Background: In longitudinal research, switching between diagnoses should be considered when examining patients with depression and anxiety. We investigated course trajectories of affective... Show moreBackground: In longitudinal research, switching between diagnoses should be considered when examining patients with depression and anxiety. We investigated course trajectories of affective disorders over a nine-year period, comparing a categorical approach using diagnoses to a dimensional approach using symptom severity.Method: Patients with a current depressive and/or anxiety disorder at baseline (N = 1701) were selected from the Netherlands Study of Depression and Anxiety (NESDA). Using psychiatric diagnoses, we described 'consistently recovered,' 'intermittently recovered,' 'intermittently recurrent', and 'consistently chronic' at two-, four-, six-, and nine-year follow-up. Additionally, latent class growth analysis (LCGA) using depressive, anxiety, fear, and worry symptom severity scores was used to identify distinct classes.Results: Considering the categorical approach, 8.5% were chronic, 32.9% were intermittently recurrent, 37.6% were intermittently recovered, and 21.0% remained consistently recovered from any affective disorder at nine-year follow-up. In the dimensional approach, 66.6% were chronic, 25.9% showed partial recovery, and 7.6% had recovered.Limitations: 30.6% of patients were lost to follow-up. Diagnoses were rated by the interviewer and questionnaires were completed by the participant.Conclusions: Using diagnoses alone as discrete categories to describe clinical course fails to fully capture the persistence of affective symptoms that were observed when using a dimensional approach. The enduring, fluctuating presence of sub-threshold affective symptoms likely predisposes patients to frequent relapse. The commonness of subthreshold symptoms and their adverse impact on long-term prognoses deserve continuous clinical attention in mental health care as well further research. Show less
Background: Predicting the onset and course of mood and anxiety disorders is of clinical importance but remains difficult. We compared the predictive performances of traditional logistic regression... Show moreBackground: Predicting the onset and course of mood and anxiety disorders is of clinical importance but remains difficult. We compared the predictive performances of traditional logistic regression, basic probabilistic machine learning (ML) methods, and automated ML (Auto-sklearn).Methods: Data were derived from the Netherlands Study of Depression and Anxiety. We compared how well multinomial logistic regression, a naïve Bayes classifier, and Auto-sklearn predicted depression and anxiety diagnoses at a 2-, 4-, 6-, and 9-year follow up, operationalized as binary or categorical variables. Predictor sets included demographic and self-report data, which can be easily collected in clinical practice at two initial time points (baseline and 1-year follow up).Results: At baseline, participants were 42.2 years old, 66.5% were women, and 53.6% had a current mood or anxiety disorder. The three methods were similarly successful in predicting (mental) health status, with correct predictions for up to 79% (95% CI 75?81%). However, Auto-sklearn was superior when assessing a more complex dataset with individual item scores.Conclusions: Automated ML methods added only limited value, compared to traditional data modelling when predicting the onset and course of depression and anxiety. However, they hold potential for automatization and may be better suited for complex datasets. Show less
