An Exploratory Study on the Prediction of Recurrence Risk of Bipolar Disorder Using Sentiment Analysis Technology Based on Multi-modal Feature Fusion

NCT07573839 | Recruiting

• 1 other identifier: 8247054596
• Study Type: observational
• Target: 400
• Locations: 1 country
• Sites: 1

Brief Summary

Bipolar disorder (BD) has become a significant public health problem with complex clinical manifestations, difficult treatment, and poor prognosis. However, there is still a lack of effective biological markers for diagnosing and predicting recurrence. Sentiment analysis computing usually refers to using machine equipment to classify, identify, interpret, and imitate human emotions. However, current multi-modal emotion analysis research is mainly based on one or two modalities. Due to the diversity and complexity of patients' emotional expressions, this single- and dual-modal information analysis is far from enough for accurate discrimination of emotional symptoms. Only emotion analysis technology based on multi-modal feature fusion can make more precise and effective judgments. The current project is based on our previous research on cognitive neuroimaging and big data analysis of bipolar disorder. The investigators plan to enroll 200 BD patients who meet DSM-5 diagnostic criteria and 200 healthy controls. The investigators will use sentiment analysis technology with multi-modal feature fusion (text data, audio and visual modalities, eye movements, and electrophysiology) to identify BD recurrence. Biological markers for risk prediction and an algorithm model for joint judgment of multi-source information will be established to analyze the characterization data. The effectiveness of this recurrence prediction model will be further verified and optimized through a large-sample, prospective cohort study design. It is hoped that it can provide a new method for predicting the recurrence risk of BD patients. In the near future, clinical decision-making aids based on this auxiliary method can be developed, and the translational application value of clinical diagnosis and treatment can be explored.

Conditions

Bipolar Disorder (BD); Healthy Control

Outcome Measures

Primary Outcomes (1)

• The recurrence status of patients with bipolar disorder

  The presence and the type of a relapse will be diagnosed by psychiatrists and assessed using DSM-5 by study assistants. Furthermore, predictive models for recurrence risk of bipolar disorder will be constructed, with adopting the Area Under Curve (AUC) of Receiver Operating Characteristic (ROC) and other measurements to evaluate the performance of constructed models.

  1 year, patients will be followed-up every 3 months and healthy controls will be assessed only at baseline

Study Arms (2)

patients with bipolar disorder

Other: This is an observational study with no intervention.

healthy control

Other: This is an observational study with no intervention.

Interventions

This is an observational study with no intervention. OTHER

This is an observational study with no intervention.

healthy control; patients with bipolar disorder

Eligibility Criteria

• Age: 18 Years - 64 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

1\. patients with bipolar disorder; 2. healthy controls.

You may qualify if:

• Patients who have previously met or currently meet the diagnostic criteria for bipolar disorder according to DSM-5, whose condition and treatment are currently stable, and who cooperate with the assessment;
• Age ≥18 years, \<65 years;
• Han Chinese ethnicity;
• Sufficient visual and auditory abilities to complete the necessary examinations for the study;
• Understanding the study content and signing the informed consent form. If the patient is unable to sign the informed consent form personally due to low education level or other reasons, it may be signed by a relative or guardian on their behalf.

You may not qualify if:

• The presence of intellectual disability or other conditions that significantly affect the patient's current mental state;
• the patient has a serious or unstable physical illness, including: neurological disorders (delirium, dementia, stroke, epilepsy, migraine, etc.), congestive heart failure, angina pectoris, myocardial infarction, arrhythmia, hypertension (including untreated or uncontrolled hypertension), malignant tumors, immunodeficiency, and blood glucose levels higher than 12 mmol/L; or other diseases that may interfere with the test assessment (abnormal indicators more than twice the normal value).
• Age ≥ 18 years, \< 65 years;
• Han Chinese ethnicity;
• Gender matched to the patient group;
• Sufficient visual and auditory ability to complete the necessary examinations for the study;
• Understanding of the study content and signing of informed consent;
• Individuals with a mental disorder conforming to DSM-5, or those with suspicious mental symptoms but not meeting the diagnostic criteria;
• Individuals with severe physical illness that makes it difficult to complete the necessary examinations.

Sponsors & Collaborators

• Shanghai Mental Health Center: lead

Study Sites (1)

Shanghai Mental Health Center

Shanghai, China

RECRUITING

MeSH Terms

Conditions

Bipolar Disorder

Condition Hierarchy (Ancestors)

Bipolar and Related Disorders; Mood Disorders; Mental Disorders

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Chief Physician

Study Record Dates

• First Submitted: April 13, 2026
• First Posted: May 7, 2026
• Study Start: April 1, 2026
• Primary Completion (Estimated): December 1, 2027
• Study Completion (Estimated): December 1, 2027
• Last Updated: May 7, 2026

Record last verified: 2026-05

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)