KL-6 in ANCA-Associated Vasculitis Patients with and without ILD: A Machine Learning Approach
Edoardo Conticini1, Miriana d'Alessandro2, Laura Bergantini2
1Rheumatology Unit, Department of Medicine, Surgery & Neurosciences, University of Siena, 53100 Siena, Italy.
Background:
ANCA-associated vasculitis (AAV) are small vessel vasculitis distinguished between microscopic polyangiitis (MPA) and granulomatosis with polyangiitis (GPA). The former may have interstitial lung disease (ILD) associated with high morbidity and mortality. Here, Krebs von den Lungen-6 (KL-6), a marker of fibrotic ILD, was assessed for distinguishing AAV patients with ILD from those without ILD, and whether its changes over time are correlated with disease activity.
Materials And Methods:
Thirteen AAV patients (eight females, mean age 61 ± 14.8 years) were enrolled: six MPA and six GPA. Serum samples were assayed for KL-6 concentrations (Fujirebio Europe, Belgium). To investigate potential binary classifiers for diagnosis of AAV-ILD, we constructed a regression decision tree model.
Results:
Higher serum KL-6 were in AAV-ILD compared with those without ILD (972.8 ± 398.5 vs 305.4 ± 93.9, p = 0.0040). Area under the receiver operating characteristics curve showed 100% of the diagnostic performance of KL-6 for identifying the ILD involvement (accuracy 91.7%) and the best cutoff value of 368 U/mL (sensitivity 100% and specificity 87.5%). The decision tree model showed a 33% improvement in class purity using a cut-off value of 513 U/mL to distinguish AAV patients with and without ILD. Stratifying AAV patients as MPA and GPA with and without ILD considering T0 and T1 KL-6, the model obtained an improvement of 40% for classifying GPA non-ILD with a T0 serum KL-6 cut-off value of 513 U/mL and a T1 KL-6 cut-off of 301 U/mL. A direct correlation was found between serum T0 KL-6 and T0 BVAS (r = 0.578, p = 0.044).
Conclusion:
Our multicenter study demonstrated KL-6 as a reliable, non-invasive, and easy-to-perform marker of ILD in AAV patients and its helpfulness for disease activity assessment. Changes in serum concentrations of KL-6 over time could be useful for monitoring AAV patients. Further study of KL-6 as a marker of response to therapy during long-term follow-up would also be worthwhile.
Insights
Krebs von den Lungen-6 (KL-6) effectively identifies interstitial lung disease (ILD) in ANCA-associated vasculitis (AAV) patients. Elevated KL-6 levels correlate with disease activity, suggesting its utility in monitoring AAV patients.
Area of Science:
- Pulmonary Medicine
- Rheumatology
- Biomarker Research
Background:
- ANCA-associated vasculitis (AAV) encompasses microscopic polyangiitis (MPA) and granulomatosis with polyangiitis (GPA).
- Interstitial lung disease (ILD) is a significant complication of MPA, leading to high morbidity and mortality.
- Krebs von den Lungen-6 (KL-6) is a recognized biomarker for fibrotic ILD.
Purpose of the Study:
- To evaluate KL-6 as a diagnostic marker for ILD in AAV patients.
- To assess the correlation between serum KL-6 levels and AAV disease activity.
- To explore the utility of KL-6 in differentiating AAV subtypes with and without ILD.
Main Methods:
- Serum KL-6 concentrations were measured in 13 AAV patients (6 MPA, 7 GPA).
- A regression decision tree model was employed to identify diagnostic classifiers for AAV-ILD.
- Serum KL-6 levels were analyzed at baseline (T0) and follow-up (T1) and correlated with Birmingham Vasculitis Activity Score (BVAS).
Main Results:
- Serum KL-6 levels were significantly higher in AAV patients with ILD compared to those without (972.8 ± 398.5 vs 305.4 ± 93.9, p = 0.0040).
- KL-6 demonstrated 100% diagnostic performance for ILD detection with a cutoff of 368 U/mL (accuracy 91.7%).
- A direct correlation was observed between baseline KL-6 and baseline BVAS (r = 0.578, p = 0.044).
Conclusions:
- KL-6 is a reliable, non-invasive biomarker for ILD in AAV patients.
- Serum KL-6 levels aid in assessing disease activity and can help distinguish AAV with ILD.
- Serial KL-6 measurements may be valuable for monitoring AAV patients and assessing treatment response.
