Multi-modal deep learning model for bipolar depression adolescents with verbal auditory hallucinations - Takeaways - MDSpire

Multi-modal deep learning model for bipolar depression adolescents with verbal auditory hallucinations

  • By

  • Qinnaer Bolatijiang

  • Shaohong Zou

  • Cheng Zhang

  • Chengji Wang

  • Jianliang Zhang

  • June 19, 2026

  • 0 min

Share

  • 1

    A multimodal deep learning model was developed to classify adolescents with bipolar depression experiencing verbal auditory hallucinations.

  • 2

    The study analyzed 47 untreated adolescent bipolar depression patients, dividing them into hallucination and non-hallucination groups based on PANSS P3 scores.

  • 3

    The model achieved a classification accuracy of 71.43%, demonstrating balanced performance for both positive and negative samples.

  • 4

    Key features of the model include bidirectional cross-attention, CBAM attention integration, and dynamic expert mixing for improved classification.

  • 5

    Magnetic Resonance Spectroscopy was utilized to collect data, allowing for the integration of clinical parameters and MRS-derived features.

Original Source(s)

Multi-modal deep learning model for bipolar depression adolescents with verbal auditory hallucinations

  • by Qinnaer Bolatijiang, Shaohong Zou, Cheng Zhang, Chengji Wang, Jianliang Zhang

  • June 19, 2026

Related Content

Explainable machine learning unveils the key role of cooperation ability in school bullying and its gender-differentiated impact on cooperative atmosphere

Postnatal maternal mental health-related hospitalisation and its association with adverse child health and maltreatment outcomes: narrative review

When Bad Data Enters the Drug Pipeline

Federal prosecutors allege that a Florida physician and research staff fabricated clinical trial records that were submitted into database systems used to evaluate investigational drugs.