Swansea University scientists are developing a diagnostic tool that would use Artificial Intelligence (AI) to quicken the process of detecting biomarkers in biofluids to rapid up health test results. The paper got published in Analytical Chemistry. It would result in quicker test results for health conditions like heart problems, joint health, and Alzheimer’s disease. The research can pave the way to reduce the hospital waiting time significantly and the option for self-screening and self-monitoring would be possible with the possibility of at-home diagnostic kits in the near future.
Biofluids including synovial fluid, blood plasma, and saliva have proteins that are crucial biomarkers for the diagnosis of many medical issues. The customised platform has been designed to detect the concentration of these proteins to help with the diagnosis of disease and monitoring its progression. Project lead, Dr Francesco Del Giudice, said, "Existing technologies for the measurements of macromolecules in biofluids are limited; they require a long turnaround time, or require complex protocols, thus calling for alternative, more suitable, methodologies aimed at such measurements."
He further added, "In our research, we looked at whether we could rapidly detect the different concentrations of macromolecules in solution at different temperatures using only 100 mL of sample (equivalent to 2 drops of blood). The key innovation is providing a result within 2 minutes, which is a leap forward compared to standard testing that can take several hours. What this means for the future is that our proof-of-concept study can be further developed as a tool to help clinicians make decisions on clinical data obtained quickly. We also foresee developing this further for an at-home-point-of-care self-screening diagnostic platform."
Dr Claire Barnes, a co-author of the work, said, "The ability of Artificial Intelligence to drive down the time required to complete various tasks has been demonstrated across a number of disciplines. The advantage of the speed offered by the implementation of machine learning allowed us to adjust almost in real-time the experimental parameters to fulfil the requirements of the theoretical model associated with this work."
"Whilst at present we employed machine learning for the purposes of automating our work, the ability to use large amounts of data to imitate aspects of human intelligence and reasoning, allowing a system to learn, predict and make recommendations, is something we would like to explore further and will form the basis of our future work in this area," she further added.