It is increasingly clear that high-need, high-cost patients are not a homogenous group, but rather a diverse set of patients with varied circumstances and needs. Acting on this insight requires comprehensive data networks we have not traditionally had, and most analyses to date have focused primarily on claims data. We argue that making clinical and financial gains will require data-sharing networks that integrate clinical factors, genomic information, and social determinants from multiple health systems. Investing in these networks may allow us to better anticipate the unique needs of patients, conceptualize care models to meet those needs, and put targeted interventions into action.