Musculoskeletal disorders can cause a considerable effect on an individual’s quality of life. As per the Global Burden of Disease study 2021, the death toll due to these disorders is 1.21 lakh in India and 5.73 lakh in the worldwide. In general, the problem can be segregated into upper and lower body parts. There does not exist any single model which can detect abnormalities in both upper and lower extremities, due to the absence of single dataset which contains radiographs from both upper and lower limbs. Therefore, in this study, an automated approach is proposed to integrate the MURA and LERA datasets to create a unified dataset that enables comprehensive analysis of abnormalities across entire musculoskeletal system. The proposed automated approach is executed in two phases: In Phase-I, the directory structure of both datasets is reorganized. In Phase-II, image augmentation techniques are applied to mitigate the imbalance issues. The unified dataset that is thus formed increases the availability of data, hence allowing models to capture more patterns and relationships that might help researchers train their models on this dataset with increased accuracy and robustness. The creation of the unified dataset marks a major advancement, as it offers a comprehensive and balanced resource for training models to detect musculoskeletal abnormalities. The automated approach developed in this work shall prove to be an ideal solution for the integration of different datasets, ensuring continuous improvement of diagnostic tools and ensuring that models remain robust and effective in varied datasets and real-world scenarios.