Two-step deep-learning candidemia prediction model using two large time-sequence electronic health datasets
A two-step deep-learning framework integrating candidemia and mortality risk may support early identification of high-risk patients and facilitate timely empiric antifungal therapy.Prospective studies are warranted to confirm the findings.
Authors
- Francisco M. Guerra (ORCID: https://orcid.org/0000-0001-7865-7350)
- Max Adelman
- Hisato Yoshida (ORCID: https://orcid.org/0000-0003-1468-1903)
- Hitoshi Yoshimura
- Ziqian Xie (ORCID: https://orcid.org/0000-0001-6541-1773)
- Degui Zhi
- Laila Rasmy
- María Alejandra Pérez
- Masayuki Nigo
- Francis Ifiora
- Cesar A. Arias
- Stephen L Jones
Institutions
- University of Fukui (JP)
- Houston Methodist (US)
- Cornell University (US)
- Methodist Hospital (US)
- Methodist Hospital (US)
- The University of Texas Medical Branch at Galveston (US)
- The University of Texas Health Science Center at Houston (US)
Publication Details
- Journal
- medRxiv
- Published
- 2026-03-04
- DOI
- https://doi.org/10.64898/2026.03.03.26347531
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health
- Houston Methodist Research Institute
- Japan Society for the Promotion of Science
- National Institute of Allergy and Infectious Diseases