Frequency and machine learning predictors of severe depressive symptoms and suicidal ideation among university students.

AIMS: Prospective studies on the mental health of university students highlighted a major concern. Specifically, young adults in academia are affected by markedly worse mental health status than their peers or adults in other vocations. This situation predisposes to exacerbated disability-adjusted life-years. METHODS: We enroled 1,388 students at the baseline, 557 of whom completed follow-up after 6 months, incorporating their demographic information and self-report questionnaires on depressive, anxiety and obsessive-compulsive symptoms. We applied multiple regression modelling to determine associations - at baseline - between demographic factors and self-reported mental health measures and supervised machine learning algorithms to predict the risk of poorer mental health at follow-up, by leveraging the demographic and clinical information collected at baseline. RESULTS: Approximately one out of five students reported severe depressive symptoms and/or suicidal ideation. An association of economic worry with depression was evidenced both at baseline (when high-frequency worry odds ratio = 3.11 [1.88-5.15]) and during follow-up. The random forest algorithm exhibited high accuracy in predicting the students who maintained well-being (balanced accuracy = 0.85) or absence of suicidal ideation but low accuracy for those whose symptoms worsened (balanced accuracy = 0.49). The most important features used for prediction were the cognitive and somatic symptoms of depression. However, while the negative predictive value of worsened symptoms after 6 months of enrolment was 0.89, the positive predictive value is basically null. CONCLUSIONS: Students' severe mental health problems reached worrying levels, and demographic factors were poor predictors of mental health outcomes. Further research including people with lived experience will be crucial to better assess students' mental health needs and improve the predictive outcome for those most at risk of worsening symptoms.

Students' mental health problems before, during, and after COVID-19 lockdown in Italy.

The lockdown due to the coronavirus pandemic may have exacerbated mental health problems. To what degree mental health may be affected by social isolation is still poorly known. We collected prospective data on students' mental health in two instances: (i) in October and December 2019, and (ii) 6 months later, in April 2020 amidst the COVID-19 lockdown in Italy and in mid-May/June 2020, after the lifting of lockdown. A total of 358 Italian students aged 18-30 completed socio-demographic questionnaires and the Beck Depression Inventory - 2 (BDI-2), the Beck Anxiety Inventory (BAI), the Obsessive-Compulsive Inventory - Revised (OCI-R), the Eating Habits Questionnaire (EHQ), and the Eating Disorder Inventory-3 (EDI-3). We applied multiple regression models to evince any changes in the aforementioned questionnaire scores during and after lockdown with respect to the scores before lockdown. Students reported on average worse depressive symptoms during lockdown than 6 months before isolation (median increase in the BDI-2 score +2; IQR = -3, 6; ß = 0.09 ± 0.03, p = 0.005), with students without any established diagnosis of psychopathology being affected the most. The regression models predict that 86.2% (IQR = 67.9, 91.4%) of students would not experience a clinically significant worsening of symptoms, while approximately 6% of our target population could develop more severe depressive symptoms. This study supports the view that depressive symptomatology may be aggravated during lockdown, but also highlights that after the lifting of lockdown any changes quickly vanished, as the BDI-2 scores were not different from the ones reported before lockdown.