An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data

• Published in: NPJ digital medicine Vol. 5; no. 1; pp. 5 - 9
• Main Authors: Kim, Chris K., Choi, Ji Whae, Jiao, Zhicheng, Wang, Dongcui, Wu, Jing, Yi, Thomas Y., Halsey, Kasey C., Eweje, Feyisope, Tran, Thi My Linh, Liu, Chang, Wang, Robin, Sollee, John, Hsieh, Celina, Chang, Ken, Yang, Fang-Xue, Singh, Ritambhara, Ou, Jie-Lin, Huang, Raymond Y., Feng, Cai, Feldman, Michael D., Liu, Tao, Gong, Ji Sheng, Lu, Shaolei, Eickhoff, Carsten, Feng, Xue, Kamel, Ihab, Sebro, Ronnie, Atalay, Michael K., Healey, Terrance, Fan, Yong, Liao, Wei-Hua, Wang, Jianxin, Bai, Harrison X.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 14.01.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 639/705/117; 692/700/1421/1770; Artificial intelligence; Automation; Biomedicine; Biotechnology; Coronaviruses; COVID-19; Digital technology; Medical diagnosis; Medical technology; Medicine; Medicine & Public Health; Pipelines
• ISSN: 2398-6352; 2398-6352
• DOI: 10.1038/s41746-021-00546-w

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital’s image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.