Predicting self-perceived general health status using machine learning: an external exposome study

Abstract

Background Self-perceived general health (SPGH) is a general health indicator commonly used in epidemiological research and is associated with a wide range of exposures from different domains. However, most studies on SPGH only investigated a limited set of exposures and did not take the entire external exposome into account. We aimed to develop predictive models for SPGH based on exposome datasets using machine learning techniques and identify the most important predictors of poor SPGH status. Methods Random forest (RF) was used on two datasets based on personal characteristics from the 2012 and 2016 editions of the Dutch national health survey, enriched with environmental and neighborhood characteristics. Model performance was determined using the area under the curve (AUC) score. The most important predictors were identified using a variable importance procedure and individual effects of exposures using partial dependence and accumulated local effect plots. The final 2012 dataset contained information on 199,840 individuals and 81 variables, whereas the final 2016 dataset had 244,557 individuals with 91 variables. Results Our RF models had overall good predictive performance (2012: AUC = 0.864 (CI: 0.852–0.876); 2016: AUC = 0.890 (CI: 0.883–0.896)) and the most important predictors were “Control of own life”, “Physical activity”, “Loneliness” and “Making ends meet”. Subjects who felt insufficiently in control of their own life, scored high on the De Jong-Gierveld loneliness scale or had difficulty in making ends meet were more likely to have poor SPGH status, whereas increased physical activity per week reduced the probability of poor SPGH. We observed associations between some neighborhood and environmental characteristics, but these variables did not contribute to the overall predictive strength of the models. Conclusions This study identified that within an external exposome dataset, the most important predictors for SPGH status are related to mental wellbeing, physical exercise, loneliness, and financial status.

Servant leadership, brand love, and work ethic: important predictors of general health in workers in the education sector

“…Furthermore, previous studies have shown that general health reflects not only physical health but also mental health (Bezuidenhout et al, 2023), because general health is a broader outcome than physical and mental health (Shi et al, 2022). A wide range of factors are known to be associated with health status (Hoekstra et al, 2023), such as lifestyle (Isola, 2020), socioeconomic status (Nadi et al, 2020), wellbeing at work (de Ceballos and Santos, 2015), anxiety (Malakoutikhah et al, 2022), perceived disease burden (Nielsen et al, 2015), sociodemographic factors (Tinella et al, 2022), work facilitation (Shi et al, 2022), and work ability (Kisiel et al, 2023). By conducting a thorough review, studies show other multidimensional models, however, it is believed that for this non-clinical study it is better suited using the GHQ-12 (Montazeri et al, 2003;Hystad and Johnsen, 2020;Mayhew et al, 2021;Lütke et al, 2022).…”

“…And in this context, general health has an important meaning in the lives of workers in the education sector, where this construct has currently been linked to many others: such as coping strategies (Tinella et al, 2022), depression (Gladstone et al, 2018), job insecurity (Setati et al, 2015), psychological discomfort (Jakubiec et al, 2014), machine learning (Hoekstra et al, 2023), working capacity (Kisiel et al, 2023), quality of life (Bezuidenhout et al, 2023), among other. Understanding general health as the mental, emotional and physical wellbeing that allows us to face challenges (Lunde et al, 2022) and acquire greater concentration in the activities that are carried out (Chavez-Espinoza et al, 2022).…”