Cancer nursing research and practice have been at the forefront of the precision oncology movement due to the early application of the precision medicine framework resulting in targeted therapies based on somatic mutations or other genomic or molecular features of the diagnosis.1 The evolution of the precision medicine framework then extended beyond solely omics-based data and targeted therapies to a broader precision health concept, including personalized clinical pathways2 and precision survivorship based on emerging late effects of therapy.3 These applications expanded the understanding of precision health to include population-based implementation and recognition of the potential exacerbation of health disparities and emerging ethical considerations.4, 5, 6, 7, 8

The development and application of precision oncology and personalized modeling perspectives rely on large amounts of data (“big data”) and emerging data science principles. The optimal development of precision health or personalized pathways for patients can only be achieved by aggregating large amounts of data from multiple sources from the patient (including omics, image data, clinical data often derived from the electronic medical record, health care utilization data, treatment/medication data, and behavioral, social, and environmental data) along with evidence generated from clinical trials data and causal pathways gleaned from large, representative, and well-annotated observational or real-world data.9 There are numerous challenges associated with combining large and diverse data entities, including issues of harmonization, privacy considerations, costs of data storage, etc.4,10,11 Simultaneously, there are barriers associated with updating these frameworks with new knowledge (eg, updated treatment recommendations following a novel clinical trial or update in clinical guidelines) or updating algorithms themselves following real-world calibration.

In an attempt to be flexible and incorporate data in real-time, analytic ecosystems offer a framework that nursing science can build from and apply known evidence or best practices to personal data trajectories.12 The term analytic ecosystem is an extension of a data ecosystem where data science capacity is developed through harmonization of data that are findable, accessible, interoperable, reusable (FAIR).12, 13, 14, 15, 16 Analytic ecosystems offer the potential for a usable data commons with strong data governance and standards to streamline sharing of data but also sharing of the analytic code along with the development of reusable data tools and protocols. Central to this proposed framework is the notion of a learning health system or a conceptual approach to capturing data from clinical encounters or health events, analyze the data to generate new knowledge, then apply this new knowledge to inform clinical practice in a manner that evokes continuous learning and feedback loops.17,18 A learning health system is viewed as a cyclical process and when combined with analytic ecosystems implies an active participatory process to the FAIR cultivation and direct application of diverse data streams.

Cancer nurses work with patients who receive care in various venues (outpatient settings, acute and intensive care hospital settings including the emergency department, acute care ward, intensive care unit, and home and community-based care). Further, they must anticipate care needs across the trajectory of their patients’ cancer experience, from prevention to diagnosis, treatment, survivorship, and end-of-life care. While the core edict of precision oncology involves personalized approaches to the right care at the right time this concept must be extended to provide anticipatory guidance and support for managing specific toxicities, late effects of treatment, and symptom clusters.19 There is much use for the intersection of data science and precision oncology nursing in creating and implementing analytic ecosystems for optimal patient outcomes. The authors aim to highlight a precision oncology nursing analytic ecosystem framework that can be used and implemented across the cancer continuum to improve quality practices and offer enhanced anticipatory guidance in the era of precision health. A case exemplar will be used to introduce the key concepts and highlight current barriers to data integration and why analytic ecosystems embedded within learning health systems are needed to revolutionize precision oncology nursing care delivery.