An Open-Source Tool for Automatic Disease Diagnosis..

Overview

OpenMedicalChatbox

An Open-Source Package for Automatic Disease Diagnosis.

Overview

Due to the lack of open source for existing RL-base automated diagnosis methods. It's hard to make a comparison for different methods. OpenMedicalChatbox integrates several current diagnostic methods and datasets.

Dataset

At here, we show all the mentioned datasets in existing medical methods, including MZ-4, Dxy, MZ-10 and a simulated dataset based on Symcat. In goal.set in their folders, explicit symptoms, implicit symptoms and diagnosis given by doctors are recorded for each sample. Also, we provide the corresponding tools to extend them for each methods.

Here is the overview of datasets.

Name # of user goal # of diseases Ave. # of im. sym # of sym.
MZ-4 1,733 4 5.46 230
MZ-10 3,745 10 5.28 318
Dxy 527 5 1.67 41
SymCat-SD-90 30,000 90 2.60 266

Methods

Besides, we reproduce several mainstream models for comparison. For further information, you can refer to the paper.

  1. Flat-DQN: This is the baseline DQN agent, which has one layer policy and an action space including both symptoms and diseases.
  2. HRL-pretrained: This is a hierarchical model. The low level policy is pre-trained first and then the high level policy is trained. Besides, there is no disease classifier and the diagnosis is made by workers.
  3. REFUEL: This is a reinforcement learning method with reward shaping and feature rebuilding. It uses a branch to reconstruct the symptom vector to guide the policy gradient.
  4. KR-DS: This is an improved method based on Flat-DQN. It integrates a relational refinement branch and a knowledge-routed graph to strengthen the relationship between disease and symptoms. Here we adjust the code from fantasySE.
  5. GAMP: This is a GAN-based policy gradient network. It uses the GAN network to avoid generating randomized trials of symptom, and add mutual information to encourage the model to select the most discriminative symptoms.
  6. HRL: This is a new hierarchical policy we purposed for diagnosis. The high level policy consists of a master model that is responsible for triggering a low level model, the low level policy consists of several symptom checkers and a disease classifier. Also, we try not to divide symptoms into different group (Denoted as HRL (w/o grouped)) to demonstrate the strength of two-level structure and remove the separate disease discriminator (Denoted as HRL (w/o discriminator)) to show the effect of disease grouping in symptom information extraction.

Installation

  1. Install the packages
pip install OpenMedicalChatBox

or Cloning this repo

git clone https://github.com/Guardianzc/OpenMedicalChatBox.git
cd OpenMedicalChatBox
python setup.py install

After installation, you can try running demo.py to check if OpenMedicalChatBox works well

python demo.py
  1. Redirect the parameter file0 to the dataset needed. Note that if you use the KR-DS model, please redirect to "dataset_dxy" folder, and HRL dataset use the "HRL" folder.
  2. Tune the parameter as you need.
  3. Run the file or use the code below

Examples

The following code shows how to use OpenMedicalChatBox to apply different diagnosis method on datasets.

import OpenMedicalChatBox as OMCB
from warnings import simplefilter
simplefilter(action='ignore', category=FutureWarning)

HRL_test = OMCB.HRL(dataset_path = '.\Data\mz4\HRL\\', model_save_path = './simulate', groups = 2, model_load_path = './simulate', cuda_idx = 1, train_mode = True)
HRL_test.run()

KRDS_test = OMCB.KRDS(dataset_path = '.\Data\mz4\dataset_dxy\\', model_save_path = './simulate', model_load_path = './simulate', cuda_idx = 1, train_mode = True)
KRDS_test.run()


Flat_DQN_test = OMCB.Flat_DQN(dataset_path = '.\Data\mz4\\', model_save_path = './simulate',  model_load_path = './simulate', cuda_idx = 1, train_mode = True)
Flat_DQN_test.run()


GAMP_test = OMCB.GAMP(dataset_path = '.\Data\mz4\\', model_save_path = './simulate', model_load_path = './simulate', cuda_idx = 1, train_mode = True)
GAMP_test.run()

REFUEL_test = OMCB.REFUEL(dataset_path = '.\Data\mz4\\', model_save_path = './simulate', model_load_path = './simulate', cuda_idx = 0, train_mode = True)
REFUEL_test.run()

The detail experimental parameters are shown in here.

Experiment

We show the accuracy for disease diagnosis (Acc.), recall for symptom recovery (M.R.) and the average turns in interaction (Avg. T).

  • In real world dataset
Dxy MZ-4 MZ-10
Model Acc. M.R. Avg.T Acc. M.R. Avg.T Acc. M.R. Avg.T
Flat-DQN 0.731 0.110 1.96 0.681 0.062 1.27 0.408 0.047 9.75
KR-DS 0.740 0.399 5.65 0.678 0.177 4.61 0.485 0.279 5.95
REFUEL 0.721 0.186 3.11 0.716 0.215 5.01 0.505 0.262 5.50
GAMP 0.731 0.268 2.84 0.644 0.107 2.93 0.500 0.067 1.78
Classifier Lower Bound 0.682 -- -- 0.671 -- -- 0.532 -- --
HRL (w/o grouped) 0.731 0.297 6.61 0.689 0.004 2.25 0.540 0.114 4.59
HRL (w/o discriminator) -- 0.512 8.42 -- 0.233 5.71 -- 0.330 8.75
HRL 0.779 0.424 8.61 0.735 0.229 5.08 0.556 0.295 6.99
Classifier Upper Bound 0.846 -- -- 0.755 -- -- 0.612 -- --
  • In synthetic dataset
Model Acc. M.R. Avg.T
Flat-DQN 0.343 0.023 1.23
KR-DS 0.357 0.388 6.24
REFUEL 0.347 0.161 4.56
GAMP 0.267 0.077 1.36
Classifier Lower Bound 0.308 -- --
HRL-pretrained 0.452 -- 3.42
HRL 0.504 0.495 6.48
Classifier Upper Bound 0.781 -- --

Reference

Citation

Please cite our paper if you use toolkit

@article{liao2020task,
  title={Task-oriented dialogue system for automatic disease diagnosis via hierarchical reinforcement learning},
  author={Liao, Kangenbei and Liu, Qianlong and Wei, Zhongyu and Peng, Baolin and Chen, Qin and Sun, Weijian and Huang, Xuanjing},
  journal={arXiv preprint arXiv:2004.14254},
  year={2020}
}
Owner
School of Data Science, Fudan University
Convert Apple NeuralHash model for CSAM Detection to ONNX.

Apple NeuralHash is a perceptual hashing method for images based on neural networks. It can tolerate image resize and compression.

Asuhariet Ygvar 1.5k Dec 31, 2022
CVPRW 2021: How to calibrate your event camera

E2Calib: How to Calibrate Your Event Camera This repository contains code that implements video reconstruction from event data for calibration as desc

Robotics and Perception Group 104 Nov 16, 2022
Make differentially private training of transformers easy for everyone

private-transformers This codebase facilitates fast experimentation of differentially private training of Hugging Face transformers. What is this? Why

Xuechen Li 73 Dec 28, 2022
NeRF visualization library under construction

NeRF visualization library using PlenOctrees, under construction pip install nerfvis Docs will be at: https://nerfvis.readthedocs.org import nerfvis s

Alex Yu 196 Jan 04, 2023
PyTorch implementation of spectral graph ConvNets, NIPS’16

Graph ConvNets in PyTorch October 15, 2017 Xavier Bresson http://www.ntu.edu.sg/home/xbresson https://github.com/xbresson https://twitter.com/xbresson

Xavier Bresson 287 Jan 04, 2023
This is an official implementation for "Self-Supervised Learning with Swin Transformers".

Self-Supervised Learning with Vision Transformers By Zhenda Xie*, Yutong Lin*, Zhuliang Yao, Zheng Zhang, Qi Dai, Yue Cao and Han Hu This repo is the

Swin Transformer 529 Jan 02, 2023
Inkscape extensions for figure resizing and editing

Academic-Inkscape: Extensions for figure resizing and editing This repository contains several Inkscape extensions designed for editing plots. Scale P

192 Dec 26, 2022
Pytorch Implementation of Interaction Networks for Learning about Objects, Relations and Physics

Interaction-Network-Pytorch Pytorch Implementraion of Interaction Networks for Learning about Objects, Relations and Physics. Interaction Network is a

117 Nov 05, 2022
QHack—the quantum machine learning hackathon

Official repo for QHack—the quantum machine learning hackathon

Xanadu 72 Dec 21, 2022
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

3k Jan 08, 2023
PyTorch implementation of "PatchGame: Learning to Signal Mid-level Patches in Referential Games" to appear in NeurIPS 2021

PatchGame: Learning to Signal Mid-level Patches in Referential Games This repository is the official implementation of the paper - "PatchGame: Learnin

Kamal Gupta 22 Mar 16, 2022
Image Recognition using Pytorch

PyTorch Project Template A simple and well designed structure is essential for any Deep Learning project, so after a lot practice and contributing in

Sarat Chinni 1 Nov 02, 2021
Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models

merged_depth runs (1) AdaBins, (2) DiverseDepth, (3) MiDaS, (4) SGDepth, and (5) Monodepth2, and calculates a weighted-average per-pixel absolute dept

Pranav 39 Nov 21, 2022
The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network.

UNet-SIDE The undersampled DWI image using Slice-Interleaved Diffusion Encoding (SIDE) method can be reconstructed by the UNet network. For Super Reso

TIANTIAN XU 1 Jan 13, 2022
SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis

SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis Pretrained Models In this work, we created synthetic tissue

Emirhan Kurtuluş 1 Feb 07, 2022
The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".

LEAR The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction". **The code is in the "master

杨攀 93 Jan 07, 2023
[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation

RCIL [CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation Chang-Bin Zhang1, Jia-Wen Xiao1, Xialei Liu1, Ying-Cong Chen2

Chang-Bin Zhang 71 Dec 28, 2022
WaveFake: A Data Set to Facilitate Audio DeepFake Detection

WaveFake: A Data Set to Facilitate Audio DeepFake Detection This is the code repository for our NeurIPS 2021 (Track on Datasets and Benchmarks) paper

Chair for Sys­tems Se­cu­ri­ty 27 Dec 22, 2022
The Pytorch implementation for "Video-Text Pre-training with Learned Regions"

Region_Learner The Pytorch implementation for "Video-Text Pre-training with Learned Regions" (arxiv) We are still cleaning up the code further and pre

Rui Yan 0 Mar 20, 2022
This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

Graphormer By Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng*, Guolin Ke, Di He*, Yanming Shen and Tie-Yan Liu. This repo is the official impl

Microsoft 1.3k Dec 26, 2022