In the last several years there have been active developments in several new as well as improvements in existing diagnostic technologies globally. Advancements in sensing technologies including multi-spectral and hyper-spectral sensing have the potential to transform large field scale mapping of crops for early assessment of plant health issues. When integrated with traditional crop scouting sensing approaches can help improve early detection of plant diseases. Other sensing approaches like Raman spectroscopy have now moved from fixed lab-equipment models into portable and easy-to-handle models and thus widely tested for utility for plant disease assessments. On the other hand, there are many developments in lab-based molecular diagnostic methods transitioning to field-based diagnostic systems. An example is Recombinase Polymerase Amplification (RPA) that can be run using battery-powered small-equipment’s or in a lateral-flow format. Machine learning approaches and artificial Intelligence tools for plant disease image classification are getting better at separating plant health issues. However, the need for major global engagements to bring greater diversity of diagnostically validated plant sample imagery from field settings is critical to effective model development and deployment. This presentation will cover the considerations to be taken while integrating the above and several other new technologies into the existing diagnostic framework for plant health issues.