Innovative use of data sources: a cross-sectional study of data linkage and artificial intelligence practices across European countries

ObjectivesPsychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.DesignCross-sectional study.SettingWe conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.ParticipantsAn AI model of the neural network and six psychiatrists.Primary outcomeThe accuracies of the AI model and psychiatrists for predicting psychological distress.MethodsIn total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.ResultsThe accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.ConclusionsA machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

Download Full-text

Factors associated with physical, psychological and social frailty among community-dwelling older persons in Europe: a cross-sectional study of Urban Health Centres Europe (UHCE)

BMC Geriatrics ◽

10.1186/s12877-021-02364-x ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Lizhen Ye ◽

Liset E. M. Elstgeest ◽

Xuxi Zhang ◽

Tamara Alhambra-Borrás ◽

Siok Swan Tan ◽

...

Keyword(s):

Risk Factors ◽

Urban Health ◽

Cross Sectional Study ◽

Community Dwelling ◽

Household Composition ◽

European Countries ◽

Sectional Study ◽

Related Condition ◽

Cross Sectional ◽

Age Related

Abstract Background Frailty is an age-related condition resulting in a state of increased vulnerability regarding functioning across multiple systems. It is a multidimensional concept referring to physical, psychological and social domains. The purpose of this study is to identify factors (demographic characteristics, lifestyle factors and health indicators) associated with overall frailty and physical, psychological and social frailty in community-dwelling older people from five European countries. Methods This cross-sectional study used baseline data from 2289 participants of the Urban Health Center European project in five European countries. Multivariable logistic regression models were used to assess associations of the factors with overall frailty and the three frailty domains. Results The mean age was 79.7 (SD = 5.7). Participants who were older, were female, had secondary or equivalent education, lived alone, not at risk of alcohol use, were less physically active, had multi-morbidity, were malnourished or with a higher level of medication risk, had higher odds of overall frailty (all P < 0.05). Age was not associated with psychological and social frailty; sex was not associated with social frailty; smoking and migration background was not associated with overall frailty or any of its domains. There existed an interaction effect between sex and household composition regarding social frailty (P < 0.0003). Conclusions The present study contributed new insights into the risk factors for frailty and its three domains (physical, psychological and social frailty). Nurses, physicians, public health professionals and policymakers should be aware of the risk factors of each type of frailty. Furthermore, examine these risk factors more comprehensively and consider overall frailty as well as its three domains in order to further contribute to decision-making more precisely on the prevention and management of frailty. Trial registration The intervention of the UHCE project was registered in the ISRCTN registry as ISRCTN52788952. The date of registration is 13/03/2017.

Download Full-text