Explainable Machine Learning Framework for Dynamic Monitoring of Disease Prognostic Risk: Retrospective Cohort Study
Integrating static admission triage with daily, explainable RSF predictions enables early identification of patients with COVID-19 at high risk of deterioration. By surfacing phase-specific, actionable predictors, the framework supports timely interventions and more efficient resource allocation. Prospective, multicenter studies are warranted to validate its generalizability and clinical impact.
Authors
- Kenichi Kamachi
- Megumi Oya (ORCID: https://orcid.org/0000-0001-8016-2541)
- Tetsuo Ishikawa (ORCID: https://orcid.org/0000-0001-5418-5387)
- Eiryo Kawakami (ORCID: https://orcid.org/0000-0001-9955-4342)
- Masaharu Shinkai (ORCID: https://orcid.org/0000-0002-4012-2518)
- Masahiro Shinoda (ORCID: https://orcid.org/0000-0002-0288-5637)
- Kazuhiro Sakurada (ORCID: https://orcid.org/0000-0002-4858-2607)
- Koichi Ashizaki (ORCID: https://orcid.org/0000-0003-2292-9112)
- Shinichiro Ota (ORCID: https://orcid.org/0000-0002-0922-8656)
Institutions
- Chiba University (JP)
- Keio University (JP)
- New Tokyo Hospital (JP)
- Department of Mathematical Sciences (RU)
- RIKEN Center for Integrative Medical Sciences (JP)
- The University of Tokyo (JP)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2025-05-28
- DOI
- https://doi.org/10.2196/65585
- Citations
- 2
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.96