Silvia Grazioli

Objectives: Personality disorders (PD) are often considered a negative prognostic factor for cognitive behavioural therapy (CBT) in anxiety and depression, yet evidence from real‐world settings with rigorous diagnostic assessment remains limited. This study examined whether PD diagnosis influences CBT outcomes using data from inTHERAPY, an Italian CBT service integrating systematic outcome monitoring with structured diagnostic assessment (SCID‐5). Methods: Patients receiving CBT for anxiety and/or depression were classified according to the presence or absence of a PD and assessed on anxiety, depression, and psychosocial functioning. Treatment effectiveness was evaluated through symptom change, reliable and clinically significant improvement (RCSI), and recovery rates. Mixed‐effects growth curve models examined outcome trajectories, and regression analyses tested the role of PD diagnosis, treatment exposure, and dropout status. Results: CBT was associated with a RCSI rate of 50%, with moderate‐to‐large pre‐post effect sizes for anxiety ( d = .77), depression ( d = .76), and functioning ( d = .63). Although patients with PD presented with higher baseline severity and lower recovery rates, PD diagnosis did not independently predict outcomes when baseline severity, dropout status, and number of sessions were controlled for. Symptom trajectories were nonlinear and largely comparable across groups. Notably, patients with PD who dropped out late showed greater functional impairment at discharge than late dropouts without PD. Conclusions: These findings suggest that standard disorder‐specific CBT is effective for patients with comorbid PD in real‐world practice. Apparent poorer outcomes primarily reflect greater initial severity, underscoring the importance of adequate treatment duration and strategies to prevent late dropout.

The current progressive adoption of online platforms and web-based interventions, within the context of Cognitive Behavioral Therapy (CBT) services, offers a novel opportunity to scale evidence-based psychotherapy. In the present work, we depict the development of a web and native application within the Italian landscape, GRETA (Graphic Robotic Engine for Therapy Automation). GRETA provides the following functions: (a) Management of therapy appointments and payments; (b) Clinical data, therapy progress, and sessions summary between professionals; (c) Production of the medical report and notes for external institutions; (d) Homework, materials, psychometric measures, progress reports, and therapy notes; (e) Systematic monitoring of the therapeutic process and outcomes; (f) Ensuring confidentiality, security, and integrity of patient information; (g) Collection, aggregation, and analysis of anonymized patient data through statistical reports and graphical dashboards. Beyond the technological implementation, this study also assesses the effectiveness of therapy delivered through GRETA. Pre-post treatment comparisons were conducted on a sample of 442 patients discharged for any reason by the CBT service, categorized into three diagnostic groups: anxiety disorder, depressive disorder, and comorbid anxiety and depressive disorder. Results revealed significant improvements in symptom severity and functional adjustment across all groups. Future developments of GRETA will involve integrating Artificial Intelligence-based features, such as predictions of clinical outcomes.

This cross-sectional study aims to identify clusters of internalizing and externalizing traits during adolescence using a bottom-up approach. The second aim is to investigate whether the different clusters differ by environmental risk factors and specific epigenetic profiles. A total of 205 adolescents, who had been referred for psychopathology in childhood, were recruited. Behavioral problems were assessed using the Child Behavior Checklist/6–18 (CBCL). Different clusters of psychopathological profiles were analyzed using a Finite mixture model. Differences in environmental risk factors and epigenetic profiles were tested with χ²-tests and Bonferroni-corrected t-tests. Two clusters were identified: a LOW cluster (51% of the sample), characterized by the presence of subclinical mean scores in both internalizing and externalizing problems, and a HIGH cluster (49% of the sample), characterized by high mean scores in both domains. The HIGH cluster had a significantly greater number of perinatal complications and changes in methylation of specific CpG sites of Brain-derived neurotrophic factor, Insulin-like growth factor-2, and Oxytocin receptor, whereas no difference was found for FK506-binding protein 5. Our results confirm the existence of a strong association between early adverse events, DNA methylation, and the presence of behavioral problems and psychopathological traits in adolescence.

Background: There is evidence that the tendency to adopt a peculiar pattern of causal inference, known as attributional style, is likely related to specific patterns of psychopathology among youth. Objective: This study aims to assess preliminary psychometric properties of the Italian Children’s Attributional Style Questionnaire-Revised (CASQ-R) and to explore the presence of any subgroups of children and early adolescents from the general population who might exhibit internally homogeneous and externally heterogeneous attributional styles through latent class analysis, delving into the potential sociodemographic, namely age and gender, and clinical differences among the identified classes of attributional styles. Method: A sample of 337 children (11.29 ± 1.76 years old, 169 females, and 168 males) was recruited and their attributional styles and depressive and anxious symptoms were analyzed. Results: Two distinct classes were defined using the CASQ-R items in a latent class analysis (LCA). In particular, high levels of depressive (Kruskal–Wallis chi-squared = 9.37, df = 1, Bonferroni-adjusted p = 0.002) and school phobia (Kruskal–Wallis chi-squared = 7.17 df = 1, Bonferroni-adjusted p = 0.037) symptoms were reported by children showing an internal, global and stable attributional style for negative events and an external, specific and unstable attributional style for positive events. Conversely, low levels of depressive and school phobia symptoms were reported by children showing the opposite attributional style. Conclusions: The identified classes shed light on distinct patterns associated with depressive and anxious symptoms, offering potential insights for targeted interventions.

Background: Diagnosis of child and adolescent psychopathologies involves a multifaceted approach, integrating clinical observations, behavioral assessments, medical history, cognitive testing, and familial context information. Digital technologies, especially internet-based platforms for administering caregiver-rated questionnaires, are increasingly used in this field, particularly during the screening phase. The ascent of digital platforms for data collection has propelled advanced psychopathology classification methods such as supervised machine learning (ML) into the forefront of both research and clinical environments. This shift, recently called psycho-informatics, has been facilitated by gradually incorporating computational devices into clinical workflows. However, an actual integration between telemedicine and the ML approach has yet to be fulfilled. Objective: Under these premises, exploring the potential of ML applications for analyzing digitally collected data may have significant implications for supporting the clinical practice of diagnosing early psychopathology. The purpose of this study was, therefore, to exploit ML models for the classification of attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) using internet-based parent-reported socio-anamnestic data, aiming at obtaining accurate predictive models for new help-seeking families. Methods: In this retrospective, single-center observational study, socio-anamnestic data were collected from 1688 children and adolescents referred for suspected neurodevelopmental conditions. The data included sociodemographic, clinical, environmental, and developmental factors, collected remotely through the first Italian internet-based screening tool for neurodevelopmental disorders, the Medea Information and Clinical Assessment On-Line (MedicalBIT). Random forest (RF), decision tree, and logistic regression models were developed and evaluated using classification accuracy, sensitivity, specificity, and importance of independent variables. Results: The RF model demonstrated robust accuracy, achieving 84% (95% CI 82-85; P<.001) for ADHD and 86% (95% CI 84-87; P<.001) for ASD classifications. Sensitivities were also high, with 93% for ADHD and 95% for ASD. In contrast, the DT and LR models exhibited lower accuracy (DT 74%, 95% CI 71-77; P<.001 for ADHD; DT 79%, 95% CI 77-82; P<.001 for ASD; LR 61%, 95% CI 57-64; P<.001 for ADHD; LR 63%, 95% CI 60-67; P<.001 for ASD) and sensitivities (DT: 82% for ADHD and 88% for ASD; LR: 62% for ADHD and 68% for ASD). The independent variables considered for classification differed in importance between the 2 models, reflecting the distinct characteristics of the 3 ML approaches. Conclusions: This study highlights the potential of ML models, particularly RF, in enhancing the diagnostic process of child and adolescent psychopathology. Altogether, the current findings underscore the significance of leveraging digital platforms and computational techniques in the diagnostic process. While interpretability remains crucial, the developed approach might provide valuable screening tools for clinicians, highlighting the significance of embedding computational techniques in the diagnostic process.

The utilization of non-invasive neurostimulation techniques, such as transcranial magnetic stimulation (TMS), is increasingly prevalent in psychiatry due to their efficacy and safety. Although the precise therapeutic mechanisms remain partially unclear, repetitive TMS, particularly high-frequency stimulation, may enhance cognitive functions, contributing to therapeutic benefits. This within-subjects study examined the impact of TMS on cognitive and symptomatic outcomes in patients with obsessive–compulsive disorder (OCD), substance use disorder (SUD), and major depressive disorder (MDD). A total of 44 patients underwent cognitive tests and symptom assessments before and after an intensive four-week TMS treatment phase, followed by a four-week maintenance phase. Cognitive assessments included Raven’s matrices, verbal fluency, and digit span tests, while symptom severity was measured using the Italian version of the SCL-90-R. Decision-making performance was also evaluated by administering a delay discounting (DD) test. Principal component analysis was used to generate a dimensional characterization of subjects along cognitive and symptom-related axes before and after treatment. The results indicated that TMS significantly improved symptom scores, but no significant cognitive enhancement was observed. Statistical analysis based on linear mixed-effects models confirmed these findings, showing a significant fixed effect of TMS treatment on symptoms but not on cognitive performance. DD metrics remained unchanged. These findings suggest that while TMS effectively alleviates clinical symptoms, it does not produce consistent or appreciable enhancement of cognitive functions in these protocols. This study highlights the need for more personalized and combined therapeutic approaches to maximize the benefits of TMS, potentially incorporating cognitive enhancement strategies. Future studies will be useful to explore whether the results we obtained are valid for other pathologies, cognitive tests, and stimulation protocols.

There is evidence that the tendency to adopt a particular pattern of causal inference, known as attributional style, is likely to be associated with specific pattern of psychopathology among youth. This study aims to assess preliminary psychometric properties of the Italian Children’s Attributional Style Questionnaire-Revised (CASQ-R) and to explore the presence of any subgroups of children and early adolescents from the general population who might exhibit internally homogeneous and externally heterogeneous attributional styles, through cluster analyses, delving also potential sociodemographic and clinical differences among the identified clusters of attributional styles. A sample of 337 children was recruited and their attributional styles and depressive symptoms were analyzed. Four distinct clusters emerged using the six CASQ-R subscales in a multivariate finite mixture model. In particular, high levels of depressive symptoms were reported by children showing high scores in all the negative attributional subscales (globality, internality and stability) and medium scores in all the positive attributional subscales. Conversely, low levels of depressive symptoms were reported by children showing medium-to-high scores in the positive attributional subscales and low-to-medium scores in the negative attributional subscales. The identified clusters shed light on distinct patterns associated with depressive symptoms, offering potential insights for targeted interventions.

BACKGROUND Diagnosis of child and adolescent psychopathologies involves a multifaceted approach, integrating clinical observations, behavioral assessments, medical history, cognitive testing, and familial context information. Digital technologies, especially internet-based platforms for administering caregiver-rated questionnaires, are increasingly used in this field, particularly during the screening phase. The ascent of digital platforms for data collection has propelled advanced psychopathology classification methods such as supervised machine learning (ML) into the forefront of both research and clinical environments. This shift, recently called psycho-informatics, has been facilitated by gradually incorporating computational devices into clinical workflows. However, an actual integration between telemedicine and the ML approach has yet to be fulfilled. OBJECTIVE Under these premises, exploring the potential of ML applications for analyzing digitally collected data may have significant implications for supporting the clinical practice of diagnosing early psychopathology. The purpose of this study was, therefore, to exploit ML models for the classification of attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) using internet-based parent-reported socio-anamnestic data, aiming at obtaining accurate predictive models for new help-seeking families. METHODS In this retrospective, single-center observational study, socio-anamnestic data were collected from 1688 children and adolescents referred for suspected neurodevelopmental conditions. The data included sociodemographic, clinical, environmental, and developmental factors, collected remotely through the first Italian internet-based screening tool for neurodevelopmental disorders, the Medea Information and Clinical Assessment On-Line (MedicalBIT). Random forest (RF), decision tree, and logistic regression models were developed and evaluated using classification accuracy, sensitivity, specificity, and importance of independent variables. RESULTS The RF model demonstrated robust accuracy, achieving 84% (95% CI 82-85; P<.001) for ADHD and 86% (95% CI 84-87; P<.001) for ASD classifications. Sensitivities were also high, with 93% for ADHD and 95% for ASD. In contrast, the DT and LR models exhibited lower accuracy (DT 74%, 95% CI 71-77; P<.001 for ADHD; DT 79%, 95% CI 77-82; P<.001 for ASD; LR 61%, 95% CI 57-64; P<.001 for ADHD; LR 63%, 95% CI 60-67; P<.001 for ASD) and sensitivities (DT: 82% for ADHD and 88% for ASD; LR: 62% for ADHD and 68% for ASD). The independent variables considered for classification differed in importance between the 2 models, reflecting the distinct characteristics of the 3 ML approaches. CONCLUSIONS This study highlights the potential of ML models, particularly RF, in enhancing the diagnostic process of child and adolescent psychopathology. Altogether, the current findings underscore the significance of leveraging digital platforms and computational techniques in the diagnostic process. While interpretability remains crucial, the developed approach might provide valuable screening tools for clinicians, highlighting the significance of embedding computational techniques in the diagnostic process.

Recently, there has been an increase in telemedicine applied to child neuropsychiatry, such as the use of online platforms to collect remotely case histories and demographic and behavioral information. In the present proof-of-concept study, we aimed to understand to what extent information parents and teachers provide through online questionnaires overlaps with clinicians’ diagnostic conclusions on attention-deficit/hyperactivity disorder (ADHD). Moreover, we intended to explore a possible role that autism spectrum disorders (ASD) symptoms played in this process. We examined parent- and teacher-rated questionnaires collected remotely and an on-site evaluation of intelligence quotients from 342 subjects (18% females), aged 3–16 years, and referred for suspected ADHD. An easily interpretable machine learning model—decision tree (DT)—was built to simulate the clinical process of classifying ADHD/non-ADHD based on collected data. Then, we tested the DT model’s predictive accuracy through a cross-validation approach. The DT classifier’s performance was compared with those that other machine learning models achieved, such as random forest and support vector machines. Differences in ASD symptoms in the DT-identified classes were tested to address their role in performing a diagnostic error using the DT model. The DT identified the decision rules clinicians adopt to classify an ADHD diagnosis with an 82% accuracy rate. Regarding the cross-validation experiment, our DT model reached a predictive accuracy of 74% that was similar to those of other classification algorithms. The caregiver-reported ADHD core symptom severity proved the most discriminative information for clinicians during the diagnostic decision process. However, ASD symptoms were a confounding factor when ADHD severity had to be established. Telehealth procedures proved effective in obtaining an automated output regarding a diagnostic risk, reducing the time delay between symptom detection and diagnosis. However, this should not be considered an alternative to on-site procedures but rather as automated support for clinical practice, enabling clinicians to allocate further resources to the most complex cases.