EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An integrative NLP framework identifies multilevel linguistic phenotypes of schizophrenia across tasks

Hironobu Nakamura iD, Yoshinobu Kano, Genichi Sugihara, Ryo Takemura iD, Yusei Yamaguchi, Masaaki Shimizu iD, Shunsuke Takagi iD, Mari Iizuka, Saaya Tashiro, Momoko Kitazawa, Ayako Sento, Hidehiko Takahashi und 1 weitere

Psychological Medicine · 2026 · 56

DOI: 10.1017/s0033291726104668 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Psychological Medicine, online erschienen am 23.06.2026. Verfasst von Hironobu Nakamura und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry and Behavioral Sciences, Institute of Science Tokyo, Japan. Hauptthemen laut MEDLINE: Schizophrenia, Linguistics, Natural Language Processing, Language Disorders. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Corporation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Linguistic abnormalities in schizophrenia (SCZ) span morphological, syntactic, semantic, and discourse levels. Converging cross-linguistic evidence suggests that SCZ may involve semantic narrowing alongside reduced syntactic differentiation, yet how these changes co-occur across linguistic domains and whether they represent core, task-general disturbances remains unclear. We applied a multilevel NLP framework to a large Japanese dataset to identify structurally related linguistic markers of SCZ across elicitation contexts.

Methods

Speech from 104 patients with SCZ and 101 healthy controls was collected through semi-structured interviews. Transcripts from free conversation, storytelling, and picture description were analyzed using GiNZA, Word2Vec, TF-IDF, and SentenceBERT to extract 76 morphosyntactic, semantic, and discourse features. Factor analysis identified representative features independent of diagnosis, which were tested using generalized estimating equations and validated with bootstrap and permutation procedures. Cross-task stability was examined to determine core linguistic markers.

Results

In free conversation, reduced Case-particle (Kakujoshi) and Adverb use and increased Mean Pairwise Word Similarity were strongly associated with SCZ (AUC = 0.87, 95% CI: 0.74–0.97). Adverbial, case-particle, and semantic-network measures functioned as cross-task markers.

Conclusions

SCZ involves multidimensional language disturbances characterized by a tripartite linguistic phenotype of diminished morphosyntactic explicitness, semantic narrowing, and reduced modification-based contextual modulation in spontaneous discourse. Extending cross-linguistic evidence, our results indicate that lexical-semantic contraction co-occurs with reduced overt marking of argument relations in Japanese, alongside weakened adverbial elaboration and framing – suggesting convergent, largely task-general dimensions of SCZ language pathology, most evident in free conversation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SchizophreniaLinguisticsNatural Language ProcessingLanguage DisordersHumansFemaleAdultMalePhenotypeMiddle AgedJapan

Stichwörter der Autor:innen

computational psychiatrydiagnosislanguagenatural language processingschizophrenia

Autor:innen und Institutionen

  • Department of Psychiatry and Behavioral Sciences, Institute of Science Tokyo, Japan.
  • Faculty of Informatics, Shizuoka University, Shizuoka Daigaku, Japan.
  • Clinical and Translational Research Center, Keio University Hospital, Keio University: Keio Gijuku Daigaku, Japan.
  • Department of Neuropsychiatry, Keio University School of Medicine, Keio University: Keio Gijuku Daigaku, Japan.
  • Institute of Science Tokyo School of Medicine, Institute of Science Tokyo, Japan.
  • Center for Promotion of Interdisciplinary Research in Medicine and Life Science, Keio University School of Medicine, Keio University: Keio Gijuku Daigaku, Japan.

ORCID-Profile: Hironobu Nakamura, Ryo Takemura, Masaaki Shimizu, Shunsuke Takagi

Förderung

  • Japan Science and Technology Corporation

Zitieren

APA

Nakamura, H., Kano, Y., Sugihara, G., Takemura, R., Yamaguchi, Y., Shimizu, M., Takagi, S., Iizuka, M., Tashiro, S., Kitazawa, M., Sento, A., Takahashi, H., & Taishiro, K. (2026). An integrative NLP framework identifies multilevel linguistic phenotypes of schizophrenia across tasks. Psychological Medicine, 56. https://doi.org/10.1017/s0033291726104668

Vancouver

Nakamura H, Kano Y, Sugihara G, Takemura R, Yamaguchi Y, Shimizu M, et al. An integrative NLP framework identifies multilevel linguistic phenotypes of schizophrenia across tasks. Psychological Medicine. 2026;56. doi:10.1017/s0033291726104668

BibTeX
@article{Nakamura2026,
  author = {Nakamura, Hironobu and Kano, Yoshinobu and Sugihara, Genichi and Takemura, Ryo and Yamaguchi, Yusei and Shimizu, Masaaki and Takagi, Shunsuke and Iizuka, Mari and Tashiro, Saaya and Kitazawa, Momoko and Sento, Ayako and Takahashi, Hidehiko and Taishiro, Kishimoto},
  title = {An integrative NLP framework identifies multilevel linguistic phenotypes of schizophrenia across tasks},
  journal = {Psychological Medicine},
  year = {2026},
  volume = {56},
  doi = {10.1017/s0033291726104668}
}
Kostenlos starten →