Machine-learning-based high-benefit approach versus conventional high-risk approach in blood pressure management

Abstract Background In medicine, clinicians treat individuals under an implicit assumption that high-risk patients would benefit most from the treatment (‘high-risk approach’). However, treating individuals with the highest estimated benefit using a novel machine-learning method (‘high-benefit approach’) may improve population health outcomes. Methods This study included 10 672 participants who were randomized to systolic blood pressure (SBP) target of either <120 mmHg (intensive treatment) or <140 mmHg (standard treatment) from two randomized controlled trials (Systolic Blood Pressure Intervention Trial, and Action to Control Cardiovascular Risk in Diabetes Blood Pressure). We applied the machine-learning causal forest to develop a prediction model of individualized treatment effect (ITE) of intensive SBP control on the reduction in cardiovascular outcomes at 3 years. We then compared the performance of high-benefit approach (treating individuals with ITE >0) versus the high-risk approach (treating individuals with SBP ≥130 mmHg). Using transportability formula, we also estimated the effect of these approaches among 14 575 US adults from National Health and Nutrition Examination Surveys (NHANES) 1999–2018. Results We found that 78.9% of individuals with SBP ≥130 mmHg benefited from the intensive SBP control. The high-benefit approach outperformed the high-risk approach [average treatment effect (95% CI), +9.36 (8.33–10.44) vs +1.65 (0.36–2.84) percentage point; difference between these two approaches, +7.71 (6.79–8.67) percentage points, P-value <0.001]. The results were consistent when we transported the results to the NHANES data. Conclusions The machine-learning-based high-benefit approach outperformed the high-risk approach with a larger treatment effect. These findings indicate that the high-benefit approach has the potential to maximize the effectiveness of treatment rather than the conventional high-risk approach, which needs to be validated in future research.