¹Asklepios Klinik Bad Abbach, Rheumatologie, Bad Abbach
²medac GmbH, Wedel
³Uniklinikum Regensburg, Innere Medizin I, Regensburg

Text

Background: Autoantibodies against cell nuclei (ANA) play a crucial role in diagnosing autoimmune diseases, particularly connective tissue diseases. The gold standard for ANA detection is the visual interpretation of indirect immunofluorescence testing (VI-IIFT) using human epithelial (HEp-2) cells [1]. Since this method is time-consuming and labor-intensive, research is focusing on automated evaluation systems utilizing artificial intelligence (AI).

Methods: A total of 143 consecutive serum samples from routine clinical care were collected from patients visiting our tertiary Rheumatology center, and included in the study. For these samples, both VI-IIFT (with ANA HEp-2 cells from AESKU, Germany) and an AI-based method for automated evaluation of processed immunofluorescence slides (akiron^® NEO by Medipan) were performed [2]. Titer levels and the International Consensus on ANA Patterns (ICAP) classification were analyzed. The primary outcomes included sensitivity, specificity, and concordance of titer concentration.

Results: Of the 143 analyzed samples, VI-IIFT, as the gold standard, classified 40 samples (28%) as negative and 102 (72%) as positive, whereas the automated interpretation identified 69 samples (48.3%) as negative and 74 (51.7%) as positive. When compared to the reference standard, the AI-based method showed no false-positive results, yielding a specificity of 100%. However, its sensitivity was limited to 71.8%.

The ICAP classification was most reliable for AC-3, where specificity reached 100%. Notably, titer levels in the automated evaluations were frequently assessed at higher values than in the gold standard interpretation.

Conclusion: Our study demonstrated a specificity of 100% for AI-assisted ANA interpretation compared to the gold standard VI-IIFT. However, sensitivity was only 71.8%, indicating a need for further optimization. Further research and algorithm refinement (e.g., improved pattern recognition and titer calibration) are necessary to enhance sensitivity and support its future implementation as a reliable screening method.

Disclosures: The study was supported by Medipan, which provided the akiron^® NEO analyzer.

References

[1] Alsuwaidi M, Dollinger M, Fleck M, Ehrenstein B. The Reliability of a Novel Automated System for ANA Immunofluorescence Analysis in Daily Clinical Practice. Int J Rheumatol. 2016;2016:6019268. DOI: 10.1155/2016/6019268
[2] Medipan & GA Generic Assays. 4450 – akiron® NEO. [accessed 2025 Mar 16]. Available from: https://www.medipan.de/products/akiron-neo/