Machine Learning–Based Decision Support Framework for Construction Injury Severity Prediction and Risk Mitigation
Bibliographic record
Abstract
Construction is a key pillar in the global economy, but it is also an industry that has one of the highest fatality rates. The goal of the current study is to employ machine learning in order to develop a framework based on which better-informed and interpretable injury-risk mitigation decisions can be made for construction sites. Central to the framework, generalizable glass-box and black-box models are developed and validated to predict injury severity levels based on the interdependent effects of identified key injury factors. To demonstrate the framework utility, a data set pertaining to construction site injury cases is utilized. By employing the developed models, safety managers can evaluate different construction site safety risk levels, and the potential high-risk zones can be flagged for devising targeted (i.e., site-specific) proactive risk mitigation strategies. Managers can also use the framework to explore complex relationships between interdependent factors and corresponding cause-and-effect of injury severity, which can further enhance their understanding of the underlying mechanisms that shape construction safety risks. Overall, the current study offers transparent, interpretable and generalizable decision-making insights for safety managers and workplace risk practitioners to better identify, understand, predict, and control the factors influencing construction site injuries and ultimately improve the safety level of their working environments by mitigating the risks of associated project disruptions.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".