tetano
Editor, Senior Moderator
Ann Transl Med
. 2022 Feb;10(3):130.
doi: 10.21037/atm-21-5571.
Integrated model for COVID-19 diagnosis based on computed tomography artificial intelligence, and clinical features: a multicenter cohort study
Yuki Kataoka[SUP] #[/SUP][SUP] 1 2 3 4 [/SUP], Yuya Kimura[SUP] #[/SUP][SUP] 5 [/SUP], Tatsuyoshi Ikenoue[SUP] 6 7 [/SUP], Yoshinori Matsuoka[SUP] 3 8 [/SUP], Junichi Matsumoto[SUP] 9 [/SUP], Junji Kumasawa[SUP] 6 10 [/SUP], Kentaro Tochitatni[SUP] 11 [/SUP], Hiraku Funakoshi[SUP] 12 [/SUP], Tomohiro Hosoda[SUP] 13 [/SUP], Aiko Kugimiya[SUP] 14 [/SUP], Michinori Shirano[SUP] 15 [/SUP], Fumiko Hamabe[SUP] 16 [/SUP], Sachiyo Iwata[SUP] 17 [/SUP], Shingo Fukuma[SUP] 6 [/SUP], Japan COVID-19 AI team*
Affiliations
Abstract
Background: We developed and validated a machine learning diagnostic model for the novel coronavirus (COVID-19) disease, integrating artificial-intelligence-based computed tomography (CT) imaging and clinical features.
Methods: We conducted a retrospective cohort study in 11 Japanese tertiary care facilities that treated COVID-19 patients. Participants were tested using both real-time reverse transcription polymerase chain reaction (RT-PCR) and chest CTs between January 1 and May 30, 2020. We chronologically split the dataset in each hospital into training and test sets, containing patients in a 7:3 ratio. A Light Gradient Boosting Machine model was used for the analysis.
Results: A total of 703 patients were included, and two models-the full model and the A-blood model-were developed for their diagnosis. The A-blood model included eight variables (the Ali-M3 confidence, along with seven clinical features of blood counts and biochemistry markers). The areas under the receiver-operator curve of both models [0.91, 95% confidence interval (CI): 0.86 to 0.95 for the full model and 0.90, 95% CI: 0.86 to 0.94 for the A-blood model] were better than that of the Ali-M3 confidence (0.78, 95% CI: 0.71 to 0.83) in the test set.
Conclusions: The A-blood model, a COVID-19 diagnostic model developed in this study, combines machine-learning and CT evaluation with blood test data and performs better than the Ali-M3 framework existing for this purpose. This would significantly aid physicians in making a quicker diagnosis of COVID-19.
Keywords: COVID-19; Light Gradient Boosting Machine (LightGBM); decision support tool; diagnosis; machine learning.
. 2022 Feb;10(3):130.
doi: 10.21037/atm-21-5571.
Integrated model for COVID-19 diagnosis based on computed tomography artificial intelligence, and clinical features: a multicenter cohort study
Yuki Kataoka[SUP] #[/SUP][SUP] 1 2 3 4 [/SUP], Yuya Kimura[SUP] #[/SUP][SUP] 5 [/SUP], Tatsuyoshi Ikenoue[SUP] 6 7 [/SUP], Yoshinori Matsuoka[SUP] 3 8 [/SUP], Junichi Matsumoto[SUP] 9 [/SUP], Junji Kumasawa[SUP] 6 10 [/SUP], Kentaro Tochitatni[SUP] 11 [/SUP], Hiraku Funakoshi[SUP] 12 [/SUP], Tomohiro Hosoda[SUP] 13 [/SUP], Aiko Kugimiya[SUP] 14 [/SUP], Michinori Shirano[SUP] 15 [/SUP], Fumiko Hamabe[SUP] 16 [/SUP], Sachiyo Iwata[SUP] 17 [/SUP], Shingo Fukuma[SUP] 6 [/SUP], Japan COVID-19 AI team*
Affiliations
- PMID: 35284557
- PMCID: PMC8904977
- DOI: 10.21037/atm-21-5571
Abstract
Background: We developed and validated a machine learning diagnostic model for the novel coronavirus (COVID-19) disease, integrating artificial-intelligence-based computed tomography (CT) imaging and clinical features.
Methods: We conducted a retrospective cohort study in 11 Japanese tertiary care facilities that treated COVID-19 patients. Participants were tested using both real-time reverse transcription polymerase chain reaction (RT-PCR) and chest CTs between January 1 and May 30, 2020. We chronologically split the dataset in each hospital into training and test sets, containing patients in a 7:3 ratio. A Light Gradient Boosting Machine model was used for the analysis.
Results: A total of 703 patients were included, and two models-the full model and the A-blood model-were developed for their diagnosis. The A-blood model included eight variables (the Ali-M3 confidence, along with seven clinical features of blood counts and biochemistry markers). The areas under the receiver-operator curve of both models [0.91, 95% confidence interval (CI): 0.86 to 0.95 for the full model and 0.90, 95% CI: 0.86 to 0.94 for the A-blood model] were better than that of the Ali-M3 confidence (0.78, 95% CI: 0.71 to 0.83) in the test set.
Conclusions: The A-blood model, a COVID-19 diagnostic model developed in this study, combines machine-learning and CT evaluation with blood test data and performs better than the Ali-M3 framework existing for this purpose. This would significantly aid physicians in making a quicker diagnosis of COVID-19.
Keywords: COVID-19; Light Gradient Boosting Machine (LightGBM); decision support tool; diagnosis; machine learning.