Assessing Schizophrenia Patients Through Linguistic and Acoustic Features Using Deep Learning Techniques.

Area of Science:

• Psychiatry
• Computational Linguistics
• Machine Learning

Background:

• Thought, language, and communication disorders are key features of schizophrenia.
• Assessing these disorders is vital for patient monitoring and early risk detection.
• Current assessment methods are resource-intensive, requiring trained clinicians.

Purpose of the Study:

• To develop an automated machine learning method for assessing schizophrenia thought disorder severity.
• To leverage both textual and acoustic speech features for prediction.
• To provide a scalable tool for clinical support.

Main Methods:

• Utilized a Transformer-based machine learning model.
• Integrated semantic, syntactic, and acoustic features from patient-clinician conversations.
• Trained and evaluated the model on schizophrenia patient data.

Main Results:

• The proposed model accurately predicts the severity of thought disorder in schizophrenia patients.
• The model demonstrated effectiveness in analyzing speech patterns for diagnostic insights.
• Experimental results indicate a strong correlation with clinical assessments.

Conclusions:

• The developed machine learning model offers a promising automated solution for schizophrenia thought disorder assessment.
• This tool can assist clinicians by providing objective, data-driven insights.
• Potential to improve patient care through efficient and accessible symptom tracking.