Background: Validated clinical prediction models of short-term remission in psychosis are lacking. Our aim was to develop a clinical prediction model aimed at predicting 4−6-week remission following a first episode of psychosis. Method: Baseline clinical data from the Athens First Episode Research Study was used to develop a Support Vector Machine prediction model of 4-week symptom remission in first-episode psychosis patients using repeated nested cross-validation. This model was further tested to predict 6-week remission in a sample of two independent, consecutive Danish first-episode cohorts. Results: Of the 179 participants in Athens, 120 were male with an average age of 25.8 years and average duration of untreated psychosis of 32.8 weeks. 62.9% were antipsychotic-naïve. Fifty-seven percent attained remission after 4 weeks. In the Danish cohort, 31% attained remission. Eleven clinical scale items were selected in the Athens 4-week remission cohort. These included the Duration of Untreated Psychosis, Personal and Social Performance Scale, Global Assessment of Functioning and eight items from the Positive and Negative Syndrome Scale. This model significantly predicted 4-week remission status (area under the receiver operator characteristic curve (ROC-AUC) = 71.45, P < .0001). It also predicted 6-week remission status in the Danish cohort (ROC-AUC = 67.74, P < .0001), demonstrating reliability. Conclusions: Using items from common and validated clinical scales, our model significantly predicted early remission in patients with first-episode psychosis. Although replicated in an independent cohort, forward testing between machine learning models and clinicians’ assessment should be undertaken to evaluate the possible utility as a routine clinical tool.

The tryptophan-metabolizing kynurenine pathway (KP) can be activated by enhanced inflammatory responses and has been implicated in the pathophysiology of schizophrenia. However, there is little evidence for KP dysregulation in the early course of psychotic illness. We aimed to investigate the potential immune-mediated hyperactivity of KP in individuals with first-episode psychosis (FEP) and the relationship with symptom severity and treatment response outcomes. Serum immunoassays were performed to measure peripheral levels of inflammatory cytokines (IL-1β, IL-10, TNF-a), KP rate-limiting enzymes (IDO/TDO), and kynurenic acid (KYNA) metabolite in 104 antipsychotic-naïve patients with FEP and 80 healthy controls (HC). The Positive and Negative Syndrome Scale (PANSS) and the Global Assessment of Functioning Scale (GAF) were administered to assess psychopathology and functioning status at admission and following 4-week treatment with antipsychotics. Cytokine and KP components levels were substantially increased in FEP patients compared to HC, before and after antipsychotic treatment. A significant positive correlation between pro-inflammatory IL-1β and KYNA levels was observed among FEP patients, but not in HC. Importantly, within-patient analysis revealed that those with higher baseline KYNA experienced more severe negative symptoms and poorer clinical improvement at follow-up. These findings suggest that KP is upregulated in early psychosis, likely through the induction of IL-1β-dependent pathways, and raised peripheral KYNA might represent a promising indicator of non-response to antipsychotic medication in patients with FEP.

Background.: Premorbid adjustment (PA) abnormalities in psychotic disorders are associated with an earlier age at onset (AAO) and unfavorable clinical outcomes, including treatment resistance. Prior family studies suggest that familial liability, likely reflecting increased genetic risk, and socioeconomic status (SES) contribute to premorbid maladjustment. However, their joint effect possibly indicating gene–environment interaction has not been evaluated.Methods.: We examined whether family history of psychosis (FHP) and parental SES may predict PA and AAO in unrelated cases with first-episode psychosis (n= 108) and schizophrenia (n= 104). Premorbid academic and social functioning domains during childhood and early adolescence were retrospectively assessed. Regression analyses were performed to investigate main effects of FHP and parental SES, as well as their interaction. The relationships between PA, AAO, and response to antipsychotic medication were also explored.Results.: Positive FHP associated with academic PA difficulties and importantly interacted with parental SES to moderate social PA during childhood (interactionp= 0.024). Positive FHP and parental SES did not predict differences in AAO. Nevertheless, an earlier AAO was observed among cases with worse social PA in childhood (β= −0.20;p= 0.005) and early adolescence (β= −0.19;p= 0.007). Further, confirming evidence emerged for an association between deficient childhood social PA and poor treatment response (p= 0.04).Conclusions.: Familial risk for psychosis may interact with parental socioeconomic position influencing social PA in childhood. In addition, this study supports the link between social PA deviations, early psychosis onset, and treatment resistance, which highlights premorbid social functioning as a promising clinical indicator.

Aggression in patients with dementia poses significant caregiving and clinical issues. In this work, fusion approaches—Early Fusion and Late Fusion—were compared to classify aggression using audio and visual signals. Early Fusion integrates the extracted features of the two modalities into one dataset before classification, while Late Fusion integrates the prediction probabilities of standalone audio and visual classifiers with a meta-classifier. Both models were tested using a Random Forest classifier with five-fold cross-validation, and the performance was compared on accuracy, precision, recall, F1-score, ROC-AUC, and inference time. The results showcase that Late Fusion is superior to Early Fusion in terms of accuracy (0.876 vs. 0.828), recall (0.914 vs. 0.818), F1-score (0.867 vs. 0.835), and ROC-AUC score (0.970 vs. 0.922), proving more suitable for high-sensitivity use cases like healthcare and security. However, Early Fusion exhibited higher precision (0.852 vs. 0.824), indicating that in cases when false positives are a requirement, Early Fusion is preferable. Paired t-tests were applied for statistical comparison and indicate that precision alone is significantly different, with the advantage of Early Fusion. Late Fusion also performs slightly less in inference time, which makes it suitable for use in real-time systems. These findings provide significant information on multimodal fusion strategies and their applicability in the detection of aggressive behavior, which can contribute to the development of efficient monitoring systems for dementia care.

This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset.

Introduction: Clinical insight constitutes a useful marker of the progress and outcome of the First Episode of Psychosis (FEP), and lack of insight has been associated with more severe psychopathology, treatment non-adherence, and rehospitalization/relapse. In this study, we aimed to further investigate the possible role of insight as a predictor of relapse, its relation to diagnosis, and other parameters of positive psychotic symptomatology (delusions, hallucinations, and suspiciousness). Methods: The Athens FEP study employed a prospective, longitudinal cohort design in which consecutive newly diagnosed patients with psychosis were interviewed and asked to voluntarily participate after completing informed consent. A total of 88/225 patients were examined at three different time points (baseline, month, and year). Their scores in the relevant items of the Positive and Negative Syndrome Scale (PANSS) were compared (G12 for insight, P1 for delusions, P3 for hallucinations, and P6 for suspiciousness), and they were further associated to diagnosis and the outcome at the end of the year (remission/relapse). Results: In total, 22/88 patients with relapse at the year had greater scores in G12 for both the month and the year, and this finding was corroborated after adjusting the statistical analysis for demographics, diagnosis, social environment, and depression via multiple logistic regression analysis. Moreover, delusions and suspiciousness were significantly higher in patients diagnosed with non-affective psychosis compared to those diagnosed with affective psychosis (p < 0.001) at the first month. Conclusions: Lack of insight at the first month may serve as a predictor of relapse at the year.