# A Bayesian Approach for Medical Inquiry and Disease Inference in Automated Differential Diagnosis

arXiv: https://arxiv.org/abs/2110.08393 · HTML: https://mlsanity.com/paper/2110.08393/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 27 references that are in the map.
- First posted on arXiv 15 Oct 2021.

## Builds on (most cited first, 2 of 2)

- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis](https://mlsanity.com/paper/1901.10623/) (2019)

## Built on by (most cited first, 5 of 5)

- [DDXPlus: A New Dataset For Automatic Medical Diagnosis](https://mlsanity.com/paper/2205.09148/) (2022)
- [MDDial: A Multi-turn Differential Diagnosis Dialogue Dataset with Reliability Evaluation](https://mlsanity.com/paper/2308.08147/) (2023)
- [Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learning](https://mlsanity.com/paper/2210.07198/) (2022)
- [NeuralSympCheck: A Symptom Checking and Disease Diagnostic Neural Model with Logic Regularization](https://mlsanity.com/paper/2206.00906/) (2022)
- [COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion](https://mlsanity.com/paper/2605.15016/) (2026)

## Abstract (arXiv)

We propose a Bayesian approach for both medical inquiry and disease inference, the two major phases in differential diagnosis. Unlike previous work that simulates data from given probabilities and uses ML algorithms on them, we directly use the Quick Medical Reference (QMR) belief network, and apply Bayesian inference in the inference phase and Bayesian experimental design in the inquiry phase. Moreover, we improve the inquiry phase by extending the Bayesian experimental design framework from one-step search to multi-step search. Our approach has some practical advantages as it is interpretable, free of costly training, and able to adapt to new changes without any additional effort. Our experiments show that our approach achieves new state-of-the-art results on two simulated datasets, SymCAT and HPO, and competitive results on two diagnosis dialogue datasets, Muzhi and Dxy.