Comparison of Aspergillus-specific antibody cut-offs for the diagnosis of aspergillosis.

Background: Aspergillus diseases are frequently encountered in patients who are immunocompromised. Without a prompt diagnosis, the clinical consequences may be lethal. Aspergillus-specific antibodies have been widely used to facilitate the diagnosis of Aspergillus diseases. To date, universally standardized cut-off values have not been established. This study aimed to investigate the cut-off values of Aspergillus-specific antibodies and perform a narrative review to depict the geographic differences in the Taiwanese population. Methods: We analyzed enrolled 118 healthy controls, 29 patients with invasive aspergillosis (IA), chronic pulmonary aspergillosis (CPA), and allergic bronchopulmonary aspergillosis (ABPA) and 99 with disease control, who were tested for Aspergillus fumigatus and Aspergillus niger-specific IgG and IgE using ImmunoCAP. 99 participants not fulfilling the diagnosis of IA, CPA, and ABPA were enrolled in the disease control group. The duration of retrieval of medical records from June 2018 to September 2021. Optimal cut-offs and association were determined using receiver operating characteristic curve (ROC) analysis. Results: We found that patients with CPA had the highest A. fumigatus-specific IgG levels while patients with ABPA had the highest A. fumigatus-specific IgE, and A. niger-specific IgG and IgE levels. In patients with CPA and ABPA, the optimal cut-offs of A. fumigatus-specific IgG and A. niger-specific IgG levels were 41.6, 40.8, 38.1, and 69.9 mgA/l, respectively. Geographic differences in the cut-off values of A. fumigatus-specific IgG were also noted. Specifically, the levels were different in eco-climatic zones. Conclusion: We identified the optimal cut-offs of Aspergillus-specific antibodies to facilitate a precise diagnosis of aspergillosis. The observed geographic differences of the antibody levels suggest that an eco-climatic-specific reference is needed to facilitate a prompt and accurate diagnosis of aspergillosis.

Application of Supervised Machine Learning to Recognize Competent Level and Mixed Antinuclear Antibody Patterns Based on ICAP International Consensus.

BACKGROUND: Antinuclear antibody pattern recognition is vital for autoimmune disease diagnosis but labor-intensive for manual interpretation. To develop an automated pattern recognition system, we established machine learning models based on the International Consensus on Antinuclear Antibody Patterns (ICAP) at a competent level, mixed patterns recognition, and evaluated their consistency with human reading. METHODS: 51,694 human epithelial cells (HEp-2) cell images with patterns assigned by experienced medical technologists collected in a medical center were used to train six machine learning algorithms and were compared by their performance. Next, we choose the best performing model to test the consistency with five experienced readers and two beginners. RESULTS: The mean F1 score in each classification of the best performing model was 0.86 evaluated by Testing Data 1. For the inter-observer agreement test on Testing Data 2, the average agreement was 0.849 (κ) among five experienced readers, 0.844 between the best performing model and experienced readers, 0.528 between experienced readers and beginners. The results indicate that the proposed model outperformed beginners and achieved an excellent agreement with experienced readers. CONCLUSIONS: This study demonstrated that the developed model could reach an excellent agreement with experienced human readers using machine learning methods.