A blockchain-based framework to support pharmacogenetic data sharing
F Albalwy et all, The PGX journal, July 22, 2022
The successful implementation of pharmacogenetics (PGx) into clinical practice requires patient genomic data to be shared between stakeholders in multiple settings. This creates a number of barriers to widespread adoption of PGx, including privacy concerns related to the storage and movement of identifiable genomic data. Informatic solutions that support secure and equitable data access for genomic data are therefore important to PGx. Here we propose a methodology that uses smart contracts implemented on a blockchain-based framework, PGxChain, to address this issue.
How better pandemic and epidemic intelligence will prepare the world for future threats.
Morgan Oliver W et al. Nature medicine 2022 6
A new approach to pandemic and epidemic intelligence is needed that includes modern approaches to surveillance and risk assessment, as well as improved trust and cooperation between stakeholders and society. Conducting effective pandemic and epidemic intelligence, however, is not straightforward. Gathering, managing, analyzing and interpreting disparate information from the health sector and beyond is complex, in part because of data fragmentation, difficulties with accessing sources on a continuous basis, licensing, ownership and security restrictions, privacy and re-identification risks, and the inherent complexity of working with a wide range of different data types and formats.
Smartphone apps in the COVID-19 pandemic
JA Pandit et al, Nature Biotechnology, June 20,2022
Smartphone apps, given accessibility in the time of physical distancing, were widely used for tracking, tracing and educating the public about COVID-19. Despite limitations, such as concerns around data privacy, data security, digital health illiteracy and structural inequities, there is ample evidence that apps are beneficial for understanding outbreak epidemiology, individual screening and contact tracing. While there were successes and failures in each category, outbreak epidemiology and individual screening were substantially enhanced by the reach of smartphone apps and accessory wearables.
Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening
J Yang et al, NPJ Digital Medicine, June 7, 2022
As patient health information is highly regulated due to privacy concerns, most machine learning (ML)-based healthcare studies are unable to test on external patient cohorts, resulting in a gap between locally reported model performance and cross-site generalizability. Different approaches have been introduced for developing models across multiple clinical sites, however less attention has been given to adopting ready-made models in new settings. We introduce three methods to do this—(1) applying a ready-made model “as-is” (2); readjusting the decision threshold on the model’s output using site-specific data and (3); finetuning the model using site-specific data via transfer learning.