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
Clinical Scorecard: Speech Analysis for Assessing Symptom Severity at the Item Level in Schizophrenia
At a Glance
Category Detail
Condition Schizophrenia Key Mechanisms Automated speech recognition and natural language processing for monitoring psychotic symptoms. Target Population Adults aged 18 years or older with schizophrenia spectrum or bipolar I disorder. Care Setting Multicenter cohort studies in clinical settings.
Key Highlights
Speech alterations can precede relapse in psychosis. Automated speech analysis can track symptom fluctuations. Study utilized PANSS and BPRS for symptom assessment. Speech features extracted include acoustic, syntactic, semantic, and sentiment. Principal component analyses were conducted to interpret speech-language components. Guideline-Based Recommendations
Diagnosis
Use structured diagnostic interviews according to DSM-IV and DSM-5 criteria. Management
Monitor symptom severity using speech-based models. Monitoring & Follow-up
Implement high-frequency monitoring of speech to detect early signs of relapse. Risks
Consider background characteristics such as age, sex, and education in assessments. Patient & Prescribing Data
Adults with confirmed diagnoses of schizophrenia spectrum or bipolar I disorder.
Speech analysis may provide real-time monitoring of psychotic symptoms.
Clinical Best Practices
Incorporate speech analysis into routine psychiatric assessments. Utilize longitudinal follow-up to track symptom changes. Ensure informed consent and ethical approval for studies. Related Resources & Content
