Quantum Application for Pathogen Detection
The Challenge
Pathogen detection using PCR testing of human serum is destructive, and not reliable. How to test human serum non-destructively, quicker than PCR testing and with greater accuracy in pathogen detection?
Our Solution
By leveraging quanvolutional neural networks, we developed a novel approach that uses Raman Spectroscopy data allowing non-destructive testing for pathogen detection in human serum. We published our research in IEEE Explore recently with the results of this approach and are in the process of commercializing it via pilots with interested sponsoring healthcare providers and pathology labs. The research paper can be found here. Please contact us by scheduling a meeting if interested in discussing further details and engaging with Pivotport in a pilot project.
Results
We achieve outstanding performance across seven evaluation metrics:
- Jaccard index(JI) of 97.73%
- Accuracy of 98.92%
- F1-score of 98.85%
- Recall of 97.73%
- Matthews correlation coefficient (MCC) of 97.86%
- Precision of 100%
- Area Under the Curve (AUC) score of 98.86%
The results demonstrate that proposed novel QNN outperforms classical models without overfitting. Our findings highlight the potential of QNN in revolutionizing diagnostic tools for critical diseases.
Future Applications
This breakthrough opens new possibilities for:
- High volume throughput for rapid testing near epidemic wavefronts in human population
- Pathogen detection with the ability to use human serum non-destructively for different pathogens using multipass Raman Spectroscopy and QNN driven HPC cloud and Quantum platform architecture
- Epidemic propagation prediction models