Researchers found that analyzing social group structures in addition to data from wearable fitness devices can provide a more comprehensive account of health.
Using a machine learning model with the combination of social network structure and data from the common wearable fitness tracker Fitbit, the model achieved a 65% improvement in predicting happiness; 54% improvement in predicting one’s self-assessed health prediction; 55% improvement in predicting positive attitude; and 38% improvement in predicting success.
The study suggests that without information about people’s social networks, there is an incomplete view of an individual’s wellness state. The study, supported by NHLBI, appeared in the Public Library of Science journal, PLoS One.
Media Coverage
|
University of Notre Dame