Reducing worry and subjective health complaints: A randomized trial of an internet-delivered worry postponement intervention

Applying ensemble machine learning models to predict individual response to a digitally delivered worry postponement intervention

OBJECTIVE

Generalized anxiety disorder (GAD) is a prevalent mental health disorder that often goes untreated. A core aspect of GAD is worry, which is associated with negative health outcomes, accentuating a need for simple treatments for worry. The present study leveraged pretreatment individual differences to predict personalized treatment response to a digital intervention.

METHODS

Linear mixed-effect models were used to model changes in daytime and nighttime worry duration and frequency for 163 participants who completed a six-day worry postponement intervention. Ensemble-based machine learning regression and classification models were implemented to predict changes in worry across the intervention. Model feature importance was derived using SHapley Additive exPlanation (SHAP).

RESULTS

Moderate predictive performance was obtained for predicting changes in daytime worry duration (test r2 = 0.221, AUC = 0.77) and nighttime worry frequency (test r2 = 0.164, AUC = 0.72), while poor predictive performance was obtained for nighttime worry duration and daytime worry frequency. Baseline levels of worry and subjective health complaints were most important in driving model predictions.

LIMITATIONS

A complete-case analysis was leveraged to analyze the present data, which was collected from participants that were Dutch and majority female.

CONCLUSIONS

This study suggests that treatment response to a digital intervention for GAD can be accurately predicted using baseline characteristics. Particularly, this worry postponement intervention may be most beneficial for individuals with high baseline worry but fewer subjective health complaints. The present findings highlight the complexities of and need for further research into daily worry dynamics and the personalizable utility of digital interventions.

A brief scale of pathological worry that everyone already has

Worry is a central process in a wide range of psychopathological and somatic conditions. Three studies (N = 856) were used to test whether a subscale composed of five items of the most commonly used trait anxiety questionnaire, Spielberger’s State Trait Anxiety Inventory-Trait version (STAI-T), is appropriate to measure worry. Results showed that the subscale, named the Brief Worry Scale (BWS), had excellent internal consistency and temporal stability. Convergent and divergent validity were supported by correlation analyses using worry questionnaires and measures of anxious arousal and depression. The BWS was a particularly good predictor of the pathogenic aspects of worry, including worry perseveration in daily life (study 1), measures of clinical worry (study 2) and the uncontrollability of experimentally induced worry (study 3). Taken together, these studies demonstrate that the BWS might be a valuable scale for pathological worry, for which many researchers already have data.

Application of a worry reduction intervention in a medically unexplained symptoms-analogue student-sample

OBJECTIVE

Worry is an important perpetuating factor of Medically Unexplained Symptoms (MUS). Former research has shown that a worry postponement instruction is effective in reducing Subjective Health Complaints (SHC) in non-clinical samples. This study aimed to (1) replicate these findings in a MUS-analogue student-sample and (2) assess alexithymia as a moderator.

DESIGN

The current study had an experimental design with two waves of data collection: pre- and post-intervention.

MAIN OUTCOME MEASURES

A MUS-analogue student-sample consisting of 114 undergraduate students with high self-reported health worry and a minimum of two doctor visits in the previous year with no current diagnosis for a (chronic or acute) disease were instructed to register their worry frequency and duration eight times per day via an experience sampling-application on their smartphones. The intervention group additionally postponed their worries to a 30-minute period in the evening. SHC were assessed pre- and post-intervention.

RESULTS

The intervention did not have an effect on worry or SHC. Alexithymia did not moderate this effect (p's > .05).

CONCLUSION

Our study did not find evidence for the effectiveness of the worry reduction intervention on SHC in a MUS-analogue student-sample. This finding contributes to several previous studies that have found mixed evidence for the effectiveness of the worry reduction intervention on SHC and suggests that the worry intervention may not be effective in all cases.