AUTHOR=Wu Xuening , Yin Chengsheng , Chen Xianqiu , Zhang Yuan , Su Yiliang , Shi Jingyun , Weng Dong , Jiang Xing , Zhang Aihong , Zhang Wenqiang , Li Huiping 

TITLE=Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.878764

DOI=10.3389/fphar.2022.878764

ISSN=1663-9812

ABSTRACT=Background：Idiopathic pulmonary fibrosis (IPF) needs a precise prediction method for its prognosis. This study took advantage of artificial intelligence (AI) deep learning to develop a new mortality risk prediction model for IPF patients. 
Method：1.We established an artificial intelligence honeycomb segmentation system which segmented honeycomb tissue area automatically from 102 manual labeled (by radiologists) cases of IPF patients' CT images. The percentage of honeycomb in the lung was calculated as the CT fibrosis score (CTS). The severity of the patients was evaluated by pulmonary function & physiological features (PF) parameters (including FVC%pred, DLco%pred, SpO2%, age, and gender). 2.Another 206 IPF cases were randomly divided into a training set (n=165) and a verification set (n=41) to calculate the fibrosis percentage in each case by the AI system mentioned above. Then used a competing risk (Fine-Gray) proportional hazards model created a risk score model according to the training set’s patient data and used the validation data set to validate this model.
Result：1.The final risk prediction model (CTPF) was established, it included the CT stages and the PF (pulmonary function & physiological features) grades. The CT stages were defined into three stages: stage I:(CTS≤5),  stage II: (5