Several studies have been conducted to investigate the influence of transport-related daily activities on health parameters using conventional methods. These traditional methods are based on several assumptions that produce bias in results. Besides, travel mode choice (TMC) data is complex and imbalanced whereas traditional methods fail to handle imbalances and complex datasets. Therefore, the current study aims to use a reciprocal approach to study the influence of health parameters on work TMC using both traditional and modern techniques. Some of the variables - based on the scope of the study, are used from the 2022 National Household Travel Survey (NHTS), California, to study the correlation between health parameters and work TMC. RStudio is used for multivariate regression analysis, whereas several machine learning (ML) algorithms were developed to compare their results based on the classification matrix and to suggest the best prediction model for work TMC. The statistical analysis shows that all the models are statistically significant with a p-value of less than 0.005 and the models are extremely acceptable range with an R2 value of over 30%. Those individuals with disabilities - using manual wheelchairs were the most significant feature that influenced work TMC which shows that health influences work TMC. The current professes those modern techniques outperformed traditional methods where SVM followed by RF shows the best accuracy and precision. SVM shows the best predictions with an accuracy of 47%, whereas RF with an accuracy of 44% and a precision of 36%. The current study helps urban planners and policymakers to provide a more convenient transportation system for disabled people and enhance the reliability, frequency, and safety of public transportation.