Dataset Information

What influences individual perception of health? Using machine learning to disentangle self-perceived health.

ABSTRACT: Self-perceived health is a subjective health outcome that summarizes all the health conditions and is widely used in population health studies. Yet, despite its well-known relationship with survival, it is still unclear as to which health conditions are actually taken into account when making an individual assessment of one's own health. The aim of this paper is to assess the influence of four objective health conditions - IADLs, ADLs, chronic diseases, and depression - in predicting self-perceived health among Europeans by age group (50-64 and 65-79) and by sex. Classification trees (J48 algorithm), which pertains to the emerging Machine Learning techniques, were applied to predict self-perceived health according to the four abovementioned objective health conditions of European individuals in the sixth wave of the Survey of Health, Ageing and Retirement in Europe (SHARE) (n = 55,611). The four variables present different degrees of relevance in establishing predictions of self-perceived health values by age and by sex. Before the age of 65, chronic diseases have the greatest importance, while IADL limitations are more important in the 65-79 age group. Likewise, ADL limitations are more important for women free of chronic diseases in the 50-64 age group; however, these differences disappear among women in the older group. There is an evident degree of interplay between the objective health indicators of chronic diseases, ADLs, IADLs, and depression when predicting self-perceived health with a high level of accuracy. This interplay implies that self-perceived health summarizes different health conditions depending on age. Gender differences are only evident for the younger age group, whereas construction of self-perceived is the same for women and men among the older group. Therefore, none of these four indicators on its own is able to totally substitute self-perceived health.

SUBMITTER: Guma J

PROVIDER: S-EPMC8669356 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Current approaches to understanding medication ordering errors rely on relatively small manually captured error samples. These approaches are resource-intensive, do not scale for computerized provider order entry (CPOE) systems, and are likely to miss important risk factors associated with medication ordering errors. Previously, we described a dataset of CPOE-based medication voiding accompanied by univariable and multivariable regression analyses. However, these traditional techniques require expert guidance and may perform poorly compared to newer approaches. In this paper, we update that analysis using machine learning (ML) models to predict erroneous medication orders and identify its contributing factors. We retrieved patient demographics (race/ethnicity, sex, age), clinician characteristics, type of medication order (inpatient, prescription, home medication by history), and order content. We compared logistic regression, random forest, boosted decision trees, and artificial neural network models. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). The dataset included 5,804,192 medication orders, of which 28,695 (0.5%) were voided. ML correctly classified voids at reasonable accuracy; with a positive predictive value of 10%, ~20% of errors were included. Gradient boosted decision trees achieved the highest AUROC (0.7968) and AUPRC (0.0647) among all models. Logistic regression had the poorest performance. Models identified predictive factors with high face validity (e.g., student orders), and a decision tree revealed interacting contexts with high rates of errors not identified by previous regression models. Prediction models using order-entry information offers promise for error surveillance, patient safety improvements, and targeted clinical review. The improved performance of models with complex interactions points to the importance of contextual medication ordering information for understanding contributors to medication errors.

Dataset Information

What influences individual perception of health? Using machine learning to disentangle self-perceived health.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets