Sedentary Behavioral Studies of Young and Middle-Aged Adults with Hypertension in the Framework of Behavioral Epidemiology: A Scoping Review

Abstract

(1) Background: As times change, the detection rate of hypertension is increasing in the young and middle-aged population due to prevalent sedentary behaviors. The purpose of this study was to conduct a scoping review to identify and summarize the research on sedentary behavior in this population by separating it into five stages: the relationship between sedentary behavior and health; measurement modalities; influencing factors; interventions; and translational research in young and middle-aged adults with hypertension. (2) Methods: Using a scoping review research approach, the PubMed, Web of Science Core Collection, and MEDLINE databases were used to search for the literature on this subject from the date of the database’s creation to 14 June 2022, and the behavioral epidemiology framework was used to classify the retrieved articles. (3) Results: A total of eight articles were included. Among them, there were six articles on the relationship between behavior and health, which includes blood pressure, insulin resistance, and the cardiovascular system; one article on the study of measurement methods, which was used for clinical decision making through decision trees; one article on influencing factors, which was divided into intrinsic and extrinsic factors; and no articles on intervention program development or the translation of intervention programs to further practice in this population. (4) Conclusions: Sedentary behavioral studies of young and middle-aged adults with hypertension are scarce and are generally carried out in the early stages of the condition. In the future, in-depth studies can be conducted on the dose–response relationship between sedentary behavior and health in this population; the development of easier and targeted measurement tools; the exploration of more influencing factors; and the effectiveness and translation of intervention programs.

Shapely additive values can effectively visualize pertinent covariates in machine learning when predicting hypertension

“…However, due to the complexity of the non‐parametric algorithms that are common in machine‐learning methods, it is impossible for a human to analyze each tree and execute an explanation of how the machine‐learning method works 7,28,30,35,42–45 . Without methods that explain how machine learning algorithms reach their predictions, clinicians will not be able to identify if models are reliable and generalizable or just replicating the biases within the training datasets 11,35–37,46 . This study is one of the first in the literature that predicts risk for hypertension from nutritional covariates using machine‐learning methods and executes model explanation algorithms to add transparency to the methods.…”

“…7,28,30,35,[42][43][44][45] Without methods that explain how machine learning algorithms reach their predictions, clinicians will not be able to identify if models are reliable and generalizable or just replicating the biases within the training datasets. 11,[35][36][37]46 This study is one of the first in the literature that predicts risk for hypertension from nutritional covariates using machine-learning methods and executes model explanation algorithms to add transparency to the methods.…”

“…Over 50% of the complications of hypertension may be prevented through diet modifications 6–9 . Guidelines for treatment and control of hypertension by the American Heart Association have increasingly leveraged lifestyle recommendations in addition to pharmaceutical‐based therapy 1,3,10,11 . Therefore, using patient diets as a potential risk factor for hypertension may enhance personalized medical care 2,12,13 …”

“…Hypertension is the leading cause of worldwide mortality, responsible for over 40% of deaths from cardiovascular disease, type 2 diabetes, leveraged lifestyle recommendations in addition to pharmaceuticalbased therapy. 1,3,10,11 Therefore, using patient diets as a potential risk factor for hypertension may enhance personalized medical care. 2,12,13 Machine learning algorithms, which generate predictions from data without explicit direction from the user, can be effectively employed to leverage the ever-growing data present in hospital systems to augment diagnosis, improve outcomes, and reduce costs.…”