Predicting mechanical neck pain intensity in computer professionals using machine learning: identification and correlation of key features.

INTRODUCTION

Mechanical neck pain has become prevalent among computer professionals possibly because of prolonged computer use. This study aimed to investigate the relationship between neck pain intensity, anthropometric metrics, cervical range of motion, and related disabilities using advanced machine learning techniques.

METHOD

This study involved 75 computer professionals, comprising 27 men and 48 women, aged between 25 and 44 years, all of whom reported neck pain following extended computer sessions. The study utilized various tools, including the visual analog scale (VAS) for pain measurement, anthropometric tools for body metrics, a Universal Goniometer for cervical ROM, and the Neck Disability Index (NDI). For data analysis, the study employed SPSS (v16.0) for basic statistics and a suite of machine-learning algorithms to discern feature importance. The capability of the kNN algorithm is evaluated using its confusion matrix.

RESULTS

The "NDI Score (%)" consistently emerged as the most significant feature across various algorithms, while metrics like age and computer usage hours varied in their rankings. Anthropometric results, such as BMI and body circumference, did not maintain consistent ranks across algorithms. The confusion matrix notably demonstrated its classification process for different VAS scores (mild, moderate, and severe). The findings indicated that 56% of the pain intensity, as measured by the VAS, could be accurately predicted by the dataset.

DISCUSSION

Machine learning clarifies the system dynamics of neck pain among computer professionals and highlights the need for different algorithms to gain a comprehensive understanding. Such insights pave the way for creating tailored ergonomic solutions and health campaigns for this population.