New model effectively predicts mortality in RA‐ILD patients

A risk prediction model based on high-resolution computed tomography (HRCT) variables appear useful for patients with rheumatoid arthritis (RA)-associated interstitial lung disease (ILD), suggests a study.

Retrospective data from 153 patients with RA-ILD were used to develop the prediction model, which was validated in an independent RA-ILD cohort (n=149). The authors screened candidate variables for the prediction models using a multivariate Cox proportional hazard model and calculated C-statistics to assess and compare the predictive ability of each model.

Over a median follow-up period of 54 months, 38.6 percent of patients in the derivation cohort showed a usual interstitial pneumonia (UIP) pattern on HRCT imaging. Multivariate Cox analysis revealed the following HRCT factors associated with poor prognosis that were included in the final model: old age (≥60 years; hazard ratio [HR], 2.063), high fibrosis score (≥20 percent of the total lung extent; HR, 4.585), a UIP pattern (HR, 1.899), and emphysema (HR, 2.596).

The prediction model demonstrated good performance in predicting 5-year mortality (C-index, 0.780; p<0.001). At-risk patients were further divided into three groups with 1-year mortality rates of 0 percent, 5.1 percent, and 24.1 percent, respectively.

Predicted and observed mortalities were similar at 1, 2, and 3 years in the derivation cohort. In addition, the prediction model effectively predicted prognosis of the validation cohort (C-index, 0.638; p<0.001).

“RA‐ILD has a variable clinical course, and its prognosis is difficult to predict. Moreover, risk prediction models for prognosis remain undefined,” the authors said.