Lupus & antiphospholipid syndrome
Enhancing predictions of subclinical cardiac dysfunction in SLE patients through integrative machine learning analysis
Authors' conclusion
This case-control study revealed that 2D-STE parameters can be used to predict subclinical cardiac dysfunction in SLE patients, and anti-U1RNP antibodies may be an essential predictive clinical factor.
Study context
- Population
- Patients newly diagnosed with SLE admitted to the rheumatology and immunology department of Sun Yat-sen University, January 2020–December 2021equal number of matched controls
- Comparison
- Newly diagnosed SLE vs healthy controls
- SLEn = 36
- Outcome
- 2D-STE parameters, SLE vs controls
Methodological detailsmatched for gender and age, machine learning, multivariate regression
- Matched for gender and age
- Machine learning
- Multivariate regression
Main finding
As reported in the abstract
- Significant differences in 2D-STE parameters between SLE patients and controls
- SLE vs Healthy controls: p-adjust<0.001
- SLE vs Healthy controls: p-adjust=0.005
- SLE vs Healthy controls: p-adjust=0.003
Observational data: associations, not effects.
Further findings
Machine learning discrimination (GLPS-APLAX)
- AUC
- 0.93 (95% CI: 0.89 to 0.96)
- Area under the precision-recall curve
- 0.96
Anti-U1RNP antibodies and GLPS (multivariate regression)
- GLPS coefficient
- −3.71 (95% CI: −5.91 to −1.51, p=0.002)
- Inverse relationship with four GLPS-related measures; significant for GLPS, GLPS-A4C and GLPS-APLAX
Original publication
Enhancing predictions of subclinical cardiac dysfunction in SLE patients through integrative machine learning analysis. Lupus Sci Med. Published 1 September 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →