The simultaneous application of multiple treatments is increasingly common in many fields, such as healthcare and marketing. In such scenarios, it is important to estimate the single treatment effects and the interaction treatment effects that arise from treatment combinations. Previous studies have proposed using independent outcome networks with subnetworks for interactions, or combining task embedding networks that capture treatment similarity with variational autoencoders. However, these methods suffer from the lack of parameter sharing among related treatments, or the estimation of unnecessary latent variables reduces the accuracy of causal effect estimation. To address these issues, we propose a novel deep learning framework that incorporates a task embedding network and a representation learning network with the balancing penalty. The task embedding network enables parameter sharing across related treatment patterns because it encodes elements common to single effects and contributions specific to interaction effects. The representation learning network with the balancing penalty learns representations nonparametrically from observed covariates while reducing distances in representation distributions across different treatment patterns. This process mitigates selection bias and avoids model misspecification. Simulation studies demonstrate that the proposed method outperforms existing baselines, and application to real-world marketing datasets confirms the practical implications and utility of our framework.

Machine learning algorithms successfully predicted visual and anatomic outcomes and dosing frequency in patients with macular edema secondary to …

For this smaller group of patients, physicians may have limited clinical decision-making experience or evidence-based guidance for choosing drug combinations. The solution is to expand the number of patients to support development of general principles to guide decision-making. Combining patient data from multiple healthcare institutions, however, requires deep expertise in artificial intelligence (AI) and wide-ranging experience in developing machine learning models using sensitive and complex healthcare data. Hitachi, U of U Health, and Regenstrief researchers partnered to develop and test a new AI method that analyzed electronic health record data across Utah and Indiana and learned generalizable treatment patterns of type 2 diabetes patients with similar characteristics. Those patterns can now be used to help determine an optimal drug regimen for a specific patient.

Appropriate treatment regimens play a vital role in improving patient health status. Although some achievements have been made, few of the recent studies of learning treatment regimens have exploited different kinds of patient information due to the difficulty in adopting heterogeneous data to many data mining methods. Moreover, current studies seem too rigid with fixed intervals of treatment periods corresponding to the varying lengths of hospital stay. To this end, this work proposes a generic data-driven framework which can derive group-treatment regimens from electronic medical records by utilizing a mixed-variate restricted Boltzmann machine and incorporating medical domain knowledge. We conducted experiments on coronary artery disease as a case study. The obtained results show that the framework is promising and capable of assisting physicians in making clinical decisions.