Predicting real-world response to mepolizumab in severe asthma using machine learning
Bibliographic record
Abstract
Mepolizumab reduces clinically significant exacerbations (CSE) in patients with severe asthma, but research is needed to better understand the factors driving response. This study aimed to identify predictors of mepolizumab response using machine learning. 122 variables from 685 patients of REALITI-A study were used as model inputs. Linear regression, random forest, and XGBoost were tested. The best performing algorithm based on R<sup>2</sup> was used to train the model to identify predictors of response, defined as CSE change between pre-exposure (1-year and run-in) and 1-year post-exposure. Shapley Additive Explanations (SHAP) ranked variables based on feature importance and estimated the direction of relationship between features and the outcome. The best performing algorithm was XGBoost (R<sup>2</sup>=0.83). The top 5 ranking predictors were: pre-exposure rates of CSE, body mass index (BMI), immunoglobulin E (IgE) levels, activity impairment, and baseline asthma control questionnaire (ACQ) score, with SHAP values of 2.25, 0.18, 0.12, 0.11 and 0.09, respectively (Figure 1). Furthermore, higher rates of pre-exposure CSE directly correlate, while higher BMI, activity impairment, and baseline ACQ scores inversely correlate with greater reductions in CSE. This study identified top predictors of response to mepolizumab and may facilitate developing a clinically relevant model to support improvement of outcomes for patients with severe asthma. <fig><object-id>erj;64/suppl_68/PA448/F1</object-id><object-id>F1</object-id><object-id>F1</object-id><graphic></graphic></fig>
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".