A new study using machine learning (ML) identified four distinct lupus disease profiles or autoantibody clusters that predict long-term disease, need for treatment, organ involvement, and risk of death. Machine learning refers to the process by which machines or computers can imitate human behavior to learn and optimize complex tasks such as statistical analysis and predictive modeling using large datasets. Autoantibodies are antibodies produced by the immune system and directed against proteins in the body. Proteins are often causative or markers of many autoimmune diseases, including lupus.
The researchers observed 805 lupus patients and examined demographic, clinical, and laboratory data within 15 months of diagnosis, and then at 3 and 5 years of illness. After analyzing the data, the researchers used predictive ML to uncover four distinct clusters or lupus disease profiles associated with important lupus outcomes.
- Cluster 1 (137 people):
- High Risk – Risk characterized by autoantibody reactivity, high disease activity, use of immunosuppressive agents/biologics, non-Caucasian/non-white people known to have more severe lupus It was more commonly seen among ethnic groups.
- Cluster 2 (376 people):
- Lowest frequency of lupus nephritis (LN) and lowest use of immunosuppressants and biologics
- Cluster 3 (80 people):
- Antiphospholipid antibodies are most frequent and predict cardiovascular disease events such as stroke and antiphospholipid syndrome
- Cluster 4 (212 people):
- High disease activity characterized by multiple autoantibody reactivity
Further studies are needed to determine other lupus biomarkers and to understand disease etiology through ML approaches. Researchers suggest that ML studies may also help inform diagnosis and treatment strategies for patients with lupus. Learn more about lupus research here.
read the study
