• Corpus ID: 227247972

FIT: a Fast and Accurate Framework for Solving Medical Inquiring and Diagnosing Tasks

@article{He2020FITAF,
  title={FIT: a Fast and Accurate Framework for Solving Medical Inquiring and Diagnosing Tasks},
  author={Weijie He and Xiaohao Mao and Chao Ma and Jos{\'e} Miguel Hern{\'a}ndez-Lobato and Ting Chen},
  journal={ArXiv},
  year={2020},
  volume={abs/2012.01065}
}
Automatic self-diagnosis provides low-cost and accessible healthcare via an agent that queries the patient and makes predictions about possible diseases. From a machine learning perspective, symptom-based self-diagnosis can be viewed as a sequential feature selection and classification problem. Reinforcement learning methods have shown good performance in this task but often suffer from large search spaces and costly training. To address these problems, we propose a competitive framework… 

Figures and Tables from this paper

A Bayesian Approach for Medical Inquiry and Disease Inference in Automated Differential Diagnosis
TLDR
A Bayesian approach for both medical inquiry and disease inference, the two major phases in differential diagnosis, is proposed, which directly uses the Quick Medical Reference (QMR) belief network and applies Bayesian inference in the inference phase and Bayesian experimental design in the inquiry phase.
"My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics
TLDR
This paper proposes a more interpretable decision process to implement the dialogue manager of DSMD by reasonably mimicking real doctors' inquiry logics, and devise a model with highly transparent components to conduct the inference.

References

SHOWING 1-10 OF 28 REFERENCES
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
TLDR
In EDDI, a novel partial variational autoencoder to predict missing data entries problematically given any subset of the observed ones, and combine it with an acquisition function that maximizes expected information gain on a set of target variables is proposed.
REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis
TLDR
REFUEL, a reinforcement learning method with two techniques: reward shaping and feature rebuilding, is proposed to improve the performance of online symptom checking for disease diagnosis.
Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis
TLDR
A new policy gradient framework based on the Generative Adversarial Network (GAN) to optimize the RL model for automatic diagnosis and beats the state-of-art methods, not only can achieve higher diagnosis accuracy, but also can use a smaller number of inquires to make diagnosis decision.
Context-Aware Symptom Checking for Disease Diagnosis Using Hierarchical Reinforcement Learning
TLDR
This paper presents a context-aware hierarchical reinforcement learning scheme, which significantly improves accuracy of symptom checking over traditional systems while also making a limited number of inquiries.
Machine learning for medical diagnosis: history, state of the art and perspective
Inquire and Diagnose : Neural Symptom Checking Ensemble using Deep Reinforcement Learning
TLDR
This work proposes a novel symptom checker: an ensemble neural network model that learns to inquire symptoms and diagnose diseases that obtains markedly higher disease-prediction accuracy.
Classification with Costly Features using Deep Reinforcement Learning
TLDR
This work uses vanilla Double Deep Q-learning, a standard reinforcement learning technique, to find a classification policy and shows that this generic approach outperforms Adapt-Gbrt, currently the best-performing algorithm developed specifically for classification with costly features.
Feature-Budgeted Random Forest
TLDR
A novel random forest algorithm to minimize prediction error for a user-specified feature acquisition budget and demonstrate superior accuracy-cost curves against state-of-the-art prediction-time algorithms.
Inductive and Bayesian learning in medical diagnosis
  • I. Kononenko
  • Computer Science, Medicine
    Appl. Artif. Intell.
  • 1993
TLDR
Surprisingly, the naive Bayesian classifier is superior to Assistant in classification accuracy and explanation ability, while the interpretation of the acquired knowledge seems to be equally valuable.
Auto-Encoding Variational Bayes
TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
...
...