Assisting Personal Support Worker’s e-Training with AI Prediction
Bibliographic record
Abstract
Abstract The increasing need for effective caregiver training, particularly for Personal Support Workers, has led to the development of innovative e-training platforms. This study explores the application of advanced ML models to predict training outcomes and identify at-risk learners early in the process. The primary goal is to improve training completion rates while ensuring compliance with industry standards. We employed a range of ML models, including Decision Trees, Random Forest, Support Vector Machines, Neural Networks, to predict the likelihood of successful course completion using a dataset comprising over 27 million user interaction records. Feature engineering was used to extract key metrics such as module and lesson completion ratios. The results indicate that the Multilayer Perceptron model performed best, achieving an AUC score of 0.99, while K-NN also demonstrated strong performance with an AUC of 0.98. Key features such as module completion ratio and temporal progress were found to be significant predictors of training success. These findings suggest that integrating predictive analytics into e-training platforms can significantly enhance the effectiveness of PSW certification processes, ultimately supporting the growing demand for skilled caregivers in healthcare.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.004 |
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".