Objective To identify risk factors for fibrosis progression and develop a predictive model in patients with usual interstitial pneumonia (UIP) pattern on CT. Methods We retrospectively enrolled 453 patients with CT-defined UIP or probable UIP, followed for one year. The study endpoint was either meeting progressive pulmonary fibrosis (PPF) criteria or completing one-year follow-up. Clinical features, pulmonary function, and laboratory data were collected. Independent risk factors were identified using logistic regression. Patients were randomly divided into training and validation cohorts at a 7:3 ratio. A nomogram was constructed in the training cohort using R and its performance and clinical utility were evaluated in the validation cohort. Results During one-year follow-up, 160 patients (35.3%) met PPF criteria. Multivariate analysis showed that higher baseline levels of CA19-9 and CA125, as well as the presence of pulmonary hypertension, were independent risk factors for pulmonary fibrosis progression, while a higher percentage of predicted forced vital capacity (FVC) and the presence of emphysema were protective factors. A nomogram model was constructed using these five variables, with the area under the curve (AUC) for predicting fibrosis progression being 0.854 in the training set and 0.817 in the validation set. Clinical decision curve analysis indicated that the model provided the greatest clinical benefit when the threshold probability was between 0.12 and 0.93. Conclusion A nomogram incorporating baseline CA19-9, CA125, FVC % predicted, pulmonary hypertension, and emphysema shows potential for predicting one-year fibrosis progression in UIP patients.
