Predicting mechanical neck pain intensity in computer professionals using machine learning: identification and...

Area of Science:

• Occupational Health
• Biomedical Informatics
• Musculoskeletal Disorders

Background:

• Mechanical neck pain is a growing concern for computer professionals due to prolonged screen time.
• Understanding the multifactorial contributors to neck pain is crucial for effective intervention.

Purpose of the Study:

• To investigate the relationship between neck pain intensity, anthropometric data, cervical range of motion, and disability in computer professionals.
• To apply advanced machine learning techniques to identify key predictors of neck pain.

Main Methods:

• 75 computer professionals with neck pain were assessed using the Visual Analog Scale (VAS), anthropometric measurements, Universal Goniometer for cervical range of motion (ROM), and the Neck Disability Index (NDI).
• Data analysis involved SPSS for descriptive statistics and machine learning algorithms to determine feature importance.
• The k-Nearest Neighbors (kNN) algorithm's performance was evaluated using a confusion matrix.

Main Results:

• The Neck Disability Index (NDI) score was consistently identified as the most significant predictor across various machine learning models.
• While age and computer usage hours showed variable importance, anthropometric metrics like BMI did not rank consistently.
• The study achieved 56% accuracy in predicting pain intensity (VAS scores) using the analyzed dataset.

Conclusions:

• Machine learning effectively elucidates the complex factors contributing to neck pain in computer professionals.
• Identifying the NDI as a primary predictor emphasizes the importance of functional disability in pain management.
• These findings support the development of personalized ergonomic interventions and targeted health campaigns for this occupational group.