The Library
Data for A method for machine learning generation of realistic synthetic datasets for validating healthcare applications
Tools
Tools
Tools
Arvanitis, Theodoros N., White, Sean, Harrison, Stuart, Chaplin, Rupert and Despotou, George (2022) Data for A method for machine learning generation of realistic synthetic datasets for validating healthcare applications. [Dataset]
![[img]](http://wrap.warwick.ac.uk/style/images/fileicons/application_msword.png) |
Microsoft Word (Readme file)
README.rtf - Published Version Embargoed item. Restricted access to Repository staff only Download (718b) |
![[img]](http://wrap.warwick.ac.uk/style/images/fileicons/application_zip.png) |
Archive (ZIP) (Dataset)
RSDGM Experiments.zip - Published Version Embargoed item. Restricted access to Repository staff only Download (9Mb) |
Official URL: http://wrap.warwick.ac.uk/162871/
Abstract
Background Digital health applications can improve quality and effectiveness of healthcare, by offering a number of tools to patients, professionals, and the healthcare system. Introduction of new technologies is not without risk, and digital health applications are often considered a medical device. Assuring their safe operation requires, amongst others, clinical validation, which needs large datasets to test their application in realistic clinical scenarios. Access to such datasets is challenging, due to concerns about patient privacy. Development of synthetic datasets, which will be sufficiently realistic to test digital applications, is seen as a potential alternative, enabling their deployment.
Objective The aim of work was to develop a method for the generation of realistic synthetic datasets, statistically equivalent to real clinical datasets, and demonstrate that Generative Adversarial Network based approach is fit for purpose.
Method A generative adversarial network was implemented and trained, in a series of six experiments, using numerical and categorical variables from three clinically relevant datasets, including ICD-9 and laboratory codes from the MIMIC III dataset. A number of contextual steps provided the success criteria for the synthetic dataset.
Results The approach created a synthetic dataset that exhibits very similar statistical characteristics with the real dataset. Pairwise association of variables is very similar. A high degree of Jaccard similarity and a successful K-S test further support this.
Conclusions The proof of concept of generating realistic synthetic datasets was successful, with the approach showing promise for further work.
| Item Type: | Dataset | ||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software R Medicine > R Medicine (General) |
||||||||||||||||||||||||||||||
| Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||||||||||||||||||||||||||
| Type of Data: | Synthetically generated data based on the experiments | ||||||||||||||||||||||||||||||
| Library of Congress Subject Headings (LCSH): | Neural networks (Computer science), Machine learning, Medical Informatics, Medicine -- Data processing | ||||||||||||||||||||||||||||||
| Publisher: | University of Warwick, Warwick Manufacturing Group | ||||||||||||||||||||||||||||||
| Official Date: | 25 February 2022 | ||||||||||||||||||||||||||||||
| Dates: |
|
||||||||||||||||||||||||||||||
| Status: | Not Peer Reviewed | ||||||||||||||||||||||||||||||
| Publication Status: | Published | ||||||||||||||||||||||||||||||
| Media of Output (format): | .log | ||||||||||||||||||||||||||||||
| Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||||||||||||||
| Copyright Holders: | University of Warwick, NHS Digital | ||||||||||||||||||||||||||||||
| Description: | The dataset contains the synthetic data produced in experiments 3-6, as described in: A Method for Machine Learning Generation of Realistic Synthetic Datasets for Validating Healthcare Applications (DOI: 10.1177/14604582221077000/) in Health Informatics Journal, SAGE. |
||||||||||||||||||||||||||||||
| Date of first compliant deposit: | 15 February 2022 | ||||||||||||||||||||||||||||||
| RIOXX Funder/Project Grant: |
|
||||||||||||||||||||||||||||||
| Related URLs: | |||||||||||||||||||||||||||||||
| Contributors: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
 |
View Item |
