| Popis: |
Introduction: Machine learning could play a key role in the development of new interventions for bulimia nervosa (BN) and alcohol use disorder (AUD) as it can be used to predict and identify specific triggers of binge behavior in daily life. Therefore, this study has the following two aims. First, to evaluate person-specific and pooled prediction models for binge eating (BE), alcohol use and binge drinking (BD) in daily life. Second, to identify important predictors for these behaviors. Methods: A total of 120 patients (BN: 50; AUD: 51; BN/AUD: 19) participated in an experience sampling study, where over a period of 12 months they reported on their eating and drinking behaviors as well as on several other emotional, behavioral and contextual factors in daily life. The study had a burst-measurement design, where assessments occurred 8 times a day on Thursdays, Fridays, and Saturdays in 7 bursts of 3 weeks. Afterwards, person-specific and pooled models were fit with elastic net regularized regression and evaluated with cross-validation. From these models, the variables with the 10% highest estimates were identified. Results: The person-specific models had a median AUC of 0.61, 0.80, and 0.85 for BE, alcohol use and BD respectively, while the pooled models had a median AUC of 0.70, 0.90, and 0.93. The most important predictors across the different behaviors were craving, and time of day. However, predictors concerning social context and affect differed between BE, alcohol use and BD.Conclusion: This study shows that BE, alcohol use and BD can be predicted in daily life, but that pooled models outperformed person-specific models and that models for alcohol use and BD outperformed those for BE. Future studies should investigate how model performance can be improved and how these models can be used to deliver interventions in daily life. |
