Construction workers are prone to physical and mental stress because of the characteristics of the construction industry. Researchers and practitioners agree that physical and mental stress should be proactively managed to mitigate their ill-effects which range from making errors to causing accidents and short term to long term illnesses. Accordingly, numerous research endeavors have pursued automated solutions for their monitoring to replace manual and subjective physical and mental stress monitoring. While these studies have been successful, they attempted to monitor either physical stress or mental stress at a time. Studies have shown that many times, construction workers are simultaneously exposed to both, physical and mental stress, necessitating automated simultaneous monitoring of physical and mental stress for more comprehensive workload evaluation. Therefore, the aim of the current study is to assess the possibility of accurately monitoring physical and mental stress simultaneously using physiological measures and machine learning algorithms. For the purpose, experiments were conducted that comprised of physical and mental stress scenarios. The results showed that using 56 features derived from heart rate, skin temperature, breathing rate and skin conductance, an accuracy of 94.7% was achieved for simultaneous physical and mental stress monitoring. Additionally, the study further investigated the impact of varying the features and physiological measures and discussed the potential future work in this direction. Overall, this study for the first time, demonstrated that it is possible to simultaneously monitor physical and mental stress with high accuracy. Moreover, it has laid the foundation for future studies to enable simultaneous physical and mental stress monitoring on actual job sites.