The competitive advantage of the project lies in its non-invasive photoacoustic approach that eliminates the need for blood sampling, enabling safer and more patient-friendly diagnosis of haemoglobin dysfunction. It also utilises lower-cost hardware combined with AI-driven analysis, improving accessibility while maintaining high diagnostic accuracy and efficiency in detecting conditions such as methemoglobinemia and carboxyhaemoglobinemia.

To replace the conventional method of detecting methemoglobinemia and carboxyhemoglobinemia, which relies on invasive blood sampling (phlebotomy), this technology offers a non-invasive alternative approach for diagnosis.

Absorption of visible light in the skin induces thermal expansion, generating acoustic waves. These waves are then processed to extract information on the concentration of different functional states of haemoglobin proteins in the blood.

The project introduces a non-invasive visible photoacoustic system for diagnosing haemoglobin dysfunction, replacing traditional blood sampling methods. It uses light-induced acoustic signals from the skin to analyse haemoglobin states and is enhanced with a hybrid deep learning model to improve diagnostic accuracy and reliability.