Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia
Background Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.Methods Deep-lear...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2021-01-01
|
| Series: | BMJ Open Respiratory Research |
| Online Access: | https://bmjopenrespres.bmj.com/content/8/1/e001045.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846159000087822336 |
|---|---|
| author | Rayan Alsuwaigh Christine Ang Jessica Quah Charlene Jin Yee Liew Lin Zou Xuan Han Koh Venkataraman Narayan Tian Yi Lu Clarence Ngoh Zhiyu Wang Juan Zhen Koh Zhiyan Fu Han Leong Goh |
| author_facet | Rayan Alsuwaigh Christine Ang Jessica Quah Charlene Jin Yee Liew Lin Zou Xuan Han Koh Venkataraman Narayan Tian Yi Lu Clarence Ngoh Zhiyu Wang Juan Zhen Koh Zhiyan Fu Han Leong Goh |
| author_sort | Rayan Alsuwaigh |
| collection | DOAJ |
| description | Background Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.Methods Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality.Results 315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) μg/L vs 1.4 (5.9) μg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001).Conclusion CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined. |
| format | Article |
| id | doaj-art-ff805f5703d04f36a7ffd92171fd8408 |
| institution | Kabale University |
| issn | 2052-4439 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Open Respiratory Research |
| spelling | doaj-art-ff805f5703d04f36a7ffd92171fd84082024-11-24T07:25:08ZengBMJ Publishing GroupBMJ Open Respiratory Research2052-44392021-01-018110.1136/bmjresp-2021-001045Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumoniaRayan Alsuwaigh0Christine Ang1Jessica Quah2Charlene Jin Yee Liew3Lin Zou4Xuan Han Koh5Venkataraman Narayan6Tian Yi Lu7Clarence Ngoh8Zhiyu Wang9Juan Zhen Koh10Zhiyan Fu11Han Leong Goh12Department of Respiratory and Critical Care Medicine, Changi General Hospital, SingaporeNGOC, Gateshead, UKDepartment of Respiratory and Critical Care Medicine, Changi General Hospital, SingaporeDepartment of Radiology, Changi General Hospital, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeHealth Services Research, Changi General Hospital, SingaporeData Management and Informatics, Changi General Hospital, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeIntegrated Health Information Systems Pte Ltd, SingaporeBackground Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.Methods Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality.Results 315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) μg/L vs 1.4 (5.9) μg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001).Conclusion CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.https://bmjopenrespres.bmj.com/content/8/1/e001045.full |
| spellingShingle | Rayan Alsuwaigh Christine Ang Jessica Quah Charlene Jin Yee Liew Lin Zou Xuan Han Koh Venkataraman Narayan Tian Yi Lu Clarence Ngoh Zhiyu Wang Juan Zhen Koh Zhiyan Fu Han Leong Goh Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia BMJ Open Respiratory Research |
| title | Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia |
| title_full | Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia |
| title_fullStr | Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia |
| title_full_unstemmed | Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia |
| title_short | Chest radiograph-based artificial intelligence predictive model for mortality in community-acquired pneumonia |
| title_sort | chest radiograph based artificial intelligence predictive model for mortality in community acquired pneumonia |
| url | https://bmjopenrespres.bmj.com/content/8/1/e001045.full |
| work_keys_str_mv | AT rayanalsuwaigh chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT christineang chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT jessicaquah chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT charlenejinyeeliew chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT linzou chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT xuanhankoh chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT venkataramannarayan chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT tianyilu chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT clarencengoh chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT zhiyuwang chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT juanzhenkoh chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT zhiyanfu chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia AT hanleonggoh chestradiographbasedartificialintelligencepredictivemodelformortalityincommunityacquiredpneumonia |