Search

Abstract Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

The [beta]-secretase [beta]-site APP cleaving enzyme (BACE1) is a central drug target for Alzheimer's disease. Clinically tested, BACE1-directed inhibitors also block the homologous protease BACE2. Yet little is known about physiological BACE2 substrates and functions in vivo. Here, we identify BACE2 as the protease shedding the lymphangiogenic vascular endothelial growth factor receptor 3 (VEGFR3). Inactivation of BACE2, but not BACE1, inhibited shedding of VEGFR3 from primary human lymphatic endothelial cells (LECs) and reduced release of the shed, soluble VEGFR3 (sVEGFR3) ectodomain into the blood of mice, nonhuman primates, and humans. Functionally, BACE2 inactivation increased full-length VEGFR3 and enhanced VEGFR3 signaling in LECs and also in vivo in zebrafish, where enhanced migration of LECs was observed. Thus, this study identifies BACE2 as a modulator of lymphangiogenic VEGFR3 signaling and demonstrates the utility of sVEGFR3 as a pharmacodynamic plasma marker for BACE2 activity in vivo, a prerequisite for developing BACE1- selective inhibitors for safer prevention of Alzheimer's disease., Introduction Alzheimer's disease (AD) is the most common neurodegenerative disorder. Effective therapeutic or preventive approaches for this deadly disease are lacking. A central drug target for AD is the transmembrane [...]

Introduction Bipolar disorder (BD) is a recurrent disorder, causing functional impairment and raised mortality, particularly due to suicide. However, the difficulty in predicting suicidal behaviors relies in the lack of clear biomarkers. Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, most ML studies focused on lifetime attempts, without having a predictive time window, and did not employ time-dependent variables. Moreover, most studies lie on cross-sectional databases, without including more than one time-point. Objectives First, we aimed to predict 12-months suicide attempts in a naturalistic sample of BD patients, using clinical and demographic data. Second, we aimed to improve the prediction by including information from intermediate visits (1, 3, and 6 months), mimicking more closely the clinician’s way of thinking and the multiple observations a patient receives. Methods A sample of 163 BD patients (53% females, mean age 44.7, SD 15.3) were recruited. Based on EHR, 56 clinical and demographic features were extracted, including hospitalizations, suicidal behaviors lifetime and in the last 12 months, along with comorbidity, family history, work, and therapies. Patients were followed up for 12 months. Support Vector Machine (SVM) was used to differentiate subjects who attempted suicide versus those who did not in a 12-month time window, within a repeated nested Cross-Validation. The SVM was optimized weighting the hyperplane for uneven group sizes. Then, we repeated the analysis including information from intermediate visits (1, 3, 6 months after the first contact). For each visit, we created a composite score based on current therapy, new admissions, and ER presentations. To avoid circularity, all the information (ER, admission etc.) related to a suicide attempt were not included. Results During the 12-months follow-up, 9.8% of patients attempted suicide. The results from the 12-months suicide prediction model obtained an Area Under the Curve of 0.71(with a Balanced Accuracy (BAC) of 68%). After incorporating the composite scores based on intermediate visits in the model, the prediction raised to an Area Under the Curve of 0.78 (BAC 73%), suggesting that including intermediate visits is a valid method to improve prediction. The features that contributed the most to the prediction were the composite score at 6-month visit, lifetime number of suicide attempts, suicide attempts in the last 12 months, substance of abuse (other than cannabis), and antipsychotics. Conclusions ML proved a good prediction accuracy for suicide in a 12-months time window, and the prediction was improved by including data from intermediate visits. The model showed the importance of time-dependent features, such as attempts in the last 12 months. Our analysis might help in identifying early clinical risk factors and underlies the importance of multiple evaluations in populations at risk. Disclosure of Interest None Declared

BackgroundSchizophrenia spectrum disorders (SSD) can be associated with an increased risk of violent behavior (VB), which can harm patients, others, and properties. Prediction of VB could help reduce the SSD burden on patients and healthcare systems. Some recent studies have used machine learning (ML) algorithms to identify SSD patients at risk of VB. In this article, we aimed to review studies that used ML to predict VB in SSD patients and discuss the most successful ML methods and predictors of VB.MethodsWe performed a systematic search in PubMed, Web of Sciences, Embase, and PsycINFO on September 30, 2023, to identify studies on the application of ML in predicting VB in SSD patients.ResultsWe included 18 studies with data from 11,733 patients diagnosed with SSD. Different ML models demonstrated mixed performance with an area under the receiver operating characteristic curve of 0.56-0.95 and an accuracy of 50.27-90.67% in predicting violence among SSD patients. Our comparative analysis demonstrated a superior performance for the gradient boosting model, compared to other ML models in predicting VB among SSD patients. Various sociodemographic, clinical, metabolic, and neuroimaging features were associated with VB, with age and olanzapine equivalent dose at the time of discharge being the most frequently identified factors.ConclusionML models demonstrated varied VB prediction performance in SSD patients, with gradient boosting outperforming. Further research is warranted for clinical applications of ML methods in this field.

Lymphedema is a chronic and worsening disease due to an abnormal accumulation of liquids, with a high protein content in the interstitial space. The disease is characterized by an insufficient flow of lymphatic fluid, which manifests as edema, inflammation, and fibrosis, all the way up to the stiffening of the affected tissues. Because it's a chronic and increasing disease, the treatment is highly complex. The literature shows that the treatment must be multidisciplinary and it is necessary to combine multiple techniques, such as manual lymphatic drainage, mechanical lymphatic drainage, elasto-compressive bandages and other complementary techniques up to surgical treatment in the most advanced forms which are not responsive to physical therapy. Furthermore, the disease is characterized by episodes of cellulitis, that may lead to infectious complications because the lymphatic function becomes insufficient. A condition of local immunodeficiency is created due to the crucial role that the lymphatic system covers with immune defenses, therefore creates a fertile ground for infections caused by small skin wounds, insect bites, animal scratches, nail fungus, blood draws. Therefore, particular attention is paid to skin folds and interdigital spaces for which hygiene is necessary using neutral detergents, drying by dabbing, and applying emollient creams for skin hydration. Unfortunately, such practices of prevention and care are often underestimated. We provide education of the patient on self-care, such as the self-bandage and the correct application of the elasto-compressed stoking. For wrapping the bandage, it is advisable to wear a glove or a special sock. The multilayer bandages are used in the first decongestant phase while over time the elastic stocking is the best aid for the management of lymphedema. Our clinic is a referral center for diagnosis, treatment and surgical therapy, where patients come for surgical evaluation. Since 2016 we have systematically collected clinical data and volume evaluation of more than 600 cases affected by lymphedema and lipoedema of all stages. They have been treated with complex decongestive therapy for 4 hours a day, 15 consecutive days, subsequently a maintenance of once a week for 3 months, then once a month for 6 months. Of more than 600 patients treated, only 150 were submitted to surgery (lymphatic venous anastomosis, fasciotomy or liposuction, chylothorax and chyloperitoneal shunt, reconstructive plastic of external genitalia). Complex decongestive interdisciplinary therapy, when properly performed can stabilize the lymphedema patient situation, reducing the stage and ensuring a good quality of life.

IntroductionThe Attenuated Psychosis Symptoms (APS) syndrome mostly represents the ultra-high-risk state of psychosis but, as does the Brief Intermittent Psychotic Symptoms (BIPS) syndrome, shows a large variance in conversion rates. This may be due to the heterogeneity of APS/BIPS that may be related to the effects of culture, sex, age, and other psychiatric morbidities. Thus, we investigated the different thematic contents of APS and their association with sex, age, country, religion, comorbidity, and functioning to gain a better understanding of the psychosis-risk syndrome.MethodA sample of 232 clinical high-risk subjects according to the ultra-high risk and basic symptom criteria was recruited as part of a European study conducted in Germany, Italy, Switzerland, and Finland. Case vignettes, originally used for supervision of inclusion criteria, were investigated for APS/BIPS contents, which were compared for sex, age, country, religion, functioning, and comorbidities using chi-squared tests and regression analyses.ResultWe extracted 109 different contents, mainly of APS (96.8%): 63 delusional, 29 hallucinatory, and 17 speech-disorganized contents. Only 20 contents (18.3%) were present in at least 5% of the sample, with paranoid and referential ideas being the most frequent. Thirty-one (28.5%) contents, in particular, bizarre ideas and perceptual abnormalities, demonstrated an association with age, country, comorbidity, or functioning, with regression models of country and obsessive-compulsive disorders explaining most of the variance: 55.8 and 38.3%, respectively. Contents did not differ between religious groups.ConclusionPsychosis-risk patients report a wide range of different contents of APS/BIPS, underlining the psychopathological heterogeneity of this group but also revealing a potential core set of contents. Compared to earlier reports on North-American samples, our maximum prevalence rates of contents were considerably lower; this likely being related to a stricter rating of APS/BIPS and cultural influences, in particular, higher schizotypy reported in North-America. The various associations of some APS/BIPS contents with country, age, comorbidities, and functioning might moderate their clinical severity and, consequently, the related risk for psychosis and/or persistent functional disability.

Abstract Although cinema narrative represents a fundamental communication tool in framing public opinion, whether a negative representation of certain species in the context of animal‐horror movies might increase the attitudinal hostilities towards them remains an aspect of wildlife perception that is poorly studied. Here, we reviewed online sources from the last 70 years to describe the negative representation of animal roles in horror and disaster movies. Specifically, we described species diversity, how the animal was depicted, the cause for its aggressive behaviour and how it came in contact with the human characters. By means of principal coordinate analysis (PCoA), we also highlighted three main typologies of animal‐horror movies. The dataset consisted of 263 titles produced world‐wide from 1950 to 2019. The results showed that animal representation is transversal yet uneven, with five species groups out of 18 appearing in more than half of the movies. There were significant associations between species, their representation and the different kinds of movies they appeared in, with some species groups appearing more commonly in certain types of film plots rather than others. Together, the results suggested that both the themes and topics of animal‐horror movies were often the result of a combination of factors, including fashion‐driven audience interests, societal and political concerns, and technological availability at the time of production. Whether this repeated and variegated representation can increase attitudinal hostility remains however unclear. Read the free Plain Language Summary for this article on the Journal blog.

Nowadays, the lack of quantitative criteria to resolve the diagnostic heterogeneity of psychotic onsets limits the development of safer and more effective treatments. Therefore, the hypothesis to integrate multimodal data to uncover biological subtypes of psychosis has risen [1,2]. Here we explored the existence of subgroups of patients affected by first episode psychosis (FEP) with a possible immunopathogenic basis.To do this, we designed a computational model that use unsupervised machine learning to cluster a sample of 127 FEP patients and 117 healthy controls (HC), based on the peripheral blood concentrations of 12 immune gene transcripts which demonstrated to classify with high accuracy between FEP patients and healthy subjects in a previous study [3]. To validate the model, we applied a resampling strategy based on the half-splitting of the total sample. Further, we tested the correlation between the subgroups and clinical, neuropsychological and brain structural variables.In both the discovery and validation samples, the model identified a FEP cluster characterized by the high expression of inflammatory and immune-activating genes (IL1b, CCR7 and IL12a) and of a single immune counterregulatory gene (CCR3)[4] and a further cluster consisting of equal number of FEP and HC subjects, which did not show a relative over or under expression of any immune marker (balanced subgroup). Also, none of the subgroups were related to specific symptoms dimensions or longitudinal diagnosis. FEP patients included in the balanced immune subgroup showed a reduced left hippocampal volume and a left supramarginal and lateroccipital cortexes’ thinning. These correlations seem to support an opposite pattern in the correspondent brain area of the inflammatory subgroup [5].Our results demonstrated the existence of a FEP patients’ subgroup that present a prominent activation of the inflammatory response. This evidence may pave the way to sample stratification in future trials aiming to develop personalized diagnostic tools and therapies targeting specific immunopathogenic pathways of psychosis onsets.

Background: Among Coronavirus Disease 2019 (COVID-19) manifestations, Olfactory (OD) and Gustatory (GD) Dysfunctions (OGD) have drawn considerable attention, becoming a sort of hallmark of the disease. Many have speculated on the pathogenesis and clinical characteristics of these disturbances; however, no definite answers have been produced on the topic. With this systematic review, we aimed to collect all the available evidence regarding the prevalence of OGD, the timing of their onset and their resolution, their rate of recovery and their role as diagnostic and prognostic tools for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection. Methods: A systematic review comprising all the observational studies that reported the prevalence and/or the longitudinal trajectories of OGD in COVID-19 patients, as self-reported by patients or measured through objective psychophysical tests. Results: After the selection process, 155 studies were included, with a total of 70,920 patients and 105,291 not-infected individuals. Prevalence reports were extremely variable across studies, with wide ranges for OD (0%–98%) and GD (0–89%) prevalence. OGD occurred early during the disease course and only rarely preceded other symptoms; out of 30 studies with a follow-up time of at least 20 days, only in 5 studies OGD fully resolved in more than 90% of patients. OGD had low sensitivity and high specificity for SARS-CoV-2 infection; accuracy of OD and GD for infection identification was higher than 80% in 10 out of 33 studies and in 8 out of 22 studies considered, respectively. 28 out of 30 studies that studied the association between OGD and disease severity found how OGD were associated with lower rates of severe pneumonia, hospitalization and mortality. Conclusions: OGD seem to be highly prevalent in SARS-CoV-2 infection. They occur early, concomitantly with other symptoms and often persist after recovery, in some cases for months; whether a full recovery eventually occurs in all cases is not clear yet. OGD are good predictors of SARS-CoV-2 infection and are associated with a milder disease course.

Background: Schizophrenia spectrum disorders (SSD) can be associated with an increased risk of violent behavior (VB), which can harm patients, others, and properties. Prediction of VB could help reduce the SSD burden on patients and healthcare systems. Some recent studies have used machine learning (ML) algorithms to identify SSD patients at risk of VB. In this article, we aimed to review studies that used ML to predict VB in SSD patients and discuss the most successful ML methods and predictors of VB. Methods: We performed a systematic search in PubMed, Web of Sciences, Embase, and PsycINFO on September 30, 2023, to identify studies on the application of ML in predicting VB in SSD patients. Results: We included 18 studies with data from 11,733 patients diagnosed with SSD. Different ML models demonstrated mixed performance with an area under the receiver operating characteristic curve of 0.56-0.95 and an accuracy of 50.27-90.67% in predicting violence among SSD patients. Our comparative analysis demonstrated a superior performance for the gradient boosting model, compared to other ML models in predicting VB among SSD patients. Various sociodemographic, clinical, metabolic, and neuroimaging features were associated with VB, with age and olanzapine equivalent dose at the time of discharge being the most frequently identified factors. Conclusion: ML models demonstrated varied VB prediction performance in SSD patients, with gradient boosting outperforming. Further research is warranted for clinical applications of ML methods in this field. [ABSTRACT FROM AUTHOR]

Sex-related differences are tied into neurodevelopmental and lifespan processes, beginning early in the perinatal and developmental phases and continue into adulthood. The present study was designed to investigate sexual dimorphism of changes in gray matter (GM) volume in post-adolescence, with a focus on early and middle-adulthood using a structural magnetic resonance imaging (MRI) dataset of healthy controls from the European Network on Psychosis, Affective disorders and Cognitive Trajectory (ENPACT). Three hundred and seventy three subjects underwent a 3.0 T MRI session across four European Centers. Age by sex effects on GM volumes were investigated using voxel-based morphometry (VBM) and the Automated Anatomical Labeling atlas regions (ROI). Females and males showed overlapping and non-overlapping patterns of GM volume changes during aging. Overlapping age-related changes emerged in bilateral frontal and temporal cortices, insula and thalamus. Both VBM and ROI analyses revealed non-overlapping changes in multiple regions, including cerebellum and vermis, bilateral mid frontal, mid occipital cortices, left inferior temporal and precentral gyri. These findings highlight the importance of accounting for sex differences in cross-sectional analyses, not only in the study of normative changes, but particularly in the context of psychiatric and neurologic disorders, wherein sex effects may be confounded with disease-related changes.

In community studies, both attenuated psychotic symptoms (APS) and basic symptoms (BS) were more frequent but less clinically relevant in children and adolescents compared to adults. In doing so, they displayed differential age thresholds that were around age 16 for APS, around age 18 for perceptive BS, and within the early twenties for cognitive BS. Only the age effect has previously been studied and replicated in clinical samples for APS. Thus, we examined the reported age effect on and age thresholds of 14 criteria-relevant BS in a patient sample at clinical-high risk of psychosis (N = 261, age 15–40 yrs.), recruited within the European multicenter PRONIA-study. BS and the BS criteria, “Cognitive Disturbances” (COGDIS) and “Cognitive-perceptive BS” (COPER), were assessed with the “Schizophrenia Proneness Instrument, Adult version” (SPI-A). Using logistic regressions, prevalence rates of perceptive and cognitive BS, and of COGDIS and COPER, as well as the impact of social and role functioning on the association between age and BS were studied in three age groups (15–18 years, 19–23 years, 24–40 years). Most patients (91.2%) reported any BS, 55.9% any perceptive and 87.4% any cognitive BS. Furthermore, 56.3% met COGDIS and 80.5% COPER. Not exhibiting the reported differential age thresholds, both perceptive and cognitive BS, and, at trend level only, COPER were less prevalent in the oldest age group (24–40 years); COGDIS was most frequent in the youngest group (15–18 years). Functional deficits did not better explain the association with age, particularly in perceptive BS and cognitive BS meeting the frequency requirement of BS criteria. Our findings broadly confirmed an age threshold in BS and, thus, the earlier assumed link between presence of BS and brain maturation processes. Yet, age thresholds of perceptive and cognitive BS did not differ. This lack of differential age thresholds might be due to more pronounced the brain abnormalities in this clinical sample compared to earlier community samples. These might have also shown in more frequently occurring and persistent BS that, however, also resulted from a sampling toward these, i.e., toward COGDIS. Future studies should address the neurobiological basis of CHR criteria in relation to age.