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

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.

Factors Associated with COVID-19 among Healthcare Workers in Kedah in 2021: A Cross-Sectional Study.

This study aimed to examine the characteristics of HCWs infected with COVID-19 and factors associated with healthcare-associated infection. A cross-sectional study, using secondary data of COVID-19 HCW cases from a registry developed by the Occupational and Environmental Health Unit (OEHU) in Kedah State Health Department, Malaysia, was analysed using Excel and STATA version 14.0. Descriptive analysis and multiple logistic regression were conducted to identify the factors for healthcare-associated COVID-19 infection. A total of 1679 HCWs tested positive for COVID-19 between 1 January 2021 and 19 September 2021. The infection was mainly non-healthcare-associated (67.0%), with healthcare-associated cases contributing to only 33% of the cases. The significant factors associated with healthcare-associated transmission were the following: doctor (aOR = 1.433; 95% CI = 1.044, 1.968), hospital setting (aOR = 1.439; 95% CI = 1.080, 1.917), asymptomatic (aOR = 1.848; 95% CI = 1.604, 2.130), incompletely or not vaccinated (aOR = 1.400; 95% CI = 1.050, 1.866) and CT-value ≥ 30 (aOR = 2.494; 95% CI = 1.927, 3.226). Identifying factors of healthcare-associated infection would help in planning control measures preventing healthcare-associated transmission in the workplace. However, more than half of COVID-19 cases among HCWs involved non-healthcare-associated COVID-19 infection, and, thus, requires further study to identify high-risk behaviours.