About this Research Topic
Schizophrenia is a heterogeneous disorder characterized by disruptions in neural circuits, fragmentations of thought, disorganized and/or impoverished speech, praxis and social interactions. Several studies have shown that speech behavior in particular plays a central role in the symptomatology and diagnostic of patient outcome. A large body of clinical evidence suggests that early detection of schizophrenia spectrum disorder (SSD) and adequate care management and psychosocial interventions can help patients recover from the disease and integrate with the community. In this context, the evaluation of spoken language of patients with SSD or at risk of developing schizophrenia is of the utmost interest. However, linguistic biomarkers extraction is a difficult task even with machine learning tools or artificial neural networks. Also, viewed in isolation most linguistic markers still lack of specificity for Schizophrenia and there is a need of integrating/combining them to improve detection of at risk patients.
Speech can be divided into several linguistic categories for which machine learning tools and Artificial Neural Networks (ANN) techniques have shown interesting results. As examples, intonation, neologisms, paraphasia or reduced syntactic complexity represent good features of the deficit. With natural language processing techniques (e.g., LSA, Parsing), it is a whole collection of new features that appears to participate to the clinical picture of SSD and clinical high risk for psychosis (CHR-P).
Unfortunately, the best cocktail mixing linguistic features alterations still remains to be discovered and most of these alterations are not specific to schizophrenia nor to psychosis.
The objective of this special edition is to bring together the most advanced studies in the field of predicting the future of patients with SSD and/or CHR-P from linguistic markers. To think about how these linguistic markers can be mixed in different pathological contexts and trajectories. We are also aiming for the possibility of bringing together studies that attempt to improve diagnostic methods through the classification of patient with SSD, the evaluation of therapeutics side-effects and most of all, the prediction of CHR-P and SSD patient clinical evolution.
The goal of this special issue aims to gather and assemble studies proposing new classification or risk prediction models based on linguistic markers. Even if the special issue is not dedicated anymore to imaging results, particular attention will be paid to the studies that attempts to establish a direct link between language deficits and neurophysiological markers through theoretical discussion and/or models. As it has already been said, taken in isolation, linguistic features are not only insufficient but also unspecific. Integrating them in larger models would probably help to focus on pertinent findings and assist in the identification of high-risk subjects.
This special topic on schizophrenia and language will focus on features combinations more than individual markers/biomarkers.
Will be accepted:
1) Original research articles
2) Systematic Reviews
Speech can be divided into several linguistic categories for which machine learning tools and Artificial Neural Networks (ANN) techniques have shown interesting results. As examples, intonation, neologisms, paraphasia or reduced syntactic complexity represent good features of the deficit. With natural language processing techniques (e.g., LSA, Parsing), it is a whole collection of new features that appears to participate to the clinical picture of SSD and clinical high risk for psychosis (CHR-P).
Unfortunately, the best cocktail mixing linguistic features alterations still remains to be discovered and most of these alterations are not specific to schizophrenia nor to psychosis.
The objective of this special edition is to bring together the most advanced studies in the field of predicting the future of patients with SSD and/or CHR-P from linguistic markers. To think about how these linguistic markers can be mixed in different pathological contexts and trajectories. We are also aiming for the possibility of bringing together studies that attempt to improve diagnostic methods through the classification of patient with SSD, the evaluation of therapeutics side-effects and most of all, the prediction of CHR-P and SSD patient clinical evolution.
The goal of this special issue aims to gather and assemble studies proposing new classification or risk prediction models based on linguistic markers. Even if the special issue is not dedicated anymore to imaging results, particular attention will be paid to the studies that attempts to establish a direct link between language deficits and neurophysiological markers through theoretical discussion and/or models. As it has already been said, taken in isolation, linguistic features are not only insufficient but also unspecific. Integrating them in larger models would probably help to focus on pertinent findings and assist in the identification of high-risk subjects.
This special topic on schizophrenia and language will focus on features combinations more than individual markers/biomarkers.
Will be accepted:
1) Original research articles
2) Systematic Reviews
Keywords: Schizophrenia, Natural language processing, machine learning, Speech, Clinical High Risk for Psychosis
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
