1
|
Bai T, Zhu X, Zhou X, Grathwohl D, Yang P, Zha Y, Jin Y, Chong H, Yu Q, Isberner N, Wang D, Zhang L, Kortüm KM, Song J, Rasche L, Einsele H, Ning K, Hou X. Reliable and Interpretable Mortality Prediction With Strong Foresight in COVID-19 Patients: An International Study From China and Germany. Front Artif Intell 2021; 4:672050. [PMID: 34541519 PMCID: PMC8446629 DOI: 10.3389/frai.2021.672050] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2021] [Accepted: 07/26/2021] [Indexed: 12/20/2022] Open
Abstract
Cohort-independent robust mortality prediction model in patients with COVID-19 infection is not yet established. To build up a reliable, interpretable mortality prediction model with strong foresight, we have performed an international, bi-institutional study from China (Wuhan cohort, collected from January to March) and Germany (Würzburg cohort, collected from March to September). A Random Forest-based machine learning approach was applied to 1,352 patients from the Wuhan cohort, generating a mortality prediction model based on their clinical features. The results showed that five clinical features at admission, including lymphocyte (%), neutrophil count, C-reactive protein, lactate dehydrogenase, and α-hydroxybutyrate dehydrogenase, could be used for mortality prediction of COVID-19 patients with more than 91% accuracy and 99% AUC. Additionally, the time-series analysis revealed that the predictive model based on these clinical features is very robust over time when patients are in the hospital, indicating the strong association of these five clinical features with the progression of treatment as well. Moreover, for different preexisting diseases, this model also demonstrated high predictive power. Finally, the mortality prediction model has been applied to the independent Würzburg cohort, resulting in high prediction accuracy (with above 90% accuracy and 85% AUC) as well, indicating the robustness of the model in different cohorts. In summary, this study has established the mortality prediction model that allowed early classification of COVID-19 patients, not only at admission but also along the treatment timeline, not only cohort-independent but also highly interpretable. This model represents a valuable tool for triaging and optimizing the resources in COVID-19 patients.
Collapse
Affiliation(s)
- Tao Bai
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xue Zhu
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Xiang Zhou
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Denise Grathwohl
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Pengshuo Yang
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Yuguo Zha
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Yu Jin
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Hui Chong
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Qingyang Yu
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Nora Isberner
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Dongke Wang
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lei Zhang
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - K Martin Kortüm
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Jun Song
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Leo Rasche
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Hermann Einsele
- Department of Internal Medicine II, University Hospital of Würzburg, Würzburg, Germany
| | - Kang Ning
- Key Laboratory of Molecular Biophysics of the Ministry of Education, Hubei Key Laboratory of Bioinformatics and Molecular-imaging, Department of Bioinformatics and Systems Biology, College of Life Science and Technology, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaohua Hou
- Division of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|