A very short Symptom Checklist-90-R version for routine outcome monitoring in psychotherapy; The SCL-3/7

Unraveling the distinction between depression and anxiety: A machine learning exploration of causal relationships

OBJECTIVE

Depression and anxiety, prevalent coexisting mood disorders, pose a clinical challenge in accurate differentiation, hindering effective healthcare interventions. This research addressed this gap by employing a streamlined Symptom Checklist 90 (SCL-90) designed to minimize patient response burden. Utilizing machine learning algorithms, the study sought to construct classification models capable of distinguishing between depression and anxiety.

METHODS

The study included 4262 individuals currently experiencing depression alone (n = 2998), anxiety alone (n = 716), or both depression and anxiety (n = 548). Counterfactual diagnosis was used to construct a causal network on the dataset. Employing a causal network, the SCL-90 was simplified. Items that have causality with only depression, only anxiety and both depression and anxiety were selected, and these streamlined items served as input features for four distinct machine learning algorithms, facilitating the creation of classification models for distinguishing depression and anxiety.

RESULTS

Cross-validation demonstrated the performance of the classification models with the following metrics: (1) K-nearest neighbors (AUC = 0.924, Acc = 92.81 %); (2) support vector machine (AUC = 0.937, Acc = 94.38 %); (3) random forest (AUC = 0.918, Acc = 94.38 %); and (4) adaptive boosting (AUC = 0.882, Acc = 94.38 %). Notably, the support vector machine excelled, with the highest AUC and superior accuracy.

CONCLUSION

Incorporating the simplified SCL-90 and machine learning presents a promising, efficient, and cost-effective tool for the precise identification of depression and anxiety.

The use of SCL-k-9 to measure general psychopathology in women and men with skin conditions

Objectives

To measure general psychopathology in dermatologic outpatients using the Symptom-Checklist-K-9 (SCL-K-9); to investigate whether the SCL-K-9 is able to categorize patients with and without significant non-psychotic disorders; and to perform a single-item analysis of the SCL-K-9, with a focus on gender differences.

Methods

Cross-sectional study on consecutive dermatological patients. We used two self-administered questionnaires to assess general psychopathology symptoms: General Health Questionnaire-12 (GHQ-12) and SCL-K-9. Sociodemographic information was collected with standardized forms. The performance of the SCL-K-9 in classifying patients according to their current emotional distress severity was assessed using a ROC procedure. Finally, we measured differences in scores obtained among women and men in SCL-K-9 single items.

Results

A total of 292 patients were studied (71.2% women). We observed statistically significant differences in SCL-K-9 total mean scores and in most single items among genders. We found that it would be more appropriate to use gender-specific cut-offs when using SCL-K-9 to screen dermatological patients for general psychopathology.

Conclusion

The SCL-K-9, with its compact format could provide, in a short time, a wide range of information related to critical areas that challenge the mental health of patients with skin diseases.