Potential suicide risk among the college student population: machine learning approaches for identifying predictors and different students' risk profiles.

BACKGROUND: Suicide is one of the leading causes of death among young people and university students. Research has identified numerous socio-demographic, relational, and clinical factors as potential predictors of suicide risk, and machine learning techniques have emerged as promising ways to improve risk assessment. OBJECTIVE: This cross-sectional observational study aimed at identifying predictors and college student profiles associated with suicide risk through a machine learning approach. METHODS: A total of 3102 students were surveyed regarding potential suicide risk, socio-demographic characteristics, academic career, and physical/mental health and well-being. The classification tree technique and the multiple correspondence analysis were applied to define students' profiles in terms of suicide risk and to detect the main predictors of such a risk. RESULTS: Among the participating students, 7% showed high potential suicide risk and 3.8% had a history of suicide attempts. Psychological distress and use of alcohol/substance were prominent predictors of suicide risk contributing to define the profile of high risk of suicide: students with significant psychological distress, and with medium/high-risk use of alcohol and psychoactive substances. Conversely, low psychological distress and low-risk use of alcohol and substances, together with religious practice, represented the profile of students with low risk of suicide. CONCLUSIONS: Machine learning techniques could hold promise for assessing suicide risk in college students, potentially leading to the development of more effective prevention programs. These programs should address both risk and protective factors and be tailored to students' needs and to the different categories of risk.

Study International Multicentric Pancreatic Left Resections (SIMPLR): Does Surgical Approach Matter?

BACKGROUND: Minimally invasive surgery is increasingly preferred for left-sided pancreatic resections. The SIMPLR study aims to compare open, laparoscopic, and robotic approaches using propensity score matching analysis. METHODS: This study included 258 patients with tumors of the left side of the pancreas who underwent surgery between 2016 and 2020 at three high-volume centers. The patients were divided into three groups based on their surgical approach and matched in a 1:1 ratio. RESULTS: The open group had significantly higher estimated blood loss (620 mL vs. 320 mL, p < 0.001), longer operative time (273 vs. 216 min, p = 0.003), and longer hospital stays (16.9 vs. 6.81 days, p < 0.001) compared to the laparoscopic group. There was no difference in lymph node yield or resection status. When comparing open and robotic groups, the robotic procedures yielded a higher number of lymph nodes (24.9 vs. 15.2, p = 0.011) without being significantly longer. The laparoscopic group had a shorter operative time (210 vs. 340 min, p < 0.001), shorter ICU stays (0.63 vs. 1.64 days, p < 0.001), and shorter hospital stays (6.61 vs. 11.8 days, p < 0.001) when compared to the robotic group. There was no difference in morbidity or mortality between the three techniques. CONCLUSION: The laparoscopic approach exhibits short-term benefits. The three techniques are equivalent in terms of oncological safety, morbidity, and mortality.

AI-assisted capsule endoscopy reading in suspected small bowel bleeding: a multicentre prospective study.

BACKGROUND: Capsule endoscopy reading is time consuming, and readers are required to maintain attention so as not to miss significant findings. Deep convolutional neural networks can recognise relevant findings, possibly exceeding human performances and reducing the reading time of capsule endoscopy. Our primary aim was to assess the non-inferiority of artificial intelligence (AI)-assisted reading versus standard reading for potentially small bowel bleeding lesions (high P2, moderate P1; Saurin classification) at per-patient analysis. The mean reading time in both reading modalities was evaluated among the secondary endpoints. METHODS: Patients aged 18 years or older with suspected small bowel bleeding (with anaemia with or without melena or haematochezia, and negative bidirectional endoscopy) were prospectively enrolled at 14 European centres. Patients underwent small bowel capsule endoscopy with the Navicam SB system (Ankon, China), which is provided with a deep neural network-based AI system (ProScan) for automatic detection of lesions. Initial reading was performed in standard reading mode. Second blinded reading was performed with AI assistance (the AI operated a first-automated reading, and only AI-selected images were assessed by human readers). The primary endpoint was to assess the non-inferiority of AI-assisted reading versus standard reading in the detection (diagnostic yield) of potentially small bowel bleeding P1 and P2 lesions in a per-patient analysis. This study is registered with ClinicalTrials.gov, NCT04821349. FINDINGS: From Feb 17, 2021 to Dec 29, 2021, 137 patients were prospectively enrolled. 133 patients were included in the final analysis (73 [55%] female, mean age 66·5 years [SD 14·4]; 112 [84%] completed capsule endoscopy). At per-patient analysis, the diagnostic yield of P1 and P2 lesions in AI-assisted reading (98 [73·7%] of 133 lesions) was non-inferior (p<0·0001) and superior (p=0·0213) to standard reading (82 [62·4%] of 133; 95% CI 3·6-19·0). Mean small bowel reading time was 33·7 min (SD 22·9) in standard reading and 3·8 min (3·3) in AI-assisted reading (p<0·0001). INTERPRETATION: AI-assisted reading might provide more accurate and faster detection of clinically relevant small bowel bleeding lesions than standard reading. FUNDING: ANKON Technologies, China and AnX Robotica, USA provided the NaviCam SB system.

Evaluation of a Novel Fixative Solution for Liquid-Based Cytology in Diagnostic Cytopathology.

Since its introduction in the early 2000s, liquid-based cytology (LBC) has been increasingly used for gynecologic and non-gynecologic cytology, and its multiple advantages have been widely recognized. The aim of this study was to investigate the use of a new fixative and pre-analytical method for morphological diagnosis in cytological samples. In particular, we evaluated the effect of a novel preservative solution on the preparation of diagnostic slides by comparing it with the standard reference used globally in cytology laboratories. This study included both gynecological (n = 139) and non-gynecological (n = 183) samples. Several morphologic variables were then identified and evaluated. Using this approach, we were then able to demonstrate the suitability of the new system, with improved safety, to be integrated within current pathology clinical practice. Overall, using a safer preservative solution, the study shows no statistical difference (and then non-inferiority) in the new fixation protocol compared with the standard reference used in routine practice in terms of diagnostic adequacy, evaluated both in clinically relevant gyn and non-gyn datasets.

Treatment Decision-Making Capacity in Forensic vs Non-forensic Psychiatric Patients: A European Comparison.

Background: Consent to treatment is a cornerstone of medical ethics and law. Nevertheless, very little empirical evidence is available to inform clinicians and policymakers regarding the capacities of forensic patients with schizophrenia spectrum disorders (SSDs) to make decisions about their treatment, with the risk of clinical and legal inertia, silent coercion, stigmatization, or ill-conceived reforms. Study Design: In this multinational study, we assessed and compared with treatment-related decisional capacities in forensic and non-forensic patients with SSD. 160 forensic and 139 non-forensic patients were used in Austria, Germany, Italy, Poland, and England. Their capacity to consent to treatment was assessed by means of the MacArthur Competence Assessment Tool for Treatment (MacCAT-T). Multiple generalized linear regression models were used to identify the socio-demographic and clinical variables associated with MacCAT-T scores. Study Results: In total, 55 forensic (34.4%) and 58 non-forensic patients (41.7%) showed high treatment-related decisional capacity, defined as scoring ≥75% of the maximum scores for the understanding, appreciation and reasoning, and 2 for expressing a choice. Forensic patients showed differences in their capacity to consent to treatment across countries. Of all socio-demographic and clinical variables, only "social support" was directly relevant to policy. Conclusions: Forensic patients have treatment-related decisional capacities comparable with their non-forensic counterparts. Social contacts might provide a substantial contribution towards enhancing the decisional autonomy of both forensic and non-forensic patients, hence improving the overall quality and legitimacy of mental health care.

Machine learning approaches to identify profiles and predictors of psychosocial discomfort among Italian college students / Enfoques de machine learning para identificar perfiles y predictores de malestar psicosocial entre estudiantes universitarios italianos

Abstract Introduction College students live a crucial period of transition from late adolescence to adulthood when they have to deal with important stressful tasks. Thus, university often represents a stressful environment, pushing students to cope with a high academic pressure. As a result, this period constitutes a sensitive age for the onset of mental disorders. Typically, students are not aware of the early signs of their own compromised mental health until symptoms aggravate to an overt disorder. Therefore, it is important to timely detect subthreshold symptoms mostly related to generic mental distress. Objective First, to assess psychophysical well-being and mental distress among college students in northern Italy, and to detect predictors, among socio-demographic and academic characteristics, and risky drug use of these two outcomes. Method The study involved 13,886 students who received an email explaining the purpose of the e-research. The questionnaires used were the General Health Questionnaire (GHQ-12), the University Stress Scale (USS), and a modified version of World Health Organization-ASSIST v3.0. Results 3,754 students completed the web-survey. Students showed poor well-being and mental distress. The strongest predictor of mental distress and compromised well-being was physical health, followed by sex, study field, risky drug use, and academic performance concerns. Discussion and conclusion This study shows that it is very important to promote in college students healthy behaviors in order to increase their physical exercise and reduce substance use. Moreover, it would be desirable to improve academic counselling facilities as an important front-line service to intercept mental health issues among young adults.

Resumen Introducción Los estudiantes universitarios pasan por un periodo crucial en su transición de la adolescencia tardía a la edad adulta, periodo en que tienen que lidiar con tareas estresantes. La universidad representa un entorno estresante, que empuja a los estudiantes a hacer frente a una alta presión académica. Como resultado, este periodo constituye una edad sensible para la aparición de trastornos mentales. En general, los estudiantes no cobran consciencia de los primeros signos de que su propia salud mental está en riesgo sino hasta que los síntomas se agravan y se convierten en un trastorno manifiesto. Por tanto, es importante detectar oportunamente los síntomas subumbrales relacionados ante todo con la angustia mental genérica. Objetivo Evaluar el bienestar psicofísico y la angustia mental entre estudiantes universitarios del norte de Italia, y en segundo lugar, detectar predictores entre las características sociodemográficas y académicas, y el uso de drogas de estos dos resultados. Método En el estudio participaron 13,886 estudiantes que recibieron un correo electrónico que explicaba el propósito de la investigación. Los instrumentos utilizados fueron el Cuestionario de Salud General (GHQ-12), la Escala de Estrés Universitario (USS) y una versión modificada de la Organización Mundial de la Salud-ASSIST v3.0. Resultados 3,754 estudiantes completaron la encuesta en línea. Los estudiantes mostraron bienestar y angustia mental. El predictor más fuerte de angustia mental y bienestar comprometido fue la salud física, seguido del sexo, el campo de estudio, el uso de drogas y el rendimiento académico. Discusión y conclusión Este estudio muestra que es muy importante promover entre los estudiantes universitarios comportamientos saludables para promover el ejercicio físico y reducir el consumo de sustancias. Además, sería deseable mejorar la orientación académica que es un importante servicio de primera línea para interceptar los problemas de salud mental en los estudiantes.

Superwellness Program: a cognitive-behavioral therapy-based group intervention to reduce weight gain in patients treated with antipsychotic drugs

Objective: To assess the effectiveness of a cognitive-behavioral therapy-based intervention (Superwellness Program) on weight gain compared with a treatment-as-usual (TAU) approach in patients treated with antipsychotics, and to evaluate the relationship between body mass index (BMI) variation and clinical variables. Method: Eighty-five patients treated with antipsychotics were allocated across two groups, experimental (n=59) and control (n=26). The Superwellness Program (experimental group) consisted of 32 twice-weekly 1-hour sessions, conducted by a psychologist and a nutritionist/nurse, concurrently with moderate food intake and moderate physical activity plans. Sociodemographic, clinical, and biological variables were collected at baseline, at the end of intervention (16 weeks), and after 6 months. Results: BMI change from baseline differed significantly between the experimental and control groups, with a larger decrease in the experimental group (F = 5.5, p = 0.021). Duration of illness moderated the effect of treatment on BMI (p = 0.026). No significant (p = 0.499) effect of intervention during the follow-up period was found. Interestingly, the intervention indirectly induced a significant (p = 0.024) reduction in metabolic risk by reducing BMI. Conclusion: A cognitive-behavioral therapy-based intervention could be useful in reducing weight in a clinical population taking antipsychotics, with consequent benefit to physical and mental health.