Lupus & antiphospholipid syndrome
Balancing automation and expertise: real-world evaluation of artificial intelligence (AI)-assisted whole-exome sequencing in lupus-causing genes
Authors' conclusion
AI-assisted WES analysis substantially reduced the number of variants requiring manual review without missing the two monogenic cases.
Study context
- Population
- Patients with systemic lupus erythematosus (SLE) and other systemic autoimmune rheumatic diseases (SARDs) undergoing whole-exome sequencing (WES)
- Participants
- 120 SARD patients
- Comparison
- AI-assisted vs expert-guided WES analysis for variants in lupus-causing genes
- Outcome
- Variants potentially likely to be causative before manual analysis
Methodological detailssame platform (Emedgene), manual analysis after filtering
- Same platform (Emedgene)
- Manual analysis after filtering
Performance
As reported in the abstract
AI-assisted
20.8
2906 events
Expert-guided
59.9
8391 events
Further findings
Variants in lupus-causing genes at end of manual analysis
- Comparable number of variants in lupus-causing genes with both methods
- 78 vs 56
- Two monogenic cases identified: PEPD (c.819-1G>A, homozygous) and CYBB (c.1314+1G>A, hemizygous)
- 2
Original publication
Balancing automation and expertise: real-world evaluation of AI-assisted whole-exome sequencing in lupus-causing genes. Lupus Sci Med. Published 30 September 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →