OBJECTIVES: To estimate the impact on lifetime health and economic outcomes of different methods of stratifying individuals with type 2 diabetes, followed by guideline-based treatment intensification, targeting BMI and LDL in addition to HbA1c.

METHODS: We divided 90,374 newly diagnosed individuals from the Clinical Practice Research Datalink (CPRD) into three data-driven clustering subgroups (based on unsupervised learning for age at diagnosis, BMI, HbA1c, and metabolic score for insulin resistance), as well as four risk-driven subgroups (based on fixed cut-offs for HbA1c and the risk of cardiovascular disease according to guidelines). The UKPDS Outcomes Model 2 estimated discounted expected lifetime complication costs and quality-adjusted life-years (QALYs) for each subgroup and across all individuals. Gains from treatment intensification were compared to “care-as-usual” as observed in CPRD. To alleviate the computational load of the simulations, a random sample of 2,000 individuals was selected.

RESULTS: Under care-as-usual, prognosis in the HTx data-driven subgroups ranged from 9.78 to 12.31 QALYs. Prognosis in the risk-driven subgroups ranged from 6.43 to 12.74 QALYs. Compared to homogenous type 2 diabetes, treatment for individuals in high-risk subgroups could cost up to 22% and 62% more and still be cost-effective for data-driven and risk-driven subgroups respectively. Targeting BMI and LDL in addition to HbA1c might deliver up to more than ten-fold increases in QALYs gained.

CONCLUSIONS: Risk-driven subgroups better discriminated regarding prognosis. Both stratification methods supported stratified treatment intensification, with the risk-driven subgroups being better in identifying individuals with the most potential to benefit from intensive treatment. Irrespective of stratification approach, better cholesterol and weight control showed substantial potential for health gains.