MRI radiomics supports individualized Duchenne disease-trajectory reconstruction
Source check: Source checked. Not independent scientific confirmation.
Finding: XGBoost combined baseline MRI radiomics and clinical features to estimate muscle fat-fraction trajectory parameters in Duchenne muscular dystrophy. The final dataset included 98 unique participants, with 68 soleus and 64 vastus-lateralis analyses; held-out reconstructed trajectories had reported mean absolute errors of 0.04 and 0.06. Targets came from a previously fitted nonlinear mixed-effects model, rather than directly observed trajectory parameters. The retrospective analysis identified candidate progression subgroups but did not establish treatment response, prospective prediction or external generalizability.
Technology: XGBoost; MRI radiomics
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Participant-level 80:20 train/test split; XGBoost estimates NLME-derived trajectory descriptors from baseline radiomic/clinical features; reconstruction compared with observed fat fraction. Derived targets can shrink sparse subject trajectories; this is not new prospective clinical utility.
- Test and result
- Held-out participant trajectory reconstruction compared with observed longitudinal fat fractions.
- Limitation / still unknown
- Independent cohort validation, robustness of derived targets and benefits for clinical trial design remain unestablished.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13752581/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 21 Nov 2026. Review scope: Primary full article Methods, Results and limitations plus Europe PMC bibliographic metadata; PMC full article..
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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.