Fig. 4: Results of the AI models to predict the 3-year survival rate.
From: Interstitial lung disease diagnosis and prognosis using an AI system integrating longitudinal data
a Distribution of longitudinal visits from each patient. Each visit of 234 patients included in the survival rate study was presented. b Characteristics of longitudinal data. c ROC curves of 3-year survival rate prediction at different endpoints. d Performance and comparison of Transformer models developed at multiple endpoints. n = 234 for 3-year survival analysis. Two-sided P-values were calculated for all comparisons. aData in parentheses indicate the range. bData in parentheses indicate 95% CI. ***p < 0.001. **p < 0.01. *p < 0.05.
