A Model-Based Reinforcement Learning Approach for a Rare Disease Diagnostic Task
This work addresses the challenge of rare disease diagnosis for medical professionals, offering a tool that integrates expert knowledge with data, but it is incremental as it adapts existing reinforcement learning methods to a specific domain.
The paper tackles the problem of diagnosing rare diseases by developing a decision support tool that aims to reduce diagnostic uncertainty below a threshold while minimizing the average number of medical tests, incorporating expert knowledge and ontological information to handle data scarcity and varying precision in symptom descriptions.
In this work, we present our various contributions to the objective of building a decision support tool for the diagnosis of rare diseases. Our goal is to achieve a state of knowledge where the uncertainty about the patient's disease is below a predetermined threshold. We aim to reach such states while minimizing the average number of medical tests to perform. In doing so, we take into account the need, in many medical applications, to avoid, as much as possible, any misdiagnosis. To solve this optimization task, we investigate several reinforcement learning algorithm and make them operable in our high-dimensional and sparse-reward setting. We also present a way to combine expert knowledge, expressed as conditional probabilities, with real clinical data. This is crucial because the scarcity of data in the field of rare diseases prevents any approach based solely on clinical data. Finally we show that it is possible to integrate the ontological information about symptoms while remaining in our probabilistic reasoning. It enables our decision support tool to process information given at different level of precision by the user.