Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model
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.Methods: We established an artificial intelligence honeycomb...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Pharmacology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphar.2022.878764/full |
| _version_ | 1818126864730816512 |
|---|---|
| author | Xuening Wu Chengsheng Yin Chengsheng Yin Xianqiu Chen Yuan Zhang Yiliang Su Jingyun Shi Dong Weng Xing Jiang Aihong Zhang Wenqiang Zhang Huiping Li |
| author_facet | Xuening Wu Chengsheng Yin Chengsheng Yin Xianqiu Chen Yuan Zhang Yiliang Su Jingyun Shi Dong Weng Xing Jiang Aihong Zhang Wenqiang Zhang Huiping Li |
| author_sort | Xuening Wu |
| collection | DOAJ |
| description | 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.Methods: We established an artificial intelligence honeycomb segmentation system that segmented the honeycomb tissue area automatically from 102 manually 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 and physiological feature (PF) parameters (including FVC%pred, DLco%pred, SpO2%, age, and gender). 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 previously. Then, using a competing risk (Fine–Gray) proportional hazards model, a risk score model was created according to the training set’s patient data and used the validation data set to validate this model.Result: The final risk prediction model (CTPF) was established, and it included the CT stages and the PF (pulmonary function and physiological features) grades. The CT stages were defined into three stages: stage I (CTS≤5), stage II (5 < CTS<25), and stage III (≥25). The PF grades were classified into mild (a, 0–3 points), moderate (b, 4–6 points), and severe (c, 7–10 points). The AUC index and Briers scores at 1, 2, and 3 years in the training set were as follows: 74.3 [63.2,85.4], 8.6 [2.4,14.8]; 78 [70.2,85.9], 16.0 [10.1,22.0]; and 72.8 [58.3,87.3], 18.2 [11.9,24.6]. The results of the validation sets were similar and suggested that high-risk patients had significantly higher mortality rates.Conclusion: This CTPF model with AI technology can predict mortality risk in IPF precisely. |
| first_indexed | 2024-12-11T07:08:14Z |
| format | Article |
| id | doaj.art-c04ddeaa5428402d9dfb1835c7a5e4aa |
| institution | Directory Open Access Journal |
| issn | 1663-9812 |
| language | English |
| last_indexed | 2024-12-11T07:08:14Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pharmacology |
| spelling | doaj.art-c04ddeaa5428402d9dfb1835c7a5e4aa2022-12-22T01:16:25ZengFrontiers Media S.A.Frontiers in Pharmacology1663-98122022-04-011310.3389/fphar.2022.878764878764Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF ModelXuening Wu0Chengsheng Yin1Chengsheng Yin2Xianqiu Chen3Yuan Zhang4Yiliang Su5Jingyun Shi6Dong Weng7Xing Jiang8Aihong Zhang9Wenqiang Zhang10Huiping Li11The Academy for Engineering and Technology, Fudan University, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Pulmonary and Critical Care Medicine, Yijishan Hospital of Wannan Medical College, Wuhu, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Radiology, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaDepartment of Medical Statistics, School of Medicine, Tongji University, Shanghai, ChinaThe Academy for Engineering and Technology, Fudan University, Shanghai, ChinaDepartment of Respiratory Medicine, Shanghai Pulmonary Hospital, Tongji University, School of Medicine, Shanghai, ChinaBackground: 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.Methods: We established an artificial intelligence honeycomb segmentation system that segmented the honeycomb tissue area automatically from 102 manually 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 and physiological feature (PF) parameters (including FVC%pred, DLco%pred, SpO2%, age, and gender). 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 previously. Then, using a competing risk (Fine–Gray) proportional hazards model, a risk score model was created according to the training set’s patient data and used the validation data set to validate this model.Result: The final risk prediction model (CTPF) was established, and it included the CT stages and the PF (pulmonary function and physiological features) grades. The CT stages were defined into three stages: stage I (CTS≤5), stage II (5 < CTS<25), and stage III (≥25). The PF grades were classified into mild (a, 0–3 points), moderate (b, 4–6 points), and severe (c, 7–10 points). The AUC index and Briers scores at 1, 2, and 3 years in the training set were as follows: 74.3 [63.2,85.4], 8.6 [2.4,14.8]; 78 [70.2,85.9], 16.0 [10.1,22.0]; and 72.8 [58.3,87.3], 18.2 [11.9,24.6]. The results of the validation sets were similar and suggested that high-risk patients had significantly higher mortality rates.Conclusion: This CTPF model with AI technology can predict mortality risk in IPF precisely.https://www.frontiersin.org/articles/10.3389/fphar.2022.878764/fullartificial intelligence (AI)deep learningsemantic segmentationidiopathic pulmonary fibrosis (IPF)pulmonary fibrosis stagedisease severity grade |
| spellingShingle | Xuening Wu Chengsheng Yin Chengsheng Yin Xianqiu Chen Yuan Zhang Yiliang Su Jingyun Shi Dong Weng Xing Jiang Aihong Zhang Wenqiang Zhang Huiping Li Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model Frontiers in Pharmacology artificial intelligence (AI) deep learning semantic segmentation idiopathic pulmonary fibrosis (IPF) pulmonary fibrosis stage disease severity grade |
| title | Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model |
| title_full | Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model |
| title_fullStr | Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model |
| title_full_unstemmed | Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model |
| title_short | Idiopathic Pulmonary Fibrosis Mortality Risk Prediction Based on Artificial Intelligence: The CTPF Model |
| title_sort | idiopathic pulmonary fibrosis mortality risk prediction based on artificial intelligence the ctpf model |
| topic | artificial intelligence (AI) deep learning semantic segmentation idiopathic pulmonary fibrosis (IPF) pulmonary fibrosis stage disease severity grade |
| url | https://www.frontiersin.org/articles/10.3389/fphar.2022.878764/full |
| work_keys_str_mv | AT xueningwu idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT chengshengyin idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT chengshengyin idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT xianqiuchen idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT yuanzhang idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT yiliangsu idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT jingyunshi idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT dongweng idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT xingjiang idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT aihongzhang idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT wenqiangzhang idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel AT huipingli idiopathicpulmonaryfibrosismortalityriskpredictionbasedonartificialintelligencethectpfmodel |