Skip to content

Research on an Intelligent System for Interpreting Anti-Nuclear Antibody Patterns and Titers Based on Artificial Intelligence Algorithms

Research on an Intelligent System for Interpreting Anti-Nuclear Antibody Patterns and Titers Based on Artificial Intelligence Algorithms

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600128477
Enrollment
Unknown
Registered
2026-07-21
Start date
2026-01-01
Completion date
Unknown
Last updated
2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Autoimmune disease

Interventions

ANA pattern negative:None
ANA single pattern positive:None
ANA compound pattern positive:None
Titer system validation sample:None

Sponsors

Renji Hospital, Shanghai Jiao Tong University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. ANA fluorescence image: From January 2023 to September 2025, the ANA screening project was conducted at Renji Hospital. The HEp-2 IFA fluorescence images were obtained through testing and the reports were issued normally: Positive samples: 1) Fluorescence titer = 1:80, meeting the fluorescence pattern interpretation standards of ICAP AC-1 to AC-29; 2) Single pattern positive or more than two compound pattern positive; 3) With clear clinical diagnostic information. Negative samples: 1) Fluorescence titer < 1:80; 2) Meeting the pattern interpretation standard of ICAP AC-0 as negative. 2. The fluorescence image of the HEp-2 cell matrix is clear, the staining is uniform, and there is no overexposure or blurring; 3. The image resolution is = 1920×1080 pixels, and the file format is lossless compression (such as TIFF or PNG); 4. The basic information of the patients corresponding to the samples and the preliminary clinical diagnosis (image acquisition equipment, pattern classification, titer) are recorded completely; 5. The manual interpretation results (pattern classification, titer value) have been independently reviewed and agreed upon by at least two senior laboratory physicians.

Exclusion criteria

Exclusion criteria: 1. The fluorescence images suffer from focusing blurring, uneven staining, cell rupture or background noise interference; 2. The image files are damaged or cannot be fully read; 3. Samples that do not conform to the ICAP AC-0 to AC-29 fluorescence pattern characteristics, unclear clinical diagnoses or controversial manual interpretation results; 4. Key variables (such as titer, karyotype category) are missing; 5. The patient identity information associated with the samples has not been fully anonymized; 6. The source of the samples does not comply with the approval requirements of the hospital's ethics committee regarding the secondary utilization of biological samples.

Design outcomes

Primary

MeasureTime frame
Karyotype classification accuracy;Precision;Recall;F1 score;ROC curve and AUC value;

Countries

China

Contacts

Public ContactZheng Bing

Renji Hospital, Shanghai Jiao Tong University School of Medicine

85750524@qq.com+86 21 5388 2224

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Aug 10, 2026