid Technologies (Wolters Kluwer Health)

Reference36 articles.

1. Measurement Error in Nonlinear Models

2. Reproducibility and Validity of a Semiquantitative Food Frequency Questionnaire in Men Assessed by Multiple Methods

3. Reproducibility and validity of diet quality scores derived from food-frequency questionnaires

4. Effect of Change in Sodium Excretion on Change in Blood Pressure Corrected for Measurement Error: The Trials of Hypertension Prevention, Phase I

5. Measurement Error Corrected Sodium and Potassium Intake Estimation Using 24-Hour Urinary Excretion