Rethinking the Approach to Artificial Intelligence for Medical Image Analysis: The Case for Precision Diagnosis.

Abstract

To date, widely generalizable artificial intelligence (AI) programs for medical image analysis have not been demonstrated, including for mammography. Rather than pursuing a strategy of collecting ever-larger databases in the attempt to build generalizable programs, we suggest three possible avenues for exploring a precision medicine or precision imaging approach. First, it is now technologically feasible to collect hundreds of thousands of multi-institutional cases along with other patient data, allowing stratification of patients into subpopulations that have similar characteristics in the manner discussed by the National Research Council in its white paper on precision medicine. A family of AI programs could be developed across different examination types that are matched to specific patient subpopulations. Such stratification can help address bias, including racial or ethnic bias, by allowing unbiased data aggregation for creation of subpopulations. Second, for common examinations, larger institutions may be able to collect enough of their own data to train AI programs that reflect disease prevalence and variety in their respective unique patient subpopulations. Third, high- and low-probability subpopulations can be identified by application of AI programs, thereby allowing their triage off the radiology work list. This would reduce radiologists' workloads, providing more time for interpretation of the remaining examinations. For high-volume procedures, investigators should come together to define reference standards, collect data, and compare the merits of pursuing generalizability versus a precision medicine subpopulation-based strategy.