Ward2ICU: A Vital Signs Dataset of Inpatients from the General Ward (2019-10-02T00:00:00.000000Z)

TL;DR

A proxy dataset of vital signs with class labels indicating patient transitions from the ward to intensive care units called Ward2ICU is presented, and a solution for a special case through class label balancing is proposed.

Abstract

We present a proxy dataset of vital signs with class labels indicating patient transitions from the ward to intensive care units called Ward2ICU. Patient privacy is protected using a Wasserstein Generative Adversarial Network to implicitly learn an approximation of the data distribution, allowing us to sample synthetic data. The quality of data generation is assessed directly on the binary classification task by comparing specificity and sensitivity of an LSTM classifier on proxy and original datasets. We initialize a discussion of unintentionally disclosing commercial sensitive information and propose a solution for a special case through class label balancing

Authors

Daniel de Souza Severo

2 papers

Fl'avio Amaro

1 papers

Estevam Hruschka

2 papers

TL;DR

Abstract

Authors

References39 items

Generative Adversarial Networks

TorchGAN: A Flexible Framework for GAN Training and Evaluation

Biosignal Generation and Latent Variable Analysis With Recurrent Generative Adversarial Networks

Synthesizing electronic health records using improved generative adversarial networks

Generation of Synthetic Electronic Medical Record Text

The eICU Collaborative Research Database, a freely available multi-center database for critical care research

Augmenting The Size of EEG datasets Using Generative Adversarial Networks

EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals

Enabling Open-Science Initiatives in Clinical Psychology and Psychiatry Without Sacrificing Patients’ Privacy: Current Practices and Future Challenges

Automatic differentiation in PyTorch

Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record

Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing

Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs

Improved Training of Wasserstein GANs

Generating Multi-label Discrete Patient Records using Generative Adversarial Networks

Wasserstein GAN

Medical Image Synthesis with Context-Aware Generative Adversarial Networks

Least Squares Generative Adversarial Networks

MIMIC-III, a freely accessible critical care database

Who Owns the Data? Open Data for Healthcare

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Empirical Evaluation of Rectified Activations in Convolutional Network

How transferable are features in deep neural networks?

Conditional Generative Adversarial Nets

The Balanced Accuracy and Its Posterior Distribution

Ganong’s Review of Medical Physiology – 23rd edition Kim E Barratt Ganong’s Review of Medical Physiology – 23rd editionet al |McGraw Hill Medical|726pp|£41.99978 0 07160567 00071605673

ImageNet: A large-scale hierarchical image database

Hypothermia therapy after traumatic brain injury in children.

Calibrating Noise to Sensitivity in Private Data Analysis

The Importance of Biological Databases in Biological Discovery

Learning to Forget: Continual Prediction with LSTM

Delmar's Comprehensive Medical Assisting: Administrative and Clinical Competencies

Dropout: a simple way to prevent neural networks from overfitting

GNU Parallel: The Command-Line Power Tool

Ganong's Review of Medical Physiology

Book Reviews: WordNet: An Electronic Lexical Database

Gradient-based learning applied to document recognition

Divergence measures based on the Shannon entropy

Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude”. In: COURSERA: Neural networks for machine learning

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names