Participants will be asked to fill out an online questionnaire about their demographics information and all 42 items from the Depression Anxiety Stress Scale (DASS-42). A series of machine learning techniques will be applied to the dataset to develop a shortened assessment using the most important demographics and DASS-42 items from the original questionnaire, to predict depression levels indicated by DASS-42.
Clinical depression affects 5-10% of the world population each year and is a serious mental health issue globally. There are many traditional psychological scales that assess levels of depression in adults, where their items are often redundant in the information they carry, and their scoring is not necessarily linear to the item scores. Thus, machine learning techniques can help find the redundancy in the items, as well as the nonlinear relationship between the item scores and the final prediction. Using the Depression Anxiety Stress Scale 42 (DASS-42) as the basis, participants will be asked to fill out an online questionnaire about their demographics information (age, gender, country of residence, race, etc.) and all 42 items of DASS-42 to provide a dataset for this study. Feature selection techniques such as MRMR and Gini feature importance were applied to identify the most important features in the dataset. Then, using machine learning methods such as Logistic Regression, XGBoost, and Ensemble models, models will be fitted on the most important features to develop a shortened depression scale (7-9 items consisting of demographics items and DASS items) that accurately predicted the levels of depression (as measured by the AUC, ROC and F1 scores.
Study Type
OBSERVATIONAL
Enrollment
39,000
University of Toronto
Toronto, Ontario, Canada
Rapid Depression Assessment Tool based on Depression Anxiety Stress Scale 42
Participants filled out an online questionnaire about their demographic information (age, sex, and ethnicity) and all 42 items from the Depression Anxiety Stress Scale (DASS-42). Each item consists of a 4-point Likert scale from 0 to 3, where 0 means "Did not apply to me at all" and 3 means "Applied to me very much, or most of the time". The depression score is the sum of scores for the items in the depression sub-scale. A higher score indicates a more severe level of depression symptoms. Machine learning techniques were used to develop a shortened assessment (Rapid Depression Assessment Tool) using demographics and 5 DASS-42 items from the original questionnaire, to predict severity levels of depression indicated by DASS-42. The assessment tool calculates the likelihood of moderate depression symptoms and severe depression symptoms given the responses from each item (ranging from 0 to 3). The data was collected and aggregated through a public website.
Time frame: All participants completed the same assessments, which took 10-15 minutes
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.