RESUMO
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.
RESUMO
INTRODUCTION: A better understanding of the earliest stages of Alzheimer's disease (AD) could expedite the development or administration of treatments. Large population biobanks hold the promise to identify individuals at an elevated risk of AD and related dementias based on health registry information. Here, we establish the protocol for an observational clinical recall and biomarker study called TWINGEN with the aim to identify individuals at high risk of AD by assessing cognition, health and AD-related biomarkers. Suitable candidates were identified and invited to participate in the new study among THL Biobank donors according to TWINGEN study criteria. METHODS AND ANALYSIS: A multi-centre study (n=800) to obtain blood-based biomarkers, telephone-administered and web-based memory and cognitive parameters, questionnaire information on lifestyle, health and psychological factors, and accelerometer data for measures of physical activity, sedentary behaviour and sleep. A subcohort is being asked to participate in an in-person neuropsychological assessment (n=200) and wear an Oura ring (n=50). All participants in the TWINGEN study have genome-wide genotyping data and up to 48 years of follow-up data from the population-based older Finnish Twin Cohort (FTC) study of the University of Helsinki. The data collected in TWINGEN will be returned to THL Biobank from where it can later be requested for other biobank studies such as FinnGen that supported TWINGEN. ETHICS AND DISSEMINATION: This recall study consists of FTC/THL Biobank/FinnGen participants whose data were acquired in accordance with the Finnish Biobank Act. The recruitment protocols followed the biobank protocols approved by Finnish Medicines Agency. The TWINGEN study plan was approved by the Ethics Committee of Hospital District of Helsinki and Uusimaa (number 16831/2022). THL Biobank approved the research plan with the permission no: THLBB2022_83.