Antti Etholén

Antti Etholén

Auto-generated profile, based on publicly available information

Antti Etholén

Department of Public Health, University of Helsinki, Helsinki, Finland

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2022 in Journal of Aging and Health
Verified
Journal Article
Open access
AEAntti Etholén
Antti Etholén
OPOlli Pietiläinen
Olli Pietiläinen
AKAnne Kouvonen
Anne Kouvonen
MHMirja Hänninen
Mirja Hänninen
OROssi Rahkonen
Ossi Rahkonen
Tea LallukkaTea Lallukka
Tea Lallukka
Objectives: We applied a person-oriented approach and used latent class linear mixed models to identify sleep trajectories that explain memory, concentration, and learning ability problems after retirement. Methods: Data consist of prospective surveys from four phases of the Helsinki Health Study between 2000–2017 (n = 3748, aged 55–77 years, 80% women). Multinomial regression was used to examine the associations between sleep trajectories and cognitive function, adjusting for sociodemographic, health-related behavior, and health factor covariates. Results: Among statutory retirees, three latent group trajectories of insomnia-related symptoms were identified: stable low, decreasing, and increasing. Among those who had retired for disability reasons, we identified one additional latent group trajectory: stable high. Insomnia symptoms were associated with worse cognitive function. Discussion: Early detection of insomnia symptoms would be a potential intervention point to improve both sleep quality and prevent cognitive decline in later life. However, intervention studies are needed.

22 December 2023 in Preventive Medicine
Verified
Journal Article
Open access
AEAntti Etholén
Antti Etholén
AKAnne Kouvonen
Anne Kouvonen
MHMirja Hänninen
Mirja Hänninen
JKJenni Kulmala
Jenni Kulmala
OROssi Rahkonen
Ossi Rahkonen
Tea LallukkaTea Lallukka
Tea Lallukka
We examined individual and dual trajectories of insomnia symptoms and body mass index (BMI) before and after retirement, and their associations with changes in subjective cognitive functioning after retirement. We used the Helsinki Health Study's (n = 2360, 79% women, aged 40-60 at baseline, Finland) repeated surveys to identify the developmental patterns of insomnia symptoms and BMI (2000-2017) and changes in subjective cognitive functioning (2017-2022). We analysed the data using latent group-based dual trajectory modelling and logistic regression analysis. Three latent groups were identified for insomnia symptoms (stable low, decreasing and increasing symptoms) and BMI (stable healthy weight, stable overweight and stable obesity). Insomnia symptoms were associated with declining subjective cognitive functioning and largely explained the effects in the dual models. The association between dual trajectories of insomnia symptoms and BMI with subjective cognitive decline is dominated by insomnia symptoms.

6 May 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
AEAntti Etholén
Antti Etholén
TRTeemu Roos
Teemu Roos
MHMirja Hänninen
Mirja Hänninen
IBIoanna Bouri
Ioanna Bouri
JKJenni Kulmala
Jenni Kulmala
Tea LallukkaTea Lallukka
Tea Lallukka
Background: Several potentially modifiable risk factors are associated with subjective cognitive decline (SCD). However, developmental patterns of these risk factors have not been used before to forecast later SCD. Practical tools for the prevention of cognitive decline are needed. Objective: We examined multifactorial trajectories of risk factors and their associations with SCD using an artificial intelligence (AI) approach to build a score calculator that forecasts later SCD. In addition, we aimed to develop a new risk score tool to facilitate personalized risk assessment and intervention planning and to validate SCD against register-based dementia diagnoses and dementia-related medications. Methods: Five repeated surveys (2000-2022) of the Helsinki Health Study (N=8960; n=7168, 80% women, aged 40-60 years in phase 1) were used to build dynamic Bayesian networks for estimating the odds of SCD. The model structure was developed using expert knowledge and automated techniques, implementing a score-based approach for training dynamic Bayesian networks with the quotient normalized maximum likelihood criterion. The developed model was used to predict SCD (memory, learning, and concentration) based on the history of consumption of fruit and vegetables, smoking, alcohol consumption, leisure time physical activity, BMI, and insomnia symptoms, adjusting for sociodemographic covariates. Model performance was assessed using 5-fold cross-validation to calculate the area under the receiver operating characteristic curve. Bayesian credible intervals were used to quantify uncertainty in model estimates. Results: Of the participants, 1842 of 5865 (31%) reported a decline in memory, 2818 of 5879 (47.4%) in learning abilities, and 1828 of 5888 (30.7%) in concentration in 2022. Physical activity was the strongest predictor of SCD in a 5-year interval, with an odds ratio of 0.76 (95% Bayesian credible interval 0.59-0.99) for physically active compared to inactive participants. Alcohol consumption showed a U-shaped relationship with SCD. Other risk factors had minor effects. Moreover, our validation confirmed that SCD has prognostic value for diagnosed dementia, with individuals reporting memory decline being over 3 times more likely to have dementia in 2017 (age 57-77 years), and this risk increased to more than 5 times by 2022 (age 62-82 years). The receiver operating characteristic curve analysis further supported the predictive validity of our outcome, with an area under the curve of 0.78 in 2017 and 0.75 in 2022. Conclusions: A new risk score tool was developed that enables individuals to inspect their risk profiles and explore potential targets for interventions and their estimated contributions to later SCD. Using AI-driven predictive modeling, the tool can aid health care professionals in providing personalized prevention strategies. A dynamic decision heatmap was presented as a communication tool to be used at health care consultations. Our findings suggest that early identification of individuals with SCD could improve targeted intervention strategies for reducing dementia risk. Future research should explore the integration of AI-based risk prediction models into clinical workflows and assess their effectiveness in guiding lifestyle interventions to mitigate SCD and dementia.

28 October 2024 in European Journal of Public Health
Verified
Journal Article
Open access
PDF file
AEA Etholén
A Etholén
TRT Roos
T Roos
MHM Hänninen
M Hänninen
IBI Bouri
I Bouri
JKJ Kulmala
J Kulmala
TLT Lallukka
T Lallukka
Background: Several potentially modifiable risk factors are associated with subjective cognitive decline (SCD). However, developmental patterns of these risk factors have not been used before to forecast later SCD. Practical tools for the prevention of cognitive decline are needed. We examined multifactorial trajectories of risk factors, and their associations with SCD using an artificial intelligence approach to build a score that forecasts later SCD. Methods: Five repeated surveys (2000-2022) of the Helsinki Health Study (n = 8960, 79% women, aged 40-60 at Phase 1) were used to build dynamic Bayesian networks (DBN) for estimating the odds of SCD. A score-based approach was implemented for learning DBN using the quotient normalized maximum likelihood criterion. The model was used to predict SCD based on the history of consumption of fruit and vegetables, smoking, alcohol consumption, leisure-time physical activity, body mass index, and insomnia symptoms, adjusting for sociodemographic covariates. Results: Of the participants, 31-48% reported decline in memory, learning, and concentration in 2022. Physical activity was the strongest predictor of SCD in a 5-year interval, with an odds ratio of 0.76 (95% Bayesian credible interval 0.59-0.99) for physically active compared to inactive participants. Alcohol consumption showed a U-shaped relationship with SCD. Other risk factors had minor effects. Conclusions: A new online risk score tool was developed that enables individuals to inspect their own risk profiles, as well as explore potential targets for interventions and their estimated contributions to later SCD. Dynamic decision heatmap was presented as a communication tool to be used at healthcare consultations. Key messages: • Potentially modifiable health-related behaviours such as physical activity can contribute to subjective cognitive decline. • Artificial intelligence can be applied to discover the complex interactions between risk factors and subjective cognitive decline, to support preventive healthcare at individual and population levels.

2 August 2024 in JMIR Preprints
Verified
Preprint
Open access
AEAntti Etholén
Antti Etholén
TRTeemu Roos
Teemu Roos
MHMirja Hänninen
Mirja Hänninen
IBIoanna Bouri
Ioanna Bouri
JKJenni Kulmala
Jenni Kulmala
Tea LallukkaTea Lallukka
Tea Lallukka
BACKGROUND Several potentially modifiable risk factors are associated with subjective cognitive decline (SCD). However, developmental patterns of these risk factors have not been used before to forecast later SCD. Practical tools for the prevention of cognitive decline are needed. OBJECTIVE We examined multifactorial trajectories of risk factors and their associations with SCD using an artificial intelligence (AI) approach to build a score calculator that forecasts later SCD. In addition, we aimed to develop a new risk score tool to facilitate personalized risk assessment and intervention planning and to validate SCD against register-based dementia diagnoses and dementia-related medications. METHODS Five repeated surveys (2000-2022) of the Helsinki Health Study (N=8960; n=7168, 80% women, aged 40-60 years in phase 1) were used to build dynamic Bayesian networks for estimating the odds of SCD. The model structure was developed using expert knowledge and automated techniques, implementing a score-based approach for training dynamic Bayesian networks with the quotient normalized maximum likelihood criterion. The developed model was used to predict SCD (memory, learning, and concentration) based on the history of consumption of fruit and vegetables, smoking, alcohol consumption, leisure time physical activity, BMI, and insomnia symptoms, adjusting for sociodemographic covariates. Model performance was assessed using 5-fold cross-validation to calculate the area under the receiver operating characteristic curve. Bayesian credible intervals were used to quantify uncertainty in model estimates. RESULTS Of the participants, 1842 of 5865 (31%) reported a decline in memory, 2818 of 5879 (47.4%) in learning abilities, and 1828 of 5888 (30.7%) in concentration in 2022. Physical activity was the strongest predictor of SCD in a 5-year interval, with an odds ratio of 0.76 (95% Bayesian credible interval 0.59-0.99) for physically active compared to inactive participants. Alcohol consumption showed a U-shaped relationship with SCD. Other risk factors had minor effects. Moreover, our validation confirmed that SCD has prognostic value for diagnosed dementia, with individuals reporting memory decline being over 3 times more likely to have dementia in 2017 (age 57-77 years), and this risk increased to more than 5 times by 2022 (age 62-82 years). The receiver operating characteristic curve analysis further supported the predictive validity of our outcome, with an area under the curve of 0.78 in 2017 and 0.75 in 2022. CONCLUSIONS A new risk score tool was developed that enables individuals to inspect their risk profiles and explore potential targets for interventions and their estimated contributions to later SCD. Using AI-driven predictive modeling, the tool can aid health care professionals in providing personalized prevention strategies. A dynamic decision heatmap was presented as a communication tool to be used at health care consultations. Our findings suggest that early identification of individuals with SCD could improve targeted intervention strategies for reducing dementia risk. Future research should explore the integration of AI-based risk prediction models into clinical workflows and assess their effectiveness in guiding lifestyle interventions to mitigate SCD and dementia.

20 October 2026 in Archives of Public Health
Verified
Journal Article
Open access
PDF file
NONiko Oikarinen
Niko Oikarinen
AEAntti Etholén
Antti Etholén
LJLari Järvensivu
Lari Järvensivu
VPVille Päivärinne
Ville Päivärinne
Tea LallukkaTea Lallukka
Tea Lallukka
OROssi Rahkonen
Ossi Rahkonen
Background: Dementia represents a major public health challenge due to its increasing prevalence. Limited research has explored how patterns of leisure-time physical activity (LTPA) vary across occupational classes and how these patterns are associated with cognition. This study aimed to examine (1) trajectories of LTPA in low and high occupational classes before and after statutory retirement and (2) the associations between trajectory membership and subjective cognitive decline (SCD) after retirement. Methods: We used repeated survey data from the Helsinki Health Study, a longitudinal cohort at Phase 1 focused on employees of the City of Helsinki, Finland, five Phases (2000–2022, N = 8960). The final analytic sample included 4059 participants, with a mean age of 51.50 years at Phase 1. LTPA was quantified as weekly metabolic equivalent hours (MET-h). SCD was assessed using questions on memory, learning ability, and concentration, classified as “Poor” or “Good”. Occupational class at Phase 1 was categorized as “Low” (e.g., manual employees) or “High” (e.g., professionals). Trajectories of LTPA were identified using group-based trajectory modeling. Binomial logistic regression was used to assess the association between trajectory membership and SCD. Results: Distinct LTPA trajectories representing patterns of LTPA levels and change over time were identified. These appeared broadly similar across low and high occupational classes. Most trajectories were stable and characterized by relatively high levels of LTPA before and after statutory retirement. A decline in the highest LTPA trajectory was found among participants with low occupational class. Results from the binomial logistic regression analyses showed that participants in lower LTPA trajectories had a higher likelihood of SCD in both classes. Notably, the lowest trajectory groups within both occupational classes were associated with poorer learning, with Average Marginal Effects (AME) of 22 percentage points [95% CI: 14–30] in low class and 18 percentage points [95% CI: 11–25] in high class. Conclusion: Our results highlight that higher levels of LTPA are associated with better cognitive health during the retirement transition in both low and high occupational class groups.