Protocol for processing multivariate time-series electronic health records of COVID-19 patients
The lack of standardized techniques for processing complex health data from COVID-19 patients hinders the development of accurate predictive models in healthcare. To address this, we present a protocol for utilizing real-world multivariate time-series electronic health records of COVID-19 patients. We describe steps for covering the necessary setup, data standardization, and formatting. We then provide detailed instructions for creating datasets and for training and evaluating AI models designed to predict two key outcomes: in-hospital mortality and length of stay. For complete details on the use and execution of this protocol, please refer to Gao et al.<sup>1</sup>.
Authors
- Zixiang Wang (ORCID: https://orcid.org/0009-0000-1257-9580)
- Chengwei Pan (ORCID: https://orcid.org/0000-0003-0497-7903)
- Dong Sui (ORCID: https://orcid.org/0000-0003-4128-8402)
- Yasha Wang (ORCID: https://orcid.org/0000-0002-8026-9688)
- Yinghao Zhu (ORCID: https://orcid.org/0000-0002-2640-6477)
- Ling Wang (ORCID: https://orcid.org/0000-0002-7621-2312)
- Xiaoyun Zhang (ORCID: https://orcid.org/0000-0003-2698-7299)
- Liantao Ma
- Tianlong Wang (ORCID: https://orcid.org/0000-0002-5869-5517)
- Junyi Gao (ORCID: https://orcid.org/0000-0002-4951-8682)
- Yuntao Zhang (ORCID: https://orcid.org/0000-0003-4514-0384)
Institutions
- King University (US)
- Xuzhou Medical College (CN)
- Peking University (CN)
- Ministry of Education (RO)
- Health Data Research UK (GB)
- Beihang University (CN)
Publication Details
- Journal
- STAR Protocols
- Published
- 2025-03-01
- DOI
- https://doi.org/10.1016/j.xpro.2025.103669
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00