A planning decision support model integrating bioinformatics and occupational health data with an emphasis on biomechanics
Year: 2025
Type: article
Abstract: In today’s rapidly evolving workplace environments, the integration of bioinformatics with occupational health data presents a unique opportunity to enhance employee well-being and optimize workplace safety, especially from the perspective of biomechanics. Existing systems often fail to account for individual genetic factors and the biomechanical aspects of the work environment when assessing occupational health risks, resulting in an increase in workplace-related health problems and less effective health treatments. The primary objective of this study is to develop a planning decision support model that integrates bioinformatics and occupational health data to recognize health risks and generate tailored interventions for employees. Incorporating biomechanics, we explore the impact of physical factors such as workstation ergonomics, repetitive motion patterns, and force exertion levels in the work environment on employee health, and analyze their relationship with genetic predispositions. For example, we study how specific genetic traits may interact with biomechanical stressors to increase the likelihood of musculoskeletal disorders. Initially, study data were collected from diverse sources, including bioinformatics databases and occupational health records, ensuring a comprehensive dataset for effective model training and validation. Data cleaning and Z-score normalization were used in the data preparation stage. Feature extraction was performed using Linear Discriminate Analysis (LDA) to reduce dimensionality from preprocessed data. Data fusion was accomplished by sharing information between bioinformatics and occupational health datasets, enabling a more comprehensive decision support model. The study proposed a Dynamic Bacterial Foraging fine-tuned Efficient Adaptive Boosting (DBF-EAdaBoost) method that integrates dynamic bacterial foraging optimization with adaptive boosting techniques to significantly enhance classification performance in bioinformatics and occupational health data analysis. The proposed algorithms offer high accuracy (0.93), precision (0.987), brier score (0.100), AUC (0.92), and log loss (0.314) in forecasting potential health issues based on workplace exposures, biomechanical factors, and genetic predispositions. To enhance the practicality of the research, a more detailed explanation of the implementation process and advantages of the proposed DBF-EAdaBoost algorithm is provided. Consider including real-world case studies to demonstrate the model’s application and the actual effectiveness of health interventions in real workplace environments. For instance, we can present a case where the model was applied in a manufacturing plant to predict and prevent musculoskeletal disorders among workers by analyzing their biomechanical workloads and genetic profiles, and implementing appropriate ergonomic interventions. The planning decision support model serves as a significant tool for public health officials, policymakers, and occupational health professionals, promoting data-driven decisions that enhance health outcomes.
DOI: 10.62617/mcb528
Authors: Jing Li, Wei Liu, Feifei Chen
Language: English
Subfield: Occupational Therapy
Field: Health Professions
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4405975242