Automated Speech-Based Modeling of Item-Level Symptom Severity in Schizophrenia - Report - MDSpire

Automated Speech-Based Modeling of Item-Level Symptom Severity in Schizophrenia

  • By

  • Silvia Ciampelli

  • Janna N. de Boer

  • Sanne Koops

  • Evan Troelstra

  • Almut Jebens

  • Jan-Bernard C. Marsman

  • Arnout C. Smit

  • Amir Hossein Nikzad

  • Ryan Partlan

  • Philipp Homan

  • Wolfram Hinzen

  • Sunny X. Tang

  • Iris E. C. Sommer

  • June 25, 2026

  • 0 min

Share

Clinical Report: Speech Analysis for Assessing Symptom Severity in Schizophrenia

Overview

This study investigates the relationship between speech characteristics and symptom severity in schizophrenia, utilizing automated speech recognition and natural language processing.

Background

Speech is a critical medium for expressing mental states in psychiatry, yet quantifying its changes has been challenging. Alterations in speech can precede relapse in psychosis, making it essential to develop methods for monitoring these changes. Recent advancements in technology offer new opportunities for scalable and precise assessments of psychotic symptoms through speech analysis.

Data Highlights

No numerical data or trial data provided in the source material.

Key Findings

  • Speech samples were collected from Dutch and US cohorts to assess symptom severity using PANSS and BPRS scales.
  • Automated pipelines extracted various speech features, including acoustic, syntactic, semantic, and sentiment characteristics.
  • Specific linguistic markers, such as reduced syntactic complexity and lower speech quantity, were associated with symptom fluctuations.
  • The study aimed to determine the accuracy of speech-based models in detecting individual symptoms like hallucinations and blunted affect.

Clinical Implications

The study highlights the potential of using speech analysis as a tool for monitoring symptom severity in schizophrenia. Clinicians may consider integrating automated speech recognition technologies to enhance their assessment capabilities.

Conclusion

This research underscores the feasibility of utilizing speech characteristics to monitor psychotic symptoms, paving the way for innovative approaches in psychiatric care.

Related Resources & Content

  1. npj Digital Medicine, 2025 -- Modeling Variability in Multimodal Speech Analysis Throughout the Psychosis Spectrum
  2. BMC Psychiatry, 2025 -- Application of PANSS-6 in the assessment of severity and improvement in patients with schizophrenia
  3. JAMA Network Open, 2025 -- The Promise of Artificial Intelligence–Powered Speech Biomarkers in Psychiatry
  4. Frontiers in Psychiatry, 2026 -- Tracking the dynamic breakdown of contextual coherence in schizophrenia using language models
  5. Die neue S3-Leitlinie Schizophrenie (living) 2025 | Der Nervenarzt, 2026
  6. Die neue S3-Leitlinie Schizophrenie (living) 2025 | Der Nervenarzt | Springer Nature Link
  7. Speech-based computational approaches for classification and symptom monitoring in schizophrenia spectrum disorders: a systematic review and meta-analysis - PMC
  8. Predicting PANSS symptoms in schizophrenia spectrum disorders using speech only: an international, multi-centre, retrospective, computational study across multiple languages | medRxiv

Original Source(s)

Related Content