Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
This addresses a common healthcare problem of personalized health profiling, but it is incremental as it builds on existing probabilistic neural networks and structured prediction methods.
The paper tackled the problem of inferring arbitrary sets of variables from observed data and high-dimensional signals in healthcare, proposing composite bidirectional inference networks (CBIN) that achieved state-of-the-art performance and better accuracy in most tasks compared to task-specific models.
We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.