Treffer: PyDPLib : Python Differential Privacy Library for Private Medical Data Analytics

Title:
PyDPLib : Python Differential Privacy Library for Private Medical Data Analytics
Authors:
Imtiaz, Sana, Matthies, Philipp, Pinto, Francisco, Maros, Mate, Wenz, Holger, Sadre, Ramin, Vlassov, Vladimir
Publisher Information:
KTH, Programvaruteknik och datorsystem, SCS Universit ́e catholique de Louvain, Louvain-la-Neuve, Belgium Smart Reporting GmbH, Munich, Germany Smart Reporting GmbH, Munich, Germany Heidelberg University, Medical Faculty Mannheim, Mannheim, Germany Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany Universit ́e catholique de Louvain, Louvain-la-Neuve, Belgium Institute of Electrical and Electronics Engineers (IEEE) 2021
Document Type:
E-Ressource Electronic Resource
Index Terms:
Differential privacy, electronic data capture, private visual statistics, prostate cancer dataset, python library, Big data, Biomedical engineering, Data Analytics, Data privacy, Data visualization, Digital libraries, High level languages, Urology, Differential privacies, Electronic data, Medical data, Medical technologies, Pharmaceutical technologies, Private visual statistic, Diseases, Atom and Molecular Physics and Optics, Atom- och molekylfysik och optik, Conference paper, info:eu-repo/semantics/conferenceObject, text
DOI:
10.1109.ICDH52753.2021.00034
URL:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-313269
Availability:
Open access content. Open access content
info:eu-repo/semantics/restrictedAccess
Note:
English
Other Numbers:
UPE oai:DiVA.org:kth-313269
0000-0002-4088-8070
0000-0002-6779-7435
doi:10.1109/ICDH52753.2021.00034
ISI:000852642500023
Scopus 2-s2.0-85119518818
1372251508
Contributing Source:
UPPSALA UNIV LIBR
From OAIster®, provided by the OCLC Cooperative.
Accession Number:
edsoai.on1372251508
Database:
OAIster

Weitere Informationen

Pharmaceutical and medical technology companies accessing real-world medical data are not interested in personally identifiable data but rather in cohort data such as statistical aggregates, patterns, and trends. These companies cooperate with medical institutions that collect medical data and want to share it but they need to protect the privacy of individuals on the shared data. We present PyDPLib, a Python Differential Privacy library for private medical data analytics. We illustrate an application of differential privacy using PyDPLib in our platform for visualizing private statistics on a database of prostate cancer patients. Our experimental results show that PyDPLib allows creating statistical data plots without compromising patients' privacy while preserving underlying data distributions. Even though PyDPLib has been developed to be used in our platform for reporting the radiological examinations and procedures, it is general enough to be used to provide differential privacy on data in any data analytics and visualization platform, service or application.
Part of proceeings: ISBN 978-1-6654-1685-6QC 20220603