The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray
Background: There is a lack of published research on the impact of the first wave of the COVID-19 pandemic in Taiwan. We investigated the mortality risk factors among critically ill patients with COVID-19 in Taiwan during the initial wave. Furthermore, we aim to develop a novel AI mortality predicti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Journal of the Formosan Medical Association |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0929664622003643 |
| _version_ | 1797900713952542720 |
|---|---|
| author | Chih-Wei Wu Bach-Tung Pham Jia-Ching Wang Yao-Kuang Wu Chan-Yen Kuo Yi-Chiung Hsu |
| author_facet | Chih-Wei Wu Bach-Tung Pham Jia-Ching Wang Yao-Kuang Wu Chan-Yen Kuo Yi-Chiung Hsu |
| author_sort | Chih-Wei Wu |
| collection | DOAJ |
| description | Background: There is a lack of published research on the impact of the first wave of the COVID-19 pandemic in Taiwan. We investigated the mortality risk factors among critically ill patients with COVID-19 in Taiwan during the initial wave. Furthermore, we aim to develop a novel AI mortality prediction model using chest X-ray (CXR) alone. Method: We retrospectively reviewed the medical records of patients with COVID-19 at Taipei Tzu Chi Hospital from May 15 to July 15 2021. We enrolled adult patients who received invasive mechanical ventilation. The CXR images of each enrolled patient were divided into 4 categories (1st, pre-ETT, ETT, and WORST). To establish a prediction model, we used the MobilenetV3-Small model with “Imagenet” pretrained weights, followed by high Dropout regularization layers. We trained the model with these data with Five-Fold Cross-Validation to evaluate model performance. Result: A total of 64 patients were enrolled. The overall mortality rate was 45%. The median time from symptom onset to intubation was 8 days. Vasopressor use and a higher BRIXIA score on the WORST CXR were associated with an increased risk of mortality. The areas under the curve of the 1st, pre-ETT, ETT, and WORST CXRs by the AI model were 0.87, 0.92, 0.96, and 0.93 respectively. Conclusion: The mortality rate of COVID-19 patients who receive invasive mechanical ventilation was high. Septic shock and high BRIXIA score were clinical predictors of mortality. The novel AI mortality prediction model using CXR alone exhibited a high performance. |
| first_indexed | 2024-04-10T08:50:26Z |
| format | Article |
| id | doaj.art-a3695a60e9584b5780cda15731574b0c |
| institution | Directory Open Access Journal |
| issn | 0929-6646 |
| language | English |
| last_indexed | 2024-04-10T08:50:26Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of the Formosan Medical Association |
| spelling | doaj.art-a3695a60e9584b5780cda15731574b0c2023-02-22T04:30:03ZengElsevierJournal of the Formosan Medical Association0929-66462023-03-011223267275The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-rayChih-Wei Wu0Bach-Tung Pham1Jia-Ching Wang2Yao-Kuang Wu3Chan-Yen Kuo4Yi-Chiung Hsu5Division of Pulmonary Medicine, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan; Department of Biomedical Sciences and Engineering, National Central University, Taoyuan, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan, TaiwanDivision of Pulmonary Medicine, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, TaiwanDepartment of Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, TaiwanDepartment of Biomedical Sciences and Engineering, National Central University, Taoyuan, Taiwan; Corresponding author. Department of Biomedical Sciences and Engineering, National Central University, No. 300, Zhongda Road, Zhongli District, Taoyuan City 32001, Taiwan. Fax: +886 3 425 3427.Background: There is a lack of published research on the impact of the first wave of the COVID-19 pandemic in Taiwan. We investigated the mortality risk factors among critically ill patients with COVID-19 in Taiwan during the initial wave. Furthermore, we aim to develop a novel AI mortality prediction model using chest X-ray (CXR) alone. Method: We retrospectively reviewed the medical records of patients with COVID-19 at Taipei Tzu Chi Hospital from May 15 to July 15 2021. We enrolled adult patients who received invasive mechanical ventilation. The CXR images of each enrolled patient were divided into 4 categories (1st, pre-ETT, ETT, and WORST). To establish a prediction model, we used the MobilenetV3-Small model with “Imagenet” pretrained weights, followed by high Dropout regularization layers. We trained the model with these data with Five-Fold Cross-Validation to evaluate model performance. Result: A total of 64 patients were enrolled. The overall mortality rate was 45%. The median time from symptom onset to intubation was 8 days. Vasopressor use and a higher BRIXIA score on the WORST CXR were associated with an increased risk of mortality. The areas under the curve of the 1st, pre-ETT, ETT, and WORST CXRs by the AI model were 0.87, 0.92, 0.96, and 0.93 respectively. Conclusion: The mortality rate of COVID-19 patients who receive invasive mechanical ventilation was high. Septic shock and high BRIXIA score were clinical predictors of mortality. The novel AI mortality prediction model using CXR alone exhibited a high performance.http://www.sciencedirect.com/science/article/pii/S0929664622003643COVID-19Artificial intelligenceChest X-raysPrognosisMortalityIntensive care unit |
| spellingShingle | Chih-Wei Wu Bach-Tung Pham Jia-Ching Wang Yao-Kuang Wu Chan-Yen Kuo Yi-Chiung Hsu The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray Journal of the Formosan Medical Association COVID-19 Artificial intelligence Chest X-rays Prognosis Mortality Intensive care unit |
| title | The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray |
| title_full | The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray |
| title_fullStr | The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray |
| title_full_unstemmed | The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray |
| title_short | The COVIDTW study: Clinical predictors of COVID-19 mortality and a novel AI prognostic model using chest X-ray |
| title_sort | covidtw study clinical predictors of covid 19 mortality and a novel ai prognostic model using chest x ray |
| topic | COVID-19 Artificial intelligence Chest X-rays Prognosis Mortality Intensive care unit |
| url | http://www.sciencedirect.com/science/article/pii/S0929664622003643 |
| work_keys_str_mv | AT chihweiwu thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT bachtungpham thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT jiachingwang thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT yaokuangwu thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT chanyenkuo thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT yichiunghsu thecovidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT chihweiwu covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT bachtungpham covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT jiachingwang covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT yaokuangwu covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT chanyenkuo covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray AT yichiunghsu covidtwstudyclinicalpredictorsofcovid19mortalityandanovelaiprognosticmodelusingchestxray |