Prediction of donation return rate in young donors using machine‐learning models
Bibliographic record
Abstract
Abstract Background and objectives The identification of factors leading to high or low return rates among volunteer blood donors is increasingly important to maintain sufficient blood supply. A particular focus on young donors is an essential component of blood bank donor retention strategy. By means of large databases, our aim was to predict the donation frequency pattern of young donors using a random forest model, to potentially improve donor retention and increase donation frequency. Materials and methods Random forests are an ensemble learning method for classification and regression designed to produce accurate predictions that do not overfit the data. They consist of a large number of independent decision trees that operate as an ensemble and classify data into groups in a sequential manner, using time‐specific cut‐offs to differentiate groups into branches. Since a large number of trees are grown, prediction of donation behaviour in young donors will be made with limited generalization errors. Results The final dataset analysed was composed of 81 986 donors aged 18–24 at the last donation. The model correctly predicts more than 91% of the donation frequencies, with an overall error rate of 8·16% and specific error rates of 4·6% and 12·3% for ‘unreturned donor’ and ‘returned donor’ groups, respectively. The best predictive variables used in the model appear to be the number of contacts used by the marketing department, the donors’ age, the number of adverse effects during donation, the donors’ status and the ethnicity. Conclusion Our results provide relevant information for interpreting donor behaviour and could contribute to the improvement of initiatives by blood services to increase donation return rate.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".