New Tool to Aid Accurate Lupus Diagnosis
NEW YORK (Reuters Health) – Clinicians in Greece have developed and validated a simple and accurate tool to aid diagnosis of systemic lupus erythematosus (SLE) based on standard clinical and serological features.
“SLE diagnosis often poses significant challenges especially at early stages and formal diagnostic criteria are currently missing. Pending further validation in prospective studies, the new diagnostic model (SLE Risk Probability Index) can assist the early diagnosis and treatment of patients with SLE to improve disease outcomes,” they write in Annals of the Rheumatic Diseases.
Dr. George Bertsias of the University of Crete School of Medicine and colleagues used machine learning to develop the SLERPI algorithm based on data from 802 adults with SLE or control rheumatologic diseases. The best model was validated in 512 adults with SLE and 143 controls.
The model includes 14 variably weighted standard clinical and serological features. The strongest SLE predictors in the model are thrombocytopenia/hemolytic anemia, malar/ maculopapular rash, proteinuria, low C3 and C4, antinuclear antibodies (ANA) and immunologic disorder.
“Our model produced SLE risk probabilities (depending on the combination of features) correlating positively with disease severity and organ damage, and allowing the unbiased classification of a validation cohort into diagnostic certainty levels (unlikely, possible, likely, definitive SLE) based on the likelihood of SLE against other diagnoses,” the team reports.
When treated as binary (SLE or not SLE), the model shows “excellent accuracy (94.8%) for identifying SLE, and high sensitivity for early disease (93.8%), nephritis (97.9%), neuropsychiatric (91.8%) and severe lupus requiring immunosuppressives/biologics (96.4%),” they say.
The logistic regression model can be converted into a simple scoring system for both clinical and serological features, with an operational cut-off score of 7, with 94.2% accuracy.
“We have uploaded the tool at the website of the Rheumatology Department, University of Crete Medical School,” Dr. Bertsias told Reuters Health by email. It can be accessed at https://www.rheumatology-uoc.gr/el/slerpi.
“The details of the tool are available in the paper so that others might use them to develop another online (or other) version. The tool can certainly be used when there is a suspicion of SLE pending of course, further validation of its diagnostic accuracy in other settings/population groups,” Dr. Bertsias said.
The study had no commercial funding, and the authors made no relevant disclosures.
SOURCE: http://bit.ly/3aSUZ7X Annals of the Rheumatic Diseases, online February 10, 2021.
Source: Read Full Article
