Best practices in the real-world data life cycle

Abstract

With increasing digitization of healthcare, real-world data (RWD) are available in greater quantity and scope than ever before. Since the 2016 United States 21st Century Cures Act, innovations in the RWD life cycle have taken tremendous strides forward, largely driven by demand for regulatory-grade real-world evidence from the biopharmaceutical sector. However, use cases for RWD continue to grow in number, moving beyond drug development, to population health and direct clinical applications pertinent to payors, providers, and health systems. Effective RWD utilization requires disparate data sources to be turned into high-quality datasets. To harness the potential of RWD for emerging use cases, providers and organizations must accelerate life cycle improvements that support this process. We build on examples obtained from the academic literature and author experience of data curation practices across a diverse range of sectors to describe a standardized RWD life cycle containing key steps in production of useful data for analysis and insights. We delineate best practices that will add value to current data pipelines. Seven themes are highlighted that ensure sustainability and scalability for RWD life cycles: data standards adherence, tailored quality assurance, data entry incentivization, deploying natural language processing, data platform solutions, RWD governance, and ensuring equity and representation in data.

Hospital-wide Natural Language Processing summarising the health data of 1 million patients

“…It also opens the door towards analyses of ‘similar patients’ for purposes of virtual trials of multimorbidity. The advent of reliable and scalable NLP methods integrated within the healthcare data lifecycle 31 brings much more expressive clinical data into a research-ready state and enables all downstream data-dependent activity including population health, business intelligence, and epidemiological and clinical research on real-world data.…”

Moving towards vertically integrated artificial intelligence development

“…A healthcare data lifecycle describes generation, curation and aggregation, and maintenance of patient data that is used by consumers (such as clinicians and researchers) and patients themselves 37 . Practical examples can be seen in Learning Healthcare Systems, where analysis is built into daily practice 38 .…”

Can Real-World Evidence Help Restore Decades of Health Inequalities by Informing Health Care Decision-Making? Certainly, and Here is How

“…As previously noted, it is without doubt encouraging that, recently, HTA bodies have started recognising that health inequalities should no longer be ignored in decision-making for new technologies; in the UK, NICE encouraged further research on how health inequalities can be quantitatively accounted for (as another type of decision-modifier) in the clinical and cost-effectiveness assessment of new technologies. Moreover, RWE collection need also to prioritise diversity to reduce bias and maintain equity in patient representation; for example, previous studies have shown that increase in data from medical wearables only increase the gap between those with and without access to interconnected devices ( Zhang et al, 2022 ; Scientific Reports, 2022 ). It is also encouraging that, FDA has just drafted detailed guidance to improve clinical trial diversity by explicitly requesting manufacturers to demonstrate that measures have been taken to enhance diversity in clinical trials ( FDA, 2022 ).…”