Authors : Palak Shori

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/v5w73pah

Scribd : https://tinyurl.com/2s2escmu

DOI : https://doi.org/10.38124/ijisrt/26apr1565

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Formal Thought Disorder (FTD) in individuals with schizophrenia and psychotic disorders is one of the adulthoodonset psychotic disorders. According to the current psychiatric guidelines of the DSM-5 and the ICD-11 manuals, FTD refers to disorders of thought form that include loosening of association, derailment, tangentiality, circumstantiality, perseveration, and incoherence. FTD requires the Scale of Assessment of Thought, Language, and Communication (TLC), Positive and Negative Symptoms Scale (PANSS), Scale of Positive Symptoms (SAPS), and diagnostic interview scales like Structured Clinical Interview for DSM Disorders (SCID). This paper proposes an NSAI (Neuro-Symbolic Artificial Intelligence) framework that integrates supervised and unsupervised machine learning techniques with symbolic clinical reasoning for the computational assessment of formal thought disorder in schizophrenia and related psychotic disorders. Transformerbased language models, such as BERT, and RNNs like LSTM, have been utilized for representation learning, and feature extraction of clinical speech and interview transcripts. Unsupervised methods utilized include K-means Clustering, Hierarchical Clustering, and Latent Dirichlet Allocation (LDA) for discovering latent linguistic structure, thematic disorganization, and emergent subtypes of thought disturbance. Supervised models, such as SVM and Extreme Gradient Boosting (XGBoost), have been implemented to classify FTD subtypes and predict symptom severity scores. On a concluding note, this paper offers an interdisciplinary view of Neuro-Symbolic AI with ML models. This hybrid framework has the potential to bridge the gap between computational efficiency and theoretical validity, offering a robust tool for early identification, differential diagnosis, and monitoring of FTDs across psychiatric populations.

Keywords : Formal Thought Disorder; Machine Learning Models; NSAI (Neuro-Symbolic AI)

References :

1. Andreasen, N. C. (1979). Thought, language, and communication disorders. I. Clinical assessment, definition of terms, and evaluation of their reliability. Archives of General Psychiatry, 36(12), 1315–1321. https://doi.org/10.1001/archpsyc.1979.01780120045006
2. Andreasen, N. C. (1986). Scale for the Assessment of Thought, Language, and Communication (TLC). Schizophrenia Bulletin, 12(3), 473–482.
3. Badie, F., & Augusto, L. M. (2022). The form in formal thought disorder: A model of dyssyntax in semantic networking. AI, 3(2), 353–370. https://doi.org/10.3390/ai3020022
4. Bedi, G., et al. (2015). Automated analysis of free speech predicts psychosis onset in high-risk youths. npj Schizophrenia, 1, Article 15030. https://doi.org/10.1038/npjschz.2015.30
5. Colombo, F., et al. (2025). Peripheral blood cells unveil neural and sex-related subtypes of depression: An unsupervised machine learning approach.
6. Garcez, A. d'Avila, & Lamb, L. C. (2019). Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning.
7. Kay, S. R., Fiszbein, A., & Opler, L. A. (1987). The Positive and Negative Syndrome Scale (PANSS) for schizophrenia. Schizophrenia Bulletin, 13(2), 261–276. https://doi.org/10.1093/schbul/13.2.261
8. Kumar, A. (2023). Neuro symbolic AI in personalized mental health therapy: Bridging cognitive science and computational psychiatry. World Journal of Advanced Research and Reviews, 19(2), 1663–1679. https://doi.org/10.30574/wjarr.2023.19.2.1516
9. Montague, P. R., Dolan, R. J., Friston, K. J., & Dayan, P. (2012). Computational psychiatry. Trends in Cognitive Sciences, 16(1), 72–80. https://doi.org/10.1016/j.tics.2011.11.018
10. Oeztuerk, O. F., et al. (2021). The clinical relevance of formal thought disorder in the early stages of psychosis: Results from the PRONIA study. World Psychiatry, 20(1), 120–129.
11. Sarzynska-Wawer, J., Wawer, A., Pawlak, A., Szymanowska, J., Stefaniak, I., Jarkiewicz, M., & Okruszek, L. (2021). Detecting formal thought disorder by deep contextualized word representations. Psychiatry Research, 304, Article 114135. https://doi.org/10.1016/j.psychres.2021.114135
12. Zakowicz, P. T., et al. (2025). Detection of formal thought disorders in child and adolescent   psychosis using machine learning and neuro-psychometric data.