Abstract and Introduction
Purpose of review: After more than a century of neuroscience research, reproducible, clinically relevant biomarkers for schizophrenia have not yet been established. This article reviews current advances in evaluating the use of language as a diagnostic or prognostic tool in schizophrenia.
Recent findings: The development of computational linguistic tools to quantify language disturbances is rapidly gaining ground in the field of schizophrenia research. Current applications are the use of semantic space models and acoustic analyses focused on phonetic markers. These features are used in machine learning models to distinguish patients with schizophrenia from healthy controls or to predict conversion to psychosis in high-risk groups, reaching accuracy scores (generally ranging from 80 to 90%) that exceed clinical raters. Other potential applications for a language biomarker in schizophrenia are monitoring of side effects, differential diagnostics and relapse prevention.
Summary: Language disturbances are a key feature of schizophrenia. Although in its early stages, the emerging field of research focused on computational linguistics suggests an important role for language analyses in the diagnosis and prognosis of schizophrenia. Spoken language as a biomarker for schizophrenia has important advantages because it can be objectively and reproducibly quantified. Furthermore, language analyses are low-cost, time efficient and noninvasive in nature.
After more than a century of neuroscience research, reproducible, clinically relevant biomarkers for schizophrenia have not yet been established. While early clinical diagnosis or relapse of a schizophrenia-spectrum disorder can be rather straightforward if there is a good working alliance between patient and psychiatrist, lack in trust, little disease insight and failing motivation may result in insufficient anamnestic information. In these situations, an objective quantitative biomarker to aid the diagnostic or prognostic process would be most welcome. However, blood-based and neuroimaging biomarkers for schizophrenia fail to reach clinically applicable levels,[2–4] with diagnostic accuracies varying between 60 and 90%. A rich source of information that has so far rarely been used, is spoken language. Recent advances in the field of computational linguistics afford the clinician to turn to language output as a novel biomarker that is low-cost, time efficient and noninvasive in nature. Language as a biomarker has important advantages over traditional biomarkers such as blood markers or imaging, because it can be reproducibly quantified without special training.
It has long been observed that schizophrenia is characterized by disturbed language, with Kraepelin describing a subgroup of patients with 'schizophasia', and Bleuler who stressed the importance of aberrant language as a feature of schizophrenia. Pioneers in this line of research applied manual linguistic analyses to spoken language to evaluate its use in the diagnostic or prognostic process in schizophrenia-spectrum disorders.[8–10]
Here, we reviewed the use of computational language analysis in schizophrenia-spectrum disorders with an emphasis on how recent translational research contributes to the development of diagnostic and prognostic tools. Much of the recent literature relates to advances in methodological and analytic tools which may facilitate diagnosis and prognosis of schizophrenia-spectrum disorders.
Curr Opin Psychiatry. 2020;33(3):212-218. © 2020 Lippincott Williams & Wilkins