Mucosal and cellular immune measures predicted SARS-CoV-2 reinfection
Source check: Source checked. Not independent scientific confirmation.
Finding: Across two community cohorts followed for a median 10 months, 1,156 participants had 128 observed reinfections. An interpretable XGBoost model identified nasal spike-specific IgA and spike-specific CD4+ central-memory T cells as informative predictors of subsequent reinfection. Predictive associations do not establish that the immune measures causally prevent reinfection or imply clinical benefit; the reviewed evidence does not establish testing of a frozen model before new outcomes.
Technology: Interpretable XGBoost
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- XGBoost integrated mucosal antibody and cellular immune measurements to predict observed reinfection.
- Test and result
- Across two community cohorts followed for a median 10 months, 1,156 participants had 128 observed reinfections. An interpretable XGBoost model identified nasal spike-specific IgA and spike-specific CD4+ central-memory T cells as informative predictors of subsequent reinfection.
- Limitation / still unknown
- Predictive associations do not establish that the immune measures causally prevent reinfection or imply clinical benefit; the reviewed evidence does not establish testing of a frozen model before new outcomes.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/articles/PMC13700530
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Original full-text Methods and Results reviewed from the primary paper or preprint; first result-bearing version checked from the supplied source review; author affiliations checked against exact-DOI metadata where available..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.