ABSTRACT
AIM: Machine learning techniques have demonstrated success in predictive modeling across various clinical cases. However, few studies have considered predicting the use of multisectoral health and social services among older adults. This research aims to utilize machine learning models to detect high-risk groups of excessive health and social services utilization at early stage, facilitating the implementation of preventive interventions. METHODS: We used pseudonymized data covering a four-year period and including information on a total of 33,374 senior citizens from Southern Finland. The endpoint was defined based on the occurrence of unplanned healthcare visits and the total number of different services used. Input features included individual's basic demographics, health status and past usage of healthcare resources. Logistic regression and eXtreme Gradient Boosting (XGBoost) methods were used for binary classification, with the dataset split into 70% training and 30% testing sets. RESULTS: Subgroup-based results mirrored trends observed in the full cohort, with age and certain health issues, e.g. mental health, emerging as positive predictors for high service utilization. Conversely, hospital stay and urban residence were associated with decreased risk. The models achieved a classification performance (AUC) of 0.61 for the full cohort and varying in the range of 0.55-0.62 for the subgroups. CONCLUSIONS: Predictive models offer potential for predicting future high service utilization in the older adult population. Achieving high classification performance remains challenging due to diverse contributing factors. We anticipate that classification performance could be increased by including features based on additional data categories such as socio-economic data.
ABSTRACT
BACKGROUND: We aimed to explore to the possibilities of utilizing automatically accumulating data on health-owned for example by local companies and non-governmental organizations-to complement traditional health data sources in health promotion work at the local level. METHODS: Data for the PUHTI study consisted of postal code level information on sport license holders, drug purchase and sales advertisements in a TOR online underground marketplace, and grocery sales in Tampere. Additionally, open population register data were utilized. An interactive reporting tool was prepared to show the well-being profile for each postal code area. Feedback from the tool's end-users was collected in interviews. RESULTS: The study showed that buying unhealthy food and alcohol, selling or buying drugs, and participating in organized sport activities differed by postal code areas according to its socioeconomic profile in the city of Tampere. The health and well-being planners and managers of Tampere found that the new type of data brought added value for the health promotion work at the local level. They perceived the interactive reporting tool as a good tool for planning, managing, allocating resources and preparing forecasts. CONCLUSIONS: Traditional health data collection methods-administrative registers and health surveys-are the cornerstone of local health promotion work. Digital footprints, including data accumulated about people's everyday lives outside the health service system, can provide additional information on health behaviour for various population groups. Combining new sources with traditional health data opens a new perspective for health promotion work at local and regional levels.
