Digital Biomarkers of Cytokine Release Syndrome: Scoping Review and Ontology Development of the Role and Relevance of Digital Measures Using a Mixed Methods Approach

Background: Advancements in cancer-targeted immunotherapies have transformed care, yet these therapies present a high likelihood of cytokine release syndrome (CRS), a potentially severe immune-related adverse event. The ability to identify CRS earlier could improve care by mitigating risks, widening patient access and reducing the burden on patients, caregivers, and healthcare providers. Digital health technologies (DHTs) are promising for early CRS detection by enabling continuous measurement of vital signs before symptoms are detected through standard intermittent clinical assessments. While the number of studies is increasing, inconsistencies in the symptoms and measures strongly associated with CRS highlight the need for a comprehensive review to identify the most reliable and commonly reported indicators. Despite this growing body of research, reliable predictive and diagnostic measures for early warning for CRS following the administration of immunotherapy have yet to be established. Objective: This scoping review aims to address this gap by developing an ontology of early warning signs for CRS – a structured model defining measurement concepts, properties, and interrelationships – for advancing early warning models for CRS. Methods: We conducted a mixed methods study including a scoping literature review, surveys, and interviews. The literature review searched PubMed and Embase (last searched 03/19/2024) for articles reporting measures collected between therapy administration and CRS onset and linked to CRS onset. Studies were limited to publications between January 2014 and March 2024 excluding those that did not assess an immunotherapy-based treatment, were not conducted in humans, did not compare collected measures to CRS diagnosed using standard of care, or were not available in English. Identified measures were further assessed through surveys and interviews with subject matter experts (n=22) and key opinion leaders (n=8), and analyzed using qualitative and quantitative methods. Results: Thirty studies met eligibility criteria and employed a variety of grading scales and threshold for severe CRS. A comprehensive ontology of early warning signs for CRS that includes physiological signs, clinical symptoms, and laboratory markers was developed. Within the full ontology, a common set of early warning signs for CRS – temperature, heart rate, blood pressure, and oxygen saturation – was identified as the minimally necessary data to evaluate for their predictive value for CRS. Three of these four signs align with the American Society for Transplantation and Cellular Therapy criteria for CRS grading and other clinical grading scales for CRS. Conclusions: Standardization and adoption of the ontology of early warning signs for CRS will streamline data collection to support the creation of robust, fit-for-purpose datasets. This approach ensures practical and informative data collection, ultimately enhancing the ability to predict and manage CRS effectively. Developing predictive models based on these early warning signs can enhance CRS risk assessment, support decentralized trials, and improve access to cancer-targeted immunotherapies.