Characterizing accident narratives with word embeddings: Improving accuracy, richness, and generalizability

Goldberg, David M.

doi:10.1016/j.jsr.2021.12.024

Cited by 15 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, one of the top labels for the type of event is contact with objects and equipment (E06) and within this category, it expands into several sub-labels like needlestick (E61) and stuck by objects or equipment (E62). Nonetheless, to prevent the scarce representation for each criterion [ 29 ], only top labels are used for further analysis. Also, the non-classifiable class in part of the affected body, type of event, and type of source are re-categorized into ‘Other(s)’.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance

Khairuddin

Hui

Hasikin‬

et al. 2022

IJERPH

View full text Add to dashboard Cite

Forecasting the severity of occupational injuries shall be all industries’ top priority. The use of machine learning is theoretically valuable to assist the predictive analysis, thus, this study attempts to propose a feature-optimized predictive model for anticipating occupational injury severity. A public database of 66,405 occupational injury records from OSHA is analyzed using five sets of machine learning models: Support Vector Machine, K-Nearest Neighbors, Naïve Bayes, Decision Tree, and Random Forest. For model comparison, Random Forest outperformed other models with higher accuracy and F1-score. Therefore, it highlighted the potential of ensemble learning as a more accurate prediction model in the field of occupational injury. In constructing the model, this study also proposed the feature optimization technique that revealed the three most important features; ‘nature of injury’, ‘type of event’, and ‘affected body part’ in developing model. The accuracy of the Random Forest model was improved by 0.5% or 0.895 and 0.954 for the prediction of hospitalization and amputation, respectively by redeveloping and optimizing the model with hyperparameter tuning. The feature optimization is essential in providing insight knowledge to the Safety and Health Practitioners for future injury corrective and preventive strategies. This study has shown promising potential for smart workplace surveillance.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Five performance metrics; accuracy, precision, recall, F1-score, and AUC value were employed to understand and interpret the performance prediction of the machine learning models. In each metric used in this experiment, the scores ranged from 0 to 1, in which a +1 score represents model perfection [ 29 ].…”

Section: Methodsmentioning

confidence: 99%

Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance

Khairuddin

Hui

Hasikin‬

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…Outside the health care system, DSS has also been found useful to automatically classify injury data, particularly occupational injury data. [16][17][18][19] While AI/ML-based DSS offers several benefits, their adoption in health care organizations is sometimes slow due to technology adoption challenges. A previous study recommended that for successful adoption and effectiveness of a DSS in hospitals, it is important to have top management support, active involvement of clinical departments, and robust hospital-wide information infrastructure to collect and process good quality data from multiple sources, among other factors.…”

Section: Related Workmentioning

confidence: 99%

“…Outside the health care system, DSS has also been found useful to automatically classify injury data, particularly occupational injury data. 16 17 18 19…”

Section: Background and Significancementioning

confidence: 99%

Application of a Machine Learning–Based Decision Support Tool to Improve an Injury Surveillance System Workflow

et al. 2022

View full text Add to dashboard Cite

Background Emergency department (ED)-based injury surveillance systems across many countries face resourcing challenges related to manual validation and coding of data. Objective This paper describes the evaluation of a machine learning-based Decision Support Tool (DST) to assist injury surveillance departments in the validation, coding and use of their data, comparing outcomes in coding time and accuracy pre- and post-implementation. Methods Manually coded injury surveillance data has been used to develop, train and iteratively refine a machine learning-based classifier to enable semi-automated coding of injury narrative data. This paper describes a trial implementation of the machine learning-based DST in the Queensland Injury Surveillance Unit (QISU) workflow using a major pediatric hospital's emergency department data comparing outcomes in coding time and accuracy pre- and post-implementation. Results The study found a 10% reduction in manual coding time after the DST was introduced. The Kappa statistics analysis in both DST-assisted and unassisted data shows increases in accuracy across three data fields; injury intent (85.4% unassisted vs. 94.5% assisted), external cause (88.8% unassisted vs. 91.8% assisted) and injury factor (89.3% unassisted vs. 92.9% assisted). The classifier was also used to produce a timely report monitoring injury patterns during the COVID-19 pandemic. Hence, it has the potential for near real-time surveillance of emerging hazards to inform public health responses. Conclusions The integration of the DST into the injury surveillance workflow shows benefits as it facilitates timely reporting and acts as a DST in the manual coding process.

show abstract

“…This is done through feature engineering or text representation techniques, such as text vectorizers; Bag of Words (BoW), and Term Frequency-Inverse Document Frequency (TF-IDF), as well as, the word embeddings pre-trained model, such as Word2Vec and Global Vector (GloVe). Both text vectorizers, BoW and TF-IDF are easily executed and compatible ( Pan et al, 2020 ); however, they do not define semantic relationships in context ( Goldberg, 2022 ). To overcome this limitation, the word embeddings approach is recommended as it is capable of preserving the relationship of semantic and syntactic linguistics in text documents ( Young et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Khairuddin,

Sankaranarayanan,

Hasikin

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Background This study introduced a novel approach for predicting occupational injury severity by leveraging deep learning-based text classification techniques to analyze unstructured narratives. Unlike conventional methods that rely on structured data, our approach recognizes the richness of information within injury narrative descriptions with the aim of extracting valuable insights for improved occupational injury severity assessment. Methods Natural language processing (NLP) techniques were harnessed to preprocess the occupational injury narratives obtained from the US Occupational Safety and Health Administration (OSHA) from January 2015 to June 2023. The methodology involved meticulous preprocessing of textual narratives to standardize text and eliminate noise, followed by the innovative integration of Term Frequency-Inverse Document Frequency (TF-IDF) and Global Vector (GloVe) word embeddings for effective text representation. The proposed predictive model adopts a novel Bidirectional Long Short-Term Memory (Bi-LSTM) architecture and is further refined through model optimization, including random search hyperparameters and in-depth feature importance analysis. The optimized Bi-LSTM model has been compared and validated against other machine learning classifiers which are naïve Bayes, support vector machine, random forest, decision trees, and K-nearest neighbor. Results The proposed optimized Bi-LSTM models’ superior predictability, boasted an accuracy of 0.95 for hospitalization and 0.98 for amputation cases with faster model processing times. Interestingly, the feature importance analysis revealed predictive keywords related to the causal factors of occupational injuries thereby providing valuable insights to enhance model interpretability. Conclusion Our proposed optimized Bi-LSTM model offers safety and health practitioners an effective tool to empower workplace safety proactive measures, thereby contributing to business productivity and sustainability. This study lays the foundation for further exploration of predictive analytics in the occupational safety and health domain.

show abstract

Characterizing accident narratives with word embeddings: Improving accuracy, richness, and generalizability

Cited by 15 publications

References 44 publications

Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance

Occupational Injury Risk Mitigation: Machine Learning Approach and Feature Optimization for Smart Workplace Surveillance

Application of a Machine Learning–Based Decision Support Tool to Improve an Injury Surveillance System Workflow

Contextualizing injury severity from occupational accident reports using an optimized deep learning prediction model

Contact Info

Product

Resources

About