Giuseppe Maniaci

The increasing prevalence of suicidal ideation among university students, especially those enrolled in medical and healthcare courses, necessitates innovative approaches for early detection and prevention. The southern part of Italy presents a distinct cultural, social, and economic context and is under‐represented in research. This study leverages the capabilities of machine learning methods and explainable artificial intelligence (XAI) to address this challenge, developing a predictive model for suicidal thoughts within a large sample of university students in Sicily, the southernmost and largest Italian region. The XGBoost algorithm was implemented for model training on survey data from 3278 students, including sociodemographic factors, academic performance metrics, and mental health indicators such as the Depression, Anxiety, and Stress Scale short version (DASS‐21) and the Eating Attitude Test short version (EAT‐26). The optimized XGBoost achieved promising performance, with AUROC ranging from 0.719 to 0.808 and balanced accuracy between 0.666 and 0.780 across internal and external test sets. Probability calibration was generally reasonable (Brier 0.151–0.185; ECE 0.035–0.120), supporting the reliability of predicted risk estimates. Performance in general varied by degree program, suggesting cohort‐specific characteristics. Our findings underscore the potential of machine learning models to identify at‐risk students and XAI for understating model prediction, emphasizing the importance of early intervention and targeted mental health support in university settings. The model′s performance and explainability highlight the potential in developing a student‐centric and self‐assessment framework while helping to mitigate potential ethical concerns associated with predictive mental health tools.

We examined the feasibility of using the neofunctional deep breathing (NDB) technique to reduce the allostatic load following the Trier Social Stress Test (TSST). Forty‐four healthy subjects were randomised into experimental and control groups. Following the TSST procedure, participants underwent either a single session of NDB or an attention control intervention. The Procomp Infinity Biofeedback system measured breath per minute (BPM), respiratory amplitude, HRV linear domains, skin conductance, and trapezius muscle electromyographic activity. Cortisol and cytokine salivary concentrations, perceived stress, and anxiety levels were also assessed. These parameters were combined into an allostatic load index (ALI) to measure the intervention's effect. This pilot RCT demonstrated the feasibility of the study design and practicality of the intervention. The NDB group showed reduced ALI, increased respiratory abdominal amplitude, decreased BPM, increased HRV indicating parasympathetic activation, and decreased cortisol and inflammatory cytokines. This study highlighted the feasibility of testing the NDB technique in reducing allostatic load through a neurobiological and anti‐inflammatory response after exposure to psychosocial stress. This protocol can represent a non‐invasive therapeutic adjutant in disorders related to a dysregulation of the HPA axis or to an inflammatory state.Trial Registration: NCT04102813

Introduction: Several studies have investigated the specific neural correlates of trans people, highlighting mixed results. This study aimed to compare the presence of specific functional connectivity and differences in cognitive profile and hormone levels in trans men diagnosed with gender dysphoria (GD), and a homogeneous group of cisgender men and cisgender women. Methods: A total of 42 participants (19 trans men, 11 cisgender men, and 12 cisgender women) underwent a resting state fMRI and were measured for blood levels of testosterone, estradiol, and progesterone. A neuropsychological battery evaluated executive functions, attention, visual-perceptual ability, verbal fluency, manual preference, and general intelligence. Results: Trans men showed weaker functional connectivity in the precentral gyrus, subcallosal cortex, paracingulate gyrus, temporal pole, and cingulate gyrus than cisgender men (p < 0.01). Trans men performed worse than cisgender men in verbal and visuospatial working memory but similarly to cisgender women (p < 0.05). In trans men, functional connectivity of the precentral gyrus correlated positively with testosterone (r = 0.459, p = 0.064) and negatively with estradiol (r = −0.654, p = 0.004) and progesterone blood levels (r = −0.475, p = 0.054). The cluster involving the subcallosal cortex showed a positive correlation with testosterone (r = 0.718, p = 0.001), and a negative correlation with estradiol (r = −0.602, p = 0.011). The functional connectivity from a cluster involving the paracingulate gyrus showed a positive correlation with testosterone (r = 0.592, p = 0.012). Conclusions: This study highlights the importance of overpassing the binary model by underlining the presence of neural pathways that could represent the peculiarity of the neural profile of people with GD.

Y Objective: Affecting more than 264 million people, depression is a systemic and multifactorial disorder that represents one of the leading causes of illness and disability worldwide. Several studies showed an inflammatory response in depressed patients, including the involvement of both chronic low-grade inflammatory response and activation of cell-mediated immunity. The present study aimed to verify the efficacy of a structured functional therapy program for patients with depressed mood, and to determine whether this program can significantly reduce levels of C-reactive protein. Method: 28 outpatients with depressed mood received 20 individual sessions of Functional therapy. Data about socio-demographic variables, depression, self-esteem, and quality of life were collected; moreover, blood specimens were collected before and after treatment, and CRP measurement was performed by immunoenzymatic method. All measures were administered at baseline, at the end of treatment (i.e., 3 months after baseline), and at follow-up (i.e., 6 months after baseline). Results: A repeated measures ANOVA showed a significant difference after treatment on depression levels, levels of self-esteem, and all dimensions of quality of life, such as physical, psychological, social relationships, and environment. Furthermore, a statistically significant difference on levels of CRP was found. Moreover, at follow-up, improvements were maintained. Conclusions: The study revealed initial evidence of the efficacy of a functional therapy program on treating depression and its psychological and inflammation-related markers.

We evaluated the association between healthy lifestyles and academic achievement in a sample of 373 adolescent Italian students. Specifically, we investigated on the association between use of illegal drugs, habits to practice a regular physical, typology of diet, levels of social support, levels of self-esteem, level of Internet use, perceived stress and amount of sleep and academic achievement. Academic performance was positively correlated with good diet, perceived social support, and self-esteem. A statistically significant difference emerged between students with high versus low correct grade point averages in relation to lifetime and current use of illegal drugs. Last, academic performance was negatively correlated with Internet use, perceived stress, and bad diet. A multiple regression analysis was conducted in order to predict academic achievement based on good diet, physical activity, self-esteem, sleep hours, perceived stress, problematic Internet use, perceived social support, and lifetime substance use while controlling for age, gender, and years of education. As expected, healthy lifestyles behaviors were highlighted as a significant predictor in academic achievement. Specifically, it was showed that a good diet as well as nonproblematic Internet use significantly predicted academic success. Moreover, it was found that gender did not moderate the relationship between those predictors and academic achievement. The results of our study show that to practice healthy lifestyle behaviors is a relevant factor for a better performance at school, at least in our sample.

Objective: This randomized controlled trial examined the efficacy of adding a fasting‐mimicking diet to a structured psychotherapy protocol for treating depression.Design: Of 20 patients with depression, 10 were randomly assigned to psychotherapy and dieting (i.e., experimental group) and the other 10 to psychotherapy only (i.e., control group). Patients in both groups received 20 individual sessions of functional therapy along with nutrition consultation. Patients in the control group were instructed to maintain their usual daily diets.Results: Both treatments were effective in reducing depression as well as increasing self‐esteem and quality of life. The experimental group showed improved self‐esteem and psychological quality of life as well as a reduction in their mean body mass index, in comparison to the control group.Conclusions: The study revealed initial evidence of the efficacy of combining psychotherapy with a fasting‐mimicking diet to treat depression and its correlates.