Applications of 0-1 Neural Networks in Prescription and Prediction
This addresses personalized healthcare decision-making by providing interpretable and effective treatment policies, though it is incremental as it builds on existing prescriptive modeling techniques.
The paper tackles the challenge of learning treatment policies in medical decision-making with limited data by introducing prescriptive networks (PNNs), shallow 0-1 neural networks trained with mixed integer programming, which outperform existing methods in synthetic data and a postpartum hypertension case study, reducing peak blood pressure by 5.47 mm Hg over clinical practice and 2 mm Hg over the next best technique.
A key challenge in medical decision making is learning treatment policies for patients with limited observational data. This challenge is particularly evident in personalized healthcare decision-making, where models need to take into account the intricate relationships between patient characteristics, treatment options, and health outcomes. To address this, we introduce prescriptive networks (PNNs), shallow 0-1 neural networks trained with mixed integer programming that can be used with counterfactual estimation to optimize policies in medium data settings. These models offer greater interpretability than deep neural networks and can encode more complex policies than common models such as decision trees. We show that PNNs can outperform existing methods in both synthetic data experiments and in a case study of assigning treatments for postpartum hypertension. In particular, PNNs are shown to produce policies that could reduce peak blood pressure by 5.47 mm Hg (p=0.02) over existing clinical practice, and by 2 mm Hg (p=0.01) over the next best prescriptive modeling technique. Moreover PNNs were more likely than all other models to correctly identify clinically significant features while existing models relied on potentially dangerous features such as patient insurance information and race that could lead to bias in treatment.