Comment on “How pharmacoepidemiology networks can manage distributed analyses to improve replicability and transparency and minimize bias”

Schuemie, Martijn J.; Madigan, David; Ryan, Patrick B.; Reich, Christian; Suchard, Marc A.; Berlin, Jesse A.; Hripcsak, George

doi:10.1002/pds.4798

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further identify and reduce potential heterogeneity in coding practices between data partners, the Sentinel System is currently exploring the use of novel code translation methods, which incorporate unsupervised learning and language translation methods, to generate data-driven code mappings that could be used as a scalable and automated approach to help address idiosyncrasies in the coding process and harmonize medical codes across databases [ 84 , 85 ]. Such initiatives highlight the importance of preserving the original data values to the greatest extent possible when populating the CDM to maintain high fidelity and minimize information loss during the conversion process—a guiding principle of both the Sentinel and OMOP CDMs (the OMOP CDM both maps codes to a common vocabulary and retains the original source codes) [ 73 , 86 ].…”

Section: Challenges and Considerationsmentioning

confidence: 99%

Applying Machine Learning in Distributed Data Networks for Pharmacoepidemiologic and Pharmacovigilance Studies: Opportunities, Challenges, and Considerations

et al. 2022

View full text Add to dashboard Cite

Increasing availability of electronic health databases capturing real-world experiences with medical products has garnered much interest in their use for pharmacoepidemiologic and pharmacovigilance studies. The traditional practice of having numerous groups use single databases to accomplish similar tasks and address common questions about medical products can be made more efficient through well-coordinated multi-database studies, greatly facilitated through distributed data network (DDN) architectures. Access to larger amounts of electronic health data within DDNs has created a growing interest in using data-adaptive machine learning (ML) techniques that can automatically model complex associations in high-dimensional data with minimal human guidance. However, the siloed storage and diverse nature of the databases in DDNs create unique challenges for using ML. In this paper, we discuss opportunities, challenges, and considerations for applying ML in DDNs for pharmacoepidemiologic and pharmacovigilance studies. We first discuss major types of activities performed by DDNs and how ML may be used. Next, we discuss practical data-related factors influencing how DDNs work in practice. We then combine these discussions and jointly consider how opportunities for ML are affected by practical data-related factors for DDNs, leading to several challenges. We present different approaches for addressing these challenges and highlight efforts that real-world DDNs have taken or are currently taking to help mitigate them. Despite these challenges, the time is ripe for the emerging interest to use ML in DDNs, and the utility of these data-adaptive modeling techniques in pharmacoepidemiologic and pharmacovigilance studies will likely continue to increase in the coming years.

show abstract

Section: Challenges and Considerationsmentioning

confidence: 99%