IMPORTANCEThere is an enormous and growing amount of data available from individual cancer cases, which makes the work of clinical oncologists more demanding. This data challenge has attracted engineers to create software that aims to improve cancer diagnosis or treatment. However, the move to use computers in the oncology clinic for diagnosis or treatment has led to instances of premature or inappropriate use of computational predictive systems.OBJECTIVE To evaluate best practices for developing and assessing the clinical utility of predictive computational methods in oncology.
EVIDENCE REVIEWThe National Cancer Policy Forum and the Board on Mathematical Sciences and Analytics at the National Academies of Sciences, Engineering, and Medicine hosted a workshop to examine the use of multidimensional data derived from patients with cancer and the computational methods used to analyze these data. The workshop convened diverse stakeholders and experts, including computer scientists, oncology clinicians, statisticians, patient advocates, industry leaders, ethicists, leaders of health systems (academic and community based), private and public health insurance carriers, federal agencies, and regulatory authorities. Key characteristics for successful computational oncology were considered in 3 thematic areas: (1) data quality, completeness, sharing, and privacy;(2) computational methods for analysis, interpretation, and use of oncology data; and(3) clinical infrastructure and expertise for best use of computational precision oncology.FINDINGS Quality control was found to be essential across all stages, from data collection to data processing, management, and use. Collecting a standardized parsimonious data set at every cancer diagnosis and restaging could enhance reliability and completeness of clinical data for precision oncology. Data completeness refers to key data elements such as information about cancer diagnosis, treatment, and outcomes, while data quality depends on whether appropriate variables have been measured in valid and reliable ways. Collecting data from diverse populations can reduce the risk of creating invalid and biased algorithms. Computational systems that aid clinicians should be classified as software as a medical device and thus regulated according to the potential risk posed. To facilitate appropriate use of computational methods that interpret high-dimensional data in oncology, treating physicians need access to multidisciplinary teams with broad expertise and deep training among a subset of clinical oncology fellows in clinical informatics.CONCLUSIONS AND RELEVANCE Workshop discussions suggested best practices in demonstrating the clinical utility of predictive computational methods for diagnosing or treating cancer.