No abstract

The language and speech of individuals with psychosis reflect their impairments in cognition and motor processes. These language disturbances can be used to identify individuals with and at high risk for psychosis, as well as help track and predict symptom progression, allowing for early intervention and improved outcomes. However, current methods of language assessment—manual annotations and/or clinical rating scales—are time intensive, expensive, subject to bias, and difficult to administer on a wide scale, limiting this area from reaching its full potential. Computational methods that can automatically perform linguistic analysis have started to be applied to this problem and could drastically improve our ability to use linguistic information clinically. In this article, we first review how these automated, computational methods work and how they have been applied to the field of psychosis. We show that across domains, these methods have captured differences between individuals with psychosis and healthy controls and can classify individuals with high accuracies, demonstrating the promise of these methods. We then consider the obstacles that need to be overcome before these methods can play a significant role in the clinical process and provide suggestions for how the field should address them. In particular, while much of the work thus far has focused on demonstrating the successes of these methods, we argue that a better understanding of when and why these models fail will be crucial toward ensuring these methods reach their potential in the field of psychosis.

No abstract

Thought disorder -linguistic disturbances including incoherence and derailment of topicis seen in individuals both with and at risk for psychosis. Methods from computational linguistics have increasingly sought to quantify thought disorder to detect group differences between clinical populations and healthy controls. While previous work has been quite successful at these classification tasks, the lack of interpretability of the computational metrics has made it unclear whether they are in fact measuring thought disorder. In this paper, we dive into these measures to try to better understand what they reflect. While we find group differences between at-risk and healthy control populations, we also find that the measures mostly do not correlate with existing measures of thought disorder symptoms (what they are intended to measure), but rather correlate with surface properties of the speech (e.g., sentence length) and sociodemographic properties of the speaker (e.g., race). These results highlight the importance of considering interpretability front and center as the field continues to grow. Ethical use of computational measures like those studied here -especially in the high-stakes context of clinical care -requires us to devote substantial attention to potential biases in our measures.

This commentary argues that to increase diversity in language acquisition research, the field should define specific, measurable, attainable, relevant, and time-defined goals, and prioritize solutions based on their importance, tractability and neglectedness, ideally in collaboration with a variety of other agents outside the research community