Archive Number: 4.683
Status of Thesis: Open
Date of start: 2020-10-15
Data analysis techniques can help to create a personalized, patient-centric healthcare, thereby improving treatment for patients. However, high privacy requirements in the healthcare industry traditionally inhibit data sharing, and thus, the analysis of large amounts of data. New cryptographic approaches, such as homomorphic encryption, secure multiparty computation, or zero knowledge proofs allow computation with data while maintaining certain privacy and security standards. In this thesis, you will dive deeper into these technologies and apply these to healthcare data sets. You can combine the topic with machine learning and / or blockchain topics. Ultimately, you will enable private data analysis techniques in healthcare!
Possible topics include, but are not limited to:
- Evaluation of cryptographic protocols for contact tracing, or machine learning on medical imaging data
- Integration of cryptographic protocols with a blockchain
This is an umbrella topic since topics of interest change rapidly. A specific topic will be selected during a first meeting.
Introductory literature and material:
- Jones, M., Johnson, M., Shervey, M., Dudley, J. T., & Zimmerman, N. (2019). Privacy-preserving methods for feature engineering using blockchain: review, evaluation, and proof of concept. Journal of medical Internet research, 21(8), e13600.
- Tjell, Katrine, Jaron Skovsted Gundersen, and Rafael Wisniewski. "Privacy Preservation in Epidemic Data Collection." arXiv preprint arXiv:2004.14759 (2020).