Search

BackgroundMachine learning modeling can provide valuable support in different areas of mental health, because it enables to make rapid predictions and therefore support the decision making, based on valuable data. However, few studies have applied this method to predict symptoms’ worsening, based on sociodemographic, contextual, and clinical data. Thus, we applied machine learning techniques to identify predictors of symptomatologic changes in a Spanish cohort of OCD patients during the initial phase of the COVID-19 pandemic.Methods127 OCD patients were assessed using the Yale–Brown Obsessive-Compulsive Scale (Y-BOCS) and a structured clinical interview during the COVID-19 pandemic. Machine learning models for classification (LDA and SVM) and regression (linear regression and SVR) were constructed to predict each symptom based on patient’s sociodemographic, clinical and contextual information.ResultsA Y-BOCS score prediction model was generated with 100% reliability at a score threshold of ± 6. Reliability of 100% was reached for obsessions and/or compulsions related to COVID-19. Symptoms of anxiety and depression were predicted with less reliability (correlation R of 0.58 and 0.68, respectively). The suicidal thoughts are predicted with a sensitivity of 79% and specificity of 88%. The best results are achieved by SVM and SVR.ConclusionOur findings reveal that sociodemographic and clinical data can be used to predict changes in OCD symptomatology. Machine learning may be valuable tool for helping clinicians to rapidly identify patients at higher risk and therefore provide optimized care, especially in future pandemics. However, further validation of these models is required to ensure greater reliability of the algorithms for clinical implementation to specific objectives of interest.

Background: Twenty years after the first use of Deep Brain Stimulation (DBS) in obsessive-compulsive disorder (OCD), our knowledge of the long-term effects of this therapeutic option remains very limited. Objective: Our study aims to assess the long-term effectiveness and tolerability of DBS in OCD patients and to look for possible predictors of long-term response to this treatment. Methods: We studied the course of 25 patients with severe refractory OCD treated with DBS over an average follow-up period of 6.4 years (±3.2) and compared them with a control group of 25 patients with severe OCD who refused DBS and maintained their usual treatment. DBS was implanted at the ventral anterior limb of the internal capsule and nucleus accumbens (vALIC-Nacc) in the first six patients and later at the bed nucleus of stria terminalis (BNST) in the rest of patients. Main outcome was change in Yale-Brown Obsessive-Compulsive Scale (Y-BOCS) score between the two groups assessed using mixed models. Secondary effectiveness outcomes included Hamilton Depression Rating Scale (HDRS) and Global Assessment of Functioning (GAF) scores. Results: Obsessive symptoms fell by 42.5% (Y-BOCS score) in patients treated with DBS and by 4.8% in the control group. Fifty-six per cent of DBS-treated patients could be considered responders at the end of follow-up and 28% partial responders. Two patients among those who rejected DBS were partial responders (8%), but none of the non-DBS group achieved criteria for complete response. HDRS and GAF scores improved significantly in 39.2% and 43.6% among DBS-treated patients, while did not significantly change in those who rejected DBS (improvement limited to 6.2% in HDRS and 4.2% in GAF scores). No statistically significant predictors of response were found. Mixed models presented very large comparative effect sizes for DBS (4.29 for Y-BOCS, 1.15 for HDRS and 2.54 for GAF). Few patients experienced adverse effects and most of these effects were mild and transitory. Conclusions: The long-term comparative effectiveness and safety of DBS confirm it as a valid option for the treatment of severe refractory OCD.

Relationships among childhood maltreatment (CM), hypothalamic-pituitary-adrenal (HPA) axis disturbances, major depressive disorder (MDD), poor functionality, and lower quality of life (QoL) in adulthood have been described. We aimed to study the roles of the remission status of depression and HPA axis function in the relationships between CM and functionality and QoL. Ninety-seven patients with MDD and 97 healthy controls were included. The cortisol awakening response, cortisol suppression ratio in the dexamethasone suppression test, and diurnal cortisol slope were assessed. Participants completed measures of psychopathology, CM, functionality, and QoL. Multiple linear regression analyses were performed to study the relationships between CM and functionality and QoL. Only non-remitted MDD patients showed lower functionality and QoL than controls, indicating that depressive symptoms may partly predict functionality and QoL. Cortisol measures did not differ between remitted and non-remitted patients. Although neither HPA axis measures nor depression remission status were consistently associated with functionality or QoL, these factors moderated the effects of CM on functionality and QoL. In conclusion, subtle neurobiological dysfunctions in stress-related systems could help to explain diminished functionality and QoL in individuals with CM and MDD and contribute to the persistence of these impairments even after the remission of depressive symptoms.