A digital twin is a dynamic virtual copy of an individual that operates and behaves identically to the real-world counterpart. Shaddo ingests data captured from sensors (wearables), organisational information and voluntary user input. Machine learning models then harvest the data, identify patterns and replicate processes to predict possible performance outcomes and the emergence of potential issues. Shaddo enables cross-functional teams to collaboratively design, test and monitor complex biopsychosocial feedback from their people in an interactive and immersive way. Comparison of historical and ongoing data provides organisations with critical insights/feedback into possible biopsychosocial factors that impact health and performance.

Shaddo takes a holistic approach to performance by accepting the notion that biological determinants, social context and psychological factors need to be considered in conjunction with one another, not measured as sperate factors. 

We have developed a new data-driven approach for predictive health and performance management. Utilising wearable technology and our own bespoke machine learning models for analysis, we uncover patterns that provide preventative and proactive health management suggestions coupled with early warning insights. We have developed a robust learning model technique that can be applied broadly across high-stress communities (sport, emergency services, mission critical teams) to improve performance and preparedness. The predictive nature of the analysis on holistic data captured in real time targets the identification of issues before they occur. Importantly, as more data is gathered and advances in wearable technologies continue to improve, the accuracy and sophistication of our learning process will continue to develop.