Pulmonary<scp>MRI</scp>and Cluster Analysis Help Identify Novel Asthma Phenotypes
Bibliographic record
Abstract
Background Outside eosinophilia, current clinical asthma phenotypes do not show strong relationships with disease pathogenesis or treatment responses. While chest x‐ray computed tomography (CT) phenotypes have previously been explored, functional MRI measurements provide complementary phenotypic information. Purpose To derive novel data‐driven asthma phenotypic clusters using functional MRI airway biomarkers that better describe airway pathologies in patients. Study Type Retrospective. Population A total of 45 patients with asthma who underwent post‐bronchodilator129Xe MRI, volume‐matched CT, spirometry and plethysmography within a 90‐minute visit. Field Strength/Sequence Three‐dimensional gradient‐recalled echo129Xe ventilation sequence at 3 T. Assessment We measured MRI ventilation defect percent (VDP), CT airway wall‐area percent (WA%), wall‐thickness (WT, WT* [*normalized for age/sex/height]), lumen‐area (LA), lumen‐diameter (D, D*) and total airway count (TAC). Univariate relationships were utilized to select variables for k‐means cluster analysis and phenotypic subgroup generation. Spirometry and plethysmography measurements were compared across imaging‐based clusters. Statistical Tests Spearman correlation (ρ), one‐way analysis of variance (ANOVA) or Kruskal–Wallis tests with post hoc Bonferroni correction for multiple comparisons, significance level 0.05. Results Based on limited common variance (Kaiser–Meyer–Olkin‐measure = 0.44), four unique clusters were generated using MRI VDP, TAC, WT* and D* (52 ± 14 years, 27 female). Imaging measurements were significantly different across clusters as was the forced expiratory volume in 1‐second (FEV1%pred), residual volume/total lung capacity and airways resistance. Asthma‐control (P = 0.9), quality‐of‐life scores (P = 0.7) and the proportions of severe‐asthma (P = 0.4) were not significantly different. Cluster1 (n = 15/8 female) reflected mildly abnormal CT airway measurements and FEV1with moderately abnormal VDP. Cluster2 (n = 12/12 female) reflected moderately abnormal TAC, WT and FEV1. In Cluster3 and Cluster4 (n = 14/6 female,n = 4/1 female, respectively), there was severely reduced TAC, D and FEV1, but Cluster4 also had significantly worse, severely abnormal VDP (7 ± 5% vs. 41 ± 12%). Data Conclusion We generated four proof‐of‐concept MRI‐derived clusters of asthma with distinct structure–function pathologies. Cluster analysis of asthma using129Xe MRI in combination with CT biomarkers is feasible and may challenge currently used paradigms for asthma phenotyping and treatment decisions. Evidence Level 3 Technical Efficacy Stage
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".