P302 The virtual patient stratifies patient-specific response to bronchial thermoplasty with high accuracy
Bibliographic record
Abstract
Introduction Bronchial Thermoplasty (BT) is an available therapy for severe asthma. However, we are unable to stratify a priori clinical responders limiting its widespread adoption. Aim To establish BT’s clinical benefit and identify responder attributes to enable clinical decision-making. Methods We pooled pre/post-BT patient biopsies from 8 sites (119 patients) that were analysed for airway smooth muscle (ASM) mass, reticular basement membrane, and epithelial integrity to assess the impact on airway remodelling: biological response. Clinical response was assessed via exacerbation and hospitalisation frequency, asthma control questionnaire scores (ACT, ACQ) and asthma quality of life questionnaire score (AQLQ). To stratify patient response, we used the virtual patient1 to create patient-specific digital avatars, simulated BT, and compared predictions vs clinical data. Results Patients showed significant reductions in ASM mass (mean±SD) 15.1±6.8% to 6.7±4.1%, basement membrane 6.4±2.5µm to 5.5±2.1µm, and improvement in epithelial integrity 30.7±19.1% to 39.9±16.9% (p<0.05 all). Annual asthma exacerbation rate decreased: 5.8±5.3 to 1.2±1.7 (p<0.001). Asthma-related hospital admissions decreased: 1.5±2.5 to 0.3±0.7 (p<0.001). ACT improved from 7.7±2.9 to 15.2±6.2, ACQ from 3.0±1.3 to 2.4±1.3, and AQLQ from 3.2±1.6 to 4.4±1.7 (p<0.05 all). The virtual patient predicted impact on airway remodelling with 90% and clinical response with 70% accuracy. Conclusions Bronchial Thermoplasty showed excellent biological and clinical response. Our computer model supports the view that BT benefits are largely an indirect vs direct result of heat-driven cell death. The model helped identify the patient profile most likely to benefit from Bronchial Thermoplasty. Reference Saunders, et al. Science Transl Med. 2019;11:eaao6451.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".