Artificial Intelligence for Predicting Emergency Departments Visits in Kids with Asthma (AIRE-KIDS)
Bibliographic record
Abstract
<bold>Background/Objectives:</bold> Asthma is common in children and leads to repeated emergency department (ED) visits and hospitalization in some. Currently there are limited tools for rapidly and accurately identifying the patients at highest risk for repeat visits. Recently, machine learning (ML) methods have been explored for predicting repeat asthma visits in adults. We aimed to use ML to accurately predict repeat asthma visits in children. <bold>Methods:</bold> We trained and compared the performance of multiple types of ML models (light gradient-boosting machine (LGBM), eXtreme Gradient Boosting (XGBoost), decision tree and classification and regression tree (CART)) using a nested cross-validation design to predict repeat ED visits and hospitalization within one year from an initial asthma ED visit in children 0-18 years old. We used a historical cohort accrued from a single pediatric center in Ottawa, Canada between Feb 1, 2017 to Feb 28, 2019, with outcomes observed up to Feb 28, 2020. We extracted 63 clinical features from the electronic health record that linked with air pollution and neighborhood marginalization data. <bold>Results:</bold> Our sample size comprised 3145 patients, with 2900 (34.6% female, mean age 4.64 years ±4.03 SD) meeting inclusion criteria. Preliminary evaluation showed that LGBM predicted the best with an area under the curve (AUC) of 0.88 and scaled Brier score of 0.41 for repeat ED visits and AUC of 0.89 with scaled Brier score of 0.18 for repeat hospitalization. <bold>Conclusion:</bold> ML approaches accurately predicted repeat asthma ED visits and hospitalization in children and following prospective validation, could enable targeted prevention for the most vulnerable children.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".