Skip to main content
OpenTrials
Recruiting

NCT Number: NCT06511713

AI-Assisted Rapid Warning for Mental Disorders Based on High-Resolution Fundus Imaging and High-Speed Eye-Tracking

This project aims to collect eye-tracking trajectories and fundus imaging data from individuals seeking mental health services. By utilizing artificial intelligence, combining dynamic (eye-tracking) and static (fundus) data, and employing convolutional neural network analysis methods, the investigators will develop models for the classification and early warning of common mental disorders. These models will assist clinicians in making objective diagnoses of common mental disorders and in predicting the risk of adverse outcomes, thereby addressing the significant technical bottleneck of the current lack of objective diagnostic and warning instruments for mental disorders.

Recruiting

Interested in participating?

Request Info

Key information

Age range

15 year–45 year

Sex eligibility

All sexes

Study type

Observational

Primary location

Shanghai Mental Health Center

Shanghai, Shanghai Municipality, 200030, China

Location status: Recruiting

Location contact

TianHong Zhang, Doctor

CONTACT

[email protected]

13127577024

About this study

The investigators have completed the construction of the eye-tracking diagnostic and warning system and have piloted the new system. The plan is to recruit 1,000 individuals at Clinical High Risk for Psychosis (CHR) for model validation of predictive outcomes, and 1,000 patients with common mental disorders for model validation of diagnostic classification. This cohort includes 300 patients with schizophrenia, 300 patients with affective disorders, 200 patients with anxiety disorders, and 200 patients with cognitive impairment in the elderly. The system will also directly connect with the investigators' previous research data collection system and be deployed in no fewer than one hospital's healthcare system. Additionally, variables that may affect the accuracy of results will be fine-tuned to ensure that the eye-tracking and fundus system more accurately reflects actual clinical conditions. The application of the system will revolve around a big data analysis platform and seamlessly integrate with the existing hospital information systems, designing real-time feedback report modules to assist clinicians in making objective diagnoses efficiently and effectively.

Who can participate

Healthy volunteers accepted: No

Only the study team can determine whether someone qualifies for participation.

Inclusion criteria

  • be aged 14 to 45-year-old
  • have had at least 6-years of primary education
  • be drug-naïve
  • be understanding the survey, be willing to enrol in the study and sign the informed consent
  • Through the Structured Interview for Prodromal Syndromes/Scale of Prodromal Symptoms (SIPS/SOPS), the participants should meet the Criteria of Prodromal Syndrome. Participants should fulfil at least one of the prodromal syndrome criteria: (1) brief intermittent psychotic syndrome, (2) attenuated positive symptom syndrome, or (3) genetic risk and deterioration syndrome
  • Meets ICD-11 diagnostic criteria for schizophrenia
  • Meets ICD-11 diagnostic criteria for mood disorders
  • Meets ICD-11 diagnostic criteria for anxiety disorders
  • Meets ICD-11 diagnostic criteria for neurocognitive disorders

Exclusion criteria

  • Acute or chronic renal failure; liver cirrhosis or active liver diseases
  • Abnormal laboratory tests results judged by the researchers to be clinically significant and considered to affect the efficacy of the test drugs or the safety of the subjects
  • Severe or unstable physical diseases, including: neurological disorders (delirium, dementia, stroke, epilepsy, migraine, etc.), congestive heart failure, angina pectoris, myocardial infarction, arrhythmia, hypertension (including untreated or uncontrolled hypertension), malignant tumours, immune compromise, and blood glucose above 12 mmol/L
  • Alcohol abuse within 30 days, or alcohol or drug dependence within 6 months before the trial
  • Pregnant or lactating women, or women in childbearing age who are positive in urine human chorionic gonadotropin test, or men and women who do not take effective contraceptive measures or plan for pregnancy within 3 months after the initiation of the trial
  • Stroke within the last month
  • Participating in any clinical trial within 30 days before the baseline
  • Other situations judged by the investigators not to be suitable for the clinical trial

Treatment and study plan

Routine clinical treatment

Other

Participants will be informed that this is not a treatment study and it involves naturalistic follow-up without any extra intervention. They will otherwise follow the routine clinical treatment procedure.

Primary outcomes

  1. Eye-tracking fixation point trajectory

    Time frame: 1 year

    Eye-tracking fixation point trajectory during free viewing of specific images by the participant (5 minutes)

  2. Fundus examination

    Time frame: 1 year

    Color fundus imaging collected by a digital fundus camera (Canon CR-2) under non-mydriatic conditions of the participant

Study contacts

Contact information is provided by the study sponsor or research team.

TianHong Zhang, Doctor

CONTACT

[email protected]

13127577024

Sponsors and collaborators

Lead sponsor

Shanghai Mental Health Center

Other

Registry information

Official study title

Artificial Intelligence-Assisted Rapid Warning for Mental Disorders Based on High-Resolution Fundus Images and High-Speed Eye-Tracking Trajectories

Important dates

Study start
2024
Primary completion
2025
Study completion
2025
First posted
Jul 22, 2024
Registry last updated
Jul 23, 2024

OpenTrials presents study information sourced from ClinicalTrials.gov. The official registry record should be consulted for the latest information.

View the official ClinicalTrials.gov record (opens in a new tab)

This listing is for discovery and informational purposes only. It is not medical advice, does not guarantee that a study is recruiting, and does not determine eligibility. Contact the study team and a qualified healthcare professional when considering participation.

Published trials that share one or more normalized conditions with this study.