62 research outputs found
Editorial: Machine learning and psychosis: Diagnosis, prognosis and treatment
No full textEditorial on the Research Topic Machine learning and psychosis: Diagnosis, prognosis and treatme
Association between formal thought disorders, neurocognition and functioning in the early stages of psychosis: a systematic review of the last half-century studies
No full textRecent review articles provided an extensive collection of studies covering many aspects of format thought disorders (FTD) among their epidemiology and phenomenology, their neurobiological underpinnings, genetics as well as their transdiagnostic prevalence. However, less attention has been paid to the association of FTD with neurocognitive and functioning deficits in the early stages of evolving psychosis. Therefore, this systematic review aims to investigate the state of the art regarding the association between FTD, neurocognition and functioning in the early stages of evolving psychotic disorders in adolescents and young adults, by following the PRISMA flowchart. A total of 106 studies were screened. We included 8 studies due to their reports of associations between FTD measures and functioning outcomes measured with different scales and 7 studies due to their reports of associations between FTD measures and neurocognition. In summary, the main findings of the included studies for functioning outcomes showed that FTD severity predicted poor social functioning, unemployment, relapses, re-hospitalisations, whereas the main findings of the included studies for neurocognition showed correlations between attentional deficits, executive functions and FTD, and highlighted the predictive potential of executive dysfunctions for sustained FTD. Further studies in upcoming years taking advantage of the acceleration in computational psychiatry would allow researchers to re-investigate the clinical importance of FTD and their role in the transition from at-risk to full-blown psychosis conditions. Employing automated computer-assisted diagnostic tools in the early stages of psychosis might open new avenues to develop targeted neuropsychotherapeutics specific to FTD
Machine learning in the prediction of postpartum depression: A review
No full textCurrent screening options in the setting of postpartum depression (PPD) are firmly rooted in self-
report symptom-based tools. The implementation of the modern machine learning (ML) approaches might, in this context, represent a way to refine patient screening by precisely identifying possible PPD predictors and, subsequently, a population at risk of developing the disease, in an effort to lower its morbidity, mortality and its economic burden.
Methods: We performed a bibliographic search on PubMed and Embase looking for studies aimed at the identification of PPD predictors using ML techniques.
Results: Among the 482 articles retrieved, 11 met the inclusion criteria. The most used algorithm was the support vector machine. Notably, all studies reached an area under the curve above 0.7, ultimately suggesting that the prediction of PPD could be feasible. Variables obtained from sociodemographic and clinical aspects (psychiatric and gynecological factors) seem to be the most reliable. Only three studies employed biological variables, in the form of blood, genetic and epigenetic predictors, while no study employed imaging techniques.
Limitations: The literature on PPD prediction via ML techniques is currently scarce, with most studies employing different variables selection and ML algorithms, ultimately reducing the generalizability of the results.
Conclusions: The identification of a population at risk of developing PPD might be feasible with current technology and clinical knowledge. Further studies are necessary to clarify how such an approach could be implemented into clinical practice
Sexual dimorphism of the planum temporale in schizophrenia: a MRI study
No full textOBJECTIVE: Anatomical alterations in the superior temporal gyrus have been consistently reported in patients with schizophrenia, and they have mostly been linked to positive symptoms, including hallucinations and thought disorders. The superior temporal gyrus is considered one of the most asymmetric and lateralized structure of the human brain, and the process of lateralization seems to vary according to gender in the normal population. However, although it has been consistently suggested that patients with schizophrenia did not show normal brain lateralization in several regions, only few studies investigated it in the superior temporal gyrus and its sub-regions considering the effects of gender. In this context, the aim of this study was to evaluate sexual dimorphism in superior temporal gyrus volumes in a sample of patients with schizophrenia compared to age- and gender-matched healthy controls. METHODS: A total of 72 right/left-handed males (40 schizophrenia patients and 32 healthy controls) and 45 right/left-handed females (18 schizophrenia patients and 27 healthy controls) underwent clinical evaluation and a 1.5T magnetic resonance imaging scan. Gray and white matter volumes of regions of interest within the superior temporal gyrus were manually detected, including the Heschl's gyrus and the planum temporale. RESULTS: Female patients with schizophrenia presented a reduction in left planum temporale gray matter volumes ( F = 4.58, p = 0.03) and a lack of the normal planum temporale asymmetry index ( t = 0.27; p = 0.79) compared to female controls ( t = 5.47; p = 0.001). No differences were found between males for any volumes or laterality indices. Finally, in female patients with schizophrenia, Heschl's gyrus gray and white matter volumes negatively correlated with positive symptoms ( r = -0.56, p = 0.01). CONCLUSION: Our results showed that sexual dimorphism plays a key role on planum temporale in schizophrenia, underlining the importance of gender as a modulator of brain morphology and lateralization of schizophrenia
Machine learning and the prediction of suicide in psychiatric populations: a systematic review
No full textAbstract 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
A diffusion weighted imaging study of basal ganglia in schizophrenia
No full textOBJECTIVES: Several magnetic resonance imaging (MRI) studies provided evidence of selective brain abnormalities in schizophrenia, both in cortical and subcortical structures. Basal ganglia are of particular interest, given not only the high concentration of dopaminergic neurons and receptors, but also for their crucial role in cognitive functions, commonly impaired in schizophrenia. To date, very few studies explored basal ganglia using diffusion imaging, which is sensitive to microstructural organization in brain tissues. The aim of our study is to explore basal ganglia structures with diffusion imaging in a sizeable sample of patients affected by schizophrenia and healthy controls. METHODS: We enrolled 52 subjects affected by schizophrenia according to DMS-IV-R criteria and 46 healthy controls. Diffusion weighted images were obtained using a 1.5 Tesla scanner and apparent diffusion coefficient (ADC) values were determined in axial and coronal sections at the level of basal ganglia. RESULTS: Patients affected by schizophrenia showed a significantly higher ADC compared to healthy controls in the left anterior lenticular nucleus (F = 3.9, p = .05). A significant positive correlation between right anterior lenticular nucleus and psychotropic dosages was found (r = 0.4, p = .01). CONCLUSIONS: Our study provides evidence of lenticular nucleus microstructure alterations in schizophrenia, potentially sustaining cognitive and motor deficits in schizophrenia. Key points The basal ganglia structures was explored with diffusion imaging in a sizeable sample of patients affected by schizophrenia and healthy controls. Patients affected by schizophrenia showed a significantly higher ADC compared to healthy controls in the left anterior lenticular nucleus. Our study provides evidence of lenticular nucleus microstructure alterations in schizophrenia, potentially sustaining cognitive and motor deficits in schizophrenia
Image/Images: A Debate Between Philosophy and Visual Studies
No full textThe third issue of the Journal for the Philosophy of Language, Mind and the Arts is centered on a series of questions related to the nature of images. What properties characterize them? Do they exist also in our minds? What relationship do they have with phenomena such as perception, memory, language and interpretation? The authors participating in this issue have been asked to answer these and other questions starting from and in dialogue with the two philosophical perspectives that have most enriched the study of our object of research since the second half of the twentieth century: analytical philosophy and visual culture studies. The first four essays address problems related to ontology (Didi-Huberman, Prinz, Bantinaki, Manzotti). In their pages the question will be asked not only about the nature of images but also about what it means for an image to represent an object or an action realistically. The second part contains discussions related to the topics of perception, appreciation and creation of pictures (Ferretti; Gavaler, Goldberg; Pigoni, Coraci, Carlenzi). The third section goes through the problems related to the very concept of representing by images (Biggs; Weichert; Derby). The last section of the issue is devoted to two cases in which images are used not so much and not only to represent something, but also to convey ethical-political values (Fasnacht; Olesiejuk)
Can Machine Learning help us in dealing with treatment resistant depression? A review
No full textBackground: About one third of patients treated with antidepressant do not show sufficient symptoms relief and up to 15% of patients remain symptomatic even after multiple trials are applied, configuring a state called treatment resistant depression (TRD). A clear definition of this state and the understanding of underlying mechanisms contributing to chronic disability caused by major depressive disorder is still unknown. Therefore, Machine Learning (ML) techniques emerged in the last years as interesting approaches to deal with such complex problems. Methods: We performed a bibliographic search on Pubmed, Google Scholar and Medline of clinical, imaging, genetic and EEG ML classification studies on treatment-responding depression and TRD as well as studies trying to predict response to a specific treatment in already established TRD. The inclusion criteria were met by eleven studies. Seven focused on the definition of predictors of TRD onset while four attempted to predict the response to specific treatments in TRD. Results: The results showed that it seems possible to classify between responders MDD and TRD with good accuracies based on clinical variables. Moreover, some studies reported the possibility of using EEG measures to predict response to different pharmacological and non-pharmacological treatments in established TRD. Limitations: The definition of TRD, the selection of variables together with ML algorithms and pipelines varies across the studies, ultimately determining the unfeasibility to implement these models in clinical practice. Conclusions: The findings suggest that ML could be a valid approach to increase our understanding of TRD and to better classify and stratify this disorder, which may ultimately help clinicians in the assessment of major depressive disorder
Combining clozapine with cariprazine: Two case reports highlighting potential drug-drug interaction
No full textStratification of first episode psychosis based on clinical and neurobiological features: from single-center studies to big data
No full textPsychosis is a common and functionally disruptive clinical syndrome that might be present in many psychiatric, neurodevelopmental, neurologic, and medical conditions. Rather than a nosological entity, psychosis is a syndrome characterized by different symptoms and domains.
Therefore, an increasing amount of pointed out the importance of recognising and treating a first episode as soon as possible. For these reasons, first episode psychosis (FEP) rapidly became a very important population of study and assessment. More than just the first symptomatic presentation of a disease, FEP often shows already some of the features of the advanced psychiatric illnesses, although to a minor extent. On the other hand, great efforts are being made in order to establish an effective intervention, given the fact that early treatment has been proved to ameliorate the course of the disease, ranging from symptoms, relapse, and number of hospitalisations to quality-of-life measures such as involvement in school or work and global functioning.
Given the multifactorial nature of FEP and the different trajectories it can follow (e.g., affective vs. non-affective psychosis), the possibility of predicting future trajectories and
to obtain clear and valid biomarkers is becoming of paramount importance.
Prediction modelling has the potential to revolutionize medicine by predicting individual patient outcome. Early identification of those with good and poor outcomes would allow for a more personalised approach to care, matching interventions and resources to those most at need.
Through a series of studies, we explored: 1) the possibility to stratify FEP patients based on neuroimaging and biological measures; 2) the possibility of use cutting edge machine learning techniques to improve classification and cluster subtypes of FEP patients; 3) the presence of autoimmune features in FEP in a multi-site study I had the opportunity to coordinate as Co-PI (namely the PHLAMES study).
Specifically, in single-site studies we showed that neuroimaging and biological variables can be predictive of the course of the disease. Moreover, in large multi-site bid data analyses we presented how machine learning can improve the prediction of the disorder and help in stratify the risk, using both clinical and neuroimaging data. Finally, in the first results of PHLAMES study emerged that a subsample of FEP with
autoimmune characteristics might be defined. This subsample shows some unique features in terms of neurological symptoms, cognitive deficits, and brain imaging alterations.
The studies presented in this dissertation point out that it is possible to dissect the clinical and biological heterogeneity of psychosis at the beginning of its disease course, by defining meaningful groups of patients and therefore tailor personalized management. In conclusion, these data foster the research for subtypes of FEP and the definition of disease trajectories. These advances might have a great impact on patients’ lives, by defining specific subgroups or progression that benefit of tailored interventions
- …
