Back

Unraveling the factors associated with digital health intervention uptake

Ruotsalainen, I.; Valtanen, M.; Karsama, R.; Umer, A.; Liedes, H.; Parikka, S.; Lundqvist, A.; Aittola, K.; Manninen, S.; Pihlajamaki, J.; Vuorinen, A.-L.; Lindstrom, J.

2024-03-19 health informatics
10.1101/2024.03.18.24304467 medRxiv
Show abstract

For preventing chronic diseases, reducing modifiable lifestyle risk factors is crucial. Digital health interventions (DHIs) hold promise for reaching large population groups, but raise health equity concerns. A subgroup (n=6978) of 20 to 74-year-old participants of the population-based Healthy Finland survey were offered an opportunity to start using a web-based DHI, aiming to support adoption of healthy lifestyle habits. We used adjusted logistic regression models to identify significant predictors of DHI uptake. Women (adjusted odds ratio [aOR] 1.69, 95% CI 1.49-1.93), middle-aged individuals (1.47, 1.21-1.79), and those with higher income (aORs between 1.76-1.97) and education (1.10, 1.08-1.12) had higher odds of DHI uptake. Moreover, healthier lifestyle indicated by better diet quality (1.07, 1.04- 1.10), less frequent or non-smoking (aORs between 1.59-2.29), sleep (0.58, 0.37-0.86), higher functional capacity (1.06, 1.02-1.11), and good overall current health (1.46, 1.15- 1.89) associated with increased likelihood of DHI uptake. Lastly, individuals with better internet connections, higher competence to use e-services (aORs between 2.00-4.10), low concerns about data security (aORs between 1.37-1.76), stronger belief in benefits of digital services (1.04, 1.02-1.05), and reporting to use e-services (aORs between 2.48-6.08) had higher odds of uptake. Our findings indicate that those with higher socioeconomic status, better health and healthier lifestyle are more likely to take up DHI. Our research also highlights the impact of digital literacy and positive attitudes towards online services in adopting DHIs. These insights will be valuable in shaping strategies for future DHI initiatives.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.