RESUMO
Causal effect estimation of individual heterogeneity is a core issue in the field of causal inference, and its application in medicine poses an active and challenging problem. In high-risk decision-making domain such as healthcare, inappropriate treatments can have serious negative impacts on patients. Recently, machine learning-based methods have been proposed to improve the accuracy of causal effect estimation results. However, many of these methods concentrate on estimating causal effects of continuous outcome variables under binary intervention conditions, and give less consideration to multivariate intervention conditions or discrete outcome variables, thus limiting their scope of application. To tackle this issue, we combine the double machine learning framework with Light Gradient Boosting Machine (LightGBM) and propose a double LightGBM model. This model can estimate binary causal effects more accurately and in less time. Two cyclic structures were added to the model. Data correction method was introduced and improved to transform discrete outcome variables into continuous outcome variables. Multivariate Cyclic Double LightGBM model (MCD-LightGBM) was proposed to intelligently estimate multivariate treatment effects. A visual human-computer interaction system for heterogeneous causal effect estimation was designed, which can be applied to different types of data. This paper reports that the system improved the Logarithm of the Minimum Angle of Resolution (LogMAR) of visual acuity change after Vascular Endothelial Growth Factor (anti-VEGF) treatment in patients with diabetic macular degeneration. The improvement was observed in two clinical problems, from 0.05 to 0.33, and the readmission rate of diabetic patients after cure was reduced from 48.4% to 10.5%. The results above demonstrate the potential of the proposed system in predicting heterogeneous clinical drug treatment effects.