Optimize individualized energy delivery for septic patients using predictive deep learning models.
Our study established time-series prediction models for septic patients to optimize energy delivery in the ICU. We recommended permissive underfeeding only in the early acute phase. Later, increased energy intake may improve survival and settle energy debts caused by underfeeding.
Authors
- Hua Jiang (ORCID: https://orcid.org/0000-0003-1465-0170)
- Jun Zeng (ORCID: https://orcid.org/0000-0001-5319-6500)
- Charles Damien Lu
- Mingwei Sun (ORCID: https://orcid.org/0000-0002-0443-6173)
- Kexun Li (ORCID: https://orcid.org/0000-0003-1235-3164)
- Ruipeng Zhang (ORCID: https://orcid.org/0000-0003-3280-0128)
- Lu Wang (ORCID: https://orcid.org/0000-0002-7305-1496)
- Xuanlin Feng
- Qi Wang (ORCID: https://orcid.org/0000-0002-7028-4956)
- Wei Chen (ORCID: https://orcid.org/0000-0001-6717-0336)
- Chang Li (ORCID: https://orcid.org/0000-0003-0311-8701)
- Yu Wang (ORCID: https://orcid.org/0000-0002-8833-9564)
Institutions
- University of Electronic Science and Technology of China (CN)
- University of South Carolina (US)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Peking Union Medical College Hospital (CN)
Publication Details
- Journal
- PubMed
- Published
- 2024-09-01
- DOI
- https://doi.org/10.6133/apjcn.202409_33(3).0005
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00