Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Development of a machine learning algorithm for generating realistic synthetic electronic healthcare records (Prosate and Breast)

Principal Investigator
Name
Andreas Maier
Degrees
Ph.D.
Institution
FAU Erlangen Nürnberg
Position Title
Professor, Head of the Pattern Recognition Lab
Email
About this CDAS Project
Study
PLCO (Learn more about this study)
Project ID
PLCO-570
Initial CDAS Request Approval
Jan 27, 2020
Title
Development of a machine learning algorithm for generating realistic synthetic electronic healthcare records (Prosate and Breast)
Summary
Machine learning brings new opportunities to the healthcare industries: it can improve the sensitivity of detection of diseases, add more value to treatment decisions and help to personalize the treatment. However, to be able to utilize machine learning sufficient amount of patient data is required. Still, due to many legal, privacy and security regulations, real persons' data is mostly not accessible to researchers.
In the project PLCO-529, the algorithm for the creating of the realistic Lung Cancer Patients is created. Unfortunately, not all the time the sufficient amount of data about the specific cancer is available. The goal of this project is to validate whenever the algorithm created in PLCO-529 can be used to create realistic healthcare records, for patients with other types of cancer (for example for Prostate and Breast cancer). This project also aims to validate whenever it is possible to use a combination of the data (for example Lung and Prostate) to create realistic healthcare records if not enough patient data is available.
Aims

- Implement an algorithm to gather causal dependencies between patient characteristics, diagnostic & therapeutic procedures, and patient outcomes (complications, survival)
- Validation of the patient generator against real patient population from available data
- Integration of domain transfer between Lung- Prostate - Breast cancer

Collaborators

Daniel Stromer FAU Erlangen Nürnberg daniel.stromer@fau.de
Oliver Haas FAU Erlangen Nürnberg oliver.haas@fau.de