@article{Panchangam Nivarthi_2022, title={How Privacy-Enhanced Technologies (Pets) are Transforming Digital Healthcare Delivery}, volume={90}, url={https://asrjetsjournal.org/index.php/American_Scientific_Journal/article/view/8268}, abstractNote={<p>Privacy Enhancing Technologies (PETs) are playing a crucial role in maturing digital healthcare delivery for mainstream adaption from both a social and regulatory perspective. Different PETs are improving different aspects of digital healthcare delivery, and we have chosen seven of them to observe in the context of their influence on digital healthcare and their use cases. Homomorphic encryption can provide data security when healthcare data is being collected from individuals via IoT or IoMT devices. It’s also a key facilitator for large-scale healthcare data pooling from multiple sources for analytics without compromising privacy. Secure Multi-Party Computation (SMPC) facilitates safe data transfer between patients and healthcare professionals, and other relevant entities. Generative Adversarial Networks (GANs) can be used to generate larger data sets from smaller training data sets directly obtained from the patients, to train AI and ML algorithms. Differential Privacy (DP) focuses on combining multiple data sets for collective or individual processing without compromising privacy. However, its addition of noise to obscure data has some technical limitations. Zero-Knowledge Proof (ZKP) can facilitate safe verifications/validation protocols to establish connections between healthcare devices without straining their hardware capacities. Federated learning leans quite heavily towards training AI/ML algorithms on multiple data sets without margining or compromising the privacy of the constituents of any dataset. Obfuscation can be used in different stages of healthcare delivery to obscure healthcare data. </p>}, number={1}, journal={American Scientific Research Journal for Engineering, Technology, and Sciences}, author={Panchangam Nivarthi, Kiran Sharma}, year={2022}, month={Nov.}, pages={351–361} }