An Explainable Cryobiopsy AI Model, CRAI, to Predict Progression in Interstitial Pneumonia.

Interstitial lung disease (ILD) encompasses diverse pulmonary disorders with varied prognoses. Current pathological diagnoses suffer from inter-observer variability, necessitating more standardized approaches. We developed an ensemble AI model for cryobiopsy, CRAI, to analyze transbronchial lung cryobiopsy (TBLC) specimens and predict patient outcomes. CRAI comprises seven modules for detecting histological features, generating 17 pathologically significant findings. A downstream XGBoost classifier was developed to predict disease progression using these findings. The model's performance was evaluated using respiratory function changes and survival analysis in cross-validation and external test cohorts. In the internal cross-validation (135 cases), the model predicted 105 cases without disease progression and 30 with disease progression. The annual Δ%FVC was -1.293 in the non-progressive group versus -5.198 in the progressive group, a difference that was significant for CRAI while only five of 19 pathologists achieved significant differentiation using usual interstitial pneumonia (UIP) diagnosis. Survival analysis demonstrated significantly shorter survival times in the progressive group (p = 0.038). CRAI provides a comprehensive, interpretable approach to analyzing TBLC specimens, offering potential for standardizing ILD diagnosis and predicting disease progression. The model could facilitate early identification of progressive cases and guide personalized therapeutic interventions.