Predictive model of risk and severity of enteritis in systemic lupus erythematosus.

INTRODUCTION

To describe the clinical and laboratory features of systemic lupus erythematosus (SLE) enteritis and to establish a predictive model of risk and severity of lupus enteritis (LE).

METHODS

Records of patients with SLE complaining about acute digestive symptoms were reviewed. The predictive nomogram for the diagnosis of LE was constructed by using R. The accuracy of the model was tested with correction curves. The receiver operating characteristic curve (ROC curve) program and a Decision curve analysis (DCA) were used for the verification of LE model. Receiver operating characteristic curve was also employed for evaluation of factors in the prediction of severity of LE.

RESULTS

During the eight year period, 46 patients were in the LE group, while 32 were in the non-LE group. Abdominal pain, emesis, D-dimer >5 μg/mL, hypo-C3, and anti-SSA positive remained statistically significant and were included into the prediction model. Area under the curve (AUC) of ROC curve in this model was 0.909. Correction curve indicated consistency between the predicted rate and actual diagnostic rates. The DCA showed that the LE model was of benefit. Forty-four patients were included in developing the prediction model of LE severity. Infection, SLE disease activity index (SLEDAI), CT score, and new CT score were validated as risk factors for LE severity. The AUC of the combined SLEDAI, infection and new CT score were 0.870.

CONCLUSION

The LE model exhibits good predictive ability to assess LE risk in SLE patients with acute digestive symptoms The combination of SLEDAI, infection, and new CT score could improve the assessment of LE severity.