Preliminary data analysis in healthcare multicentric data mining: A privacy-preserving distributed approach

Andrea Damiani, Carlotta Masciocchi, Luca Boldrini, Roberto Gatta, Nicola Dinapoli, Jacopo Lenkowicz, Giuditta Chiloiro, Maria Antonietta Gambacorta, Luca Tagliaferri, Rosa Autorino, Monica Maria Pagliara, Maria Antonietta Blasi, Johan Van Soest, Andre Dekker, Vincenzo Valentini

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The new era of cognitive health care systems offers a large amount of patient data that can be used to develop prediction models and clinical decision support systems. In this frame, the multi-institutional approach is strongly encouraged in order to reach more numerous samples for data mining and more reliable statistics. For these purposes, shared ontologies need to be developed for data management to ensure database semantic coherence in accordance with the various centers’ ethical and legal policies. Therefore, we propose a privacy-preserving distributed approach as a preliminary data analysis tool to identify possible compliance issues and heterogeneity from the agreed multi-institutional research protocol before training a clinical prediction model. This kind of preliminary analysis appeared fast and reliable and its results corresponded to those obtained using the traditional centralized approach. A real time interactive dashboard has also been presented to show analysis results and make the workflow swifter and easier.

Original languageEnglish
Pages (from-to)71-81
Number of pages11
JournalJournal of E-Learning and Knowledge Society
Volume14
Issue number1
DOIs
Publication statusPublished - Jan 1 2018

Fingerprint

Data mining
privacy
data analysis
Decision support systems
Health care
Information management
legal policy
Ontology
Semantics
Statistics
workflow
Network protocols
ontology
statistics
semantics
health care
management
Compliance
time
coherence

Keywords

  • Data mining
  • Distributed learning
  • Distributed preliminary analysis
  • Healthcare
  • Privacy-preserving

ASJC Scopus subject areas

  • Education
  • Computer Science Applications

Cite this

Preliminary data analysis in healthcare multicentric data mining : A privacy-preserving distributed approach. / Damiani, Andrea; Masciocchi, Carlotta; Boldrini, Luca; Gatta, Roberto; Dinapoli, Nicola; Lenkowicz, Jacopo; Chiloiro, Giuditta; Gambacorta, Maria Antonietta; Tagliaferri, Luca; Autorino, Rosa; Pagliara, Monica Maria; Blasi, Maria Antonietta; Van Soest, Johan; Dekker, Andre; Valentini, Vincenzo.

In: Journal of E-Learning and Knowledge Society, Vol. 14, No. 1, 01.01.2018, p. 71-81.

Research output: Contribution to journalArticle

Damiani, Andrea ; Masciocchi, Carlotta ; Boldrini, Luca ; Gatta, Roberto ; Dinapoli, Nicola ; Lenkowicz, Jacopo ; Chiloiro, Giuditta ; Gambacorta, Maria Antonietta ; Tagliaferri, Luca ; Autorino, Rosa ; Pagliara, Monica Maria ; Blasi, Maria Antonietta ; Van Soest, Johan ; Dekker, Andre ; Valentini, Vincenzo. / Preliminary data analysis in healthcare multicentric data mining : A privacy-preserving distributed approach. In: Journal of E-Learning and Knowledge Society. 2018 ; Vol. 14, No. 1. pp. 71-81.
@article{3924ee1b3f2b4025bb94a4f041a40b91,
title = "Preliminary data analysis in healthcare multicentric data mining: A privacy-preserving distributed approach",
abstract = "The new era of cognitive health care systems offers a large amount of patient data that can be used to develop prediction models and clinical decision support systems. In this frame, the multi-institutional approach is strongly encouraged in order to reach more numerous samples for data mining and more reliable statistics. For these purposes, shared ontologies need to be developed for data management to ensure database semantic coherence in accordance with the various centers’ ethical and legal policies. Therefore, we propose a privacy-preserving distributed approach as a preliminary data analysis tool to identify possible compliance issues and heterogeneity from the agreed multi-institutional research protocol before training a clinical prediction model. This kind of preliminary analysis appeared fast and reliable and its results corresponded to those obtained using the traditional centralized approach. A real time interactive dashboard has also been presented to show analysis results and make the workflow swifter and easier.",
keywords = "Data mining, Distributed learning, Distributed preliminary analysis, Healthcare, Privacy-preserving",
author = "Andrea Damiani and Carlotta Masciocchi and Luca Boldrini and Roberto Gatta and Nicola Dinapoli and Jacopo Lenkowicz and Giuditta Chiloiro and Gambacorta, {Maria Antonietta} and Luca Tagliaferri and Rosa Autorino and Pagliara, {Monica Maria} and Blasi, {Maria Antonietta} and {Van Soest}, Johan and Andre Dekker and Vincenzo Valentini",
year = "2018",
month = "1",
day = "1",
doi = "10.20368/1971-8829/1454",
language = "English",
volume = "14",
pages = "71--81",
journal = "Journal of E-Learning and Knowledge Society",
issn = "1826-6223",
publisher = "Italian e-Learning Association",
number = "1",

}

TY - JOUR

T1 - Preliminary data analysis in healthcare multicentric data mining

T2 - A privacy-preserving distributed approach

AU - Damiani, Andrea

AU - Masciocchi, Carlotta

AU - Boldrini, Luca

AU - Gatta, Roberto

AU - Dinapoli, Nicola

AU - Lenkowicz, Jacopo

AU - Chiloiro, Giuditta

AU - Gambacorta, Maria Antonietta

AU - Tagliaferri, Luca

AU - Autorino, Rosa

AU - Pagliara, Monica Maria

AU - Blasi, Maria Antonietta

AU - Van Soest, Johan

AU - Dekker, Andre

AU - Valentini, Vincenzo

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The new era of cognitive health care systems offers a large amount of patient data that can be used to develop prediction models and clinical decision support systems. In this frame, the multi-institutional approach is strongly encouraged in order to reach more numerous samples for data mining and more reliable statistics. For these purposes, shared ontologies need to be developed for data management to ensure database semantic coherence in accordance with the various centers’ ethical and legal policies. Therefore, we propose a privacy-preserving distributed approach as a preliminary data analysis tool to identify possible compliance issues and heterogeneity from the agreed multi-institutional research protocol before training a clinical prediction model. This kind of preliminary analysis appeared fast and reliable and its results corresponded to those obtained using the traditional centralized approach. A real time interactive dashboard has also been presented to show analysis results and make the workflow swifter and easier.

AB - The new era of cognitive health care systems offers a large amount of patient data that can be used to develop prediction models and clinical decision support systems. In this frame, the multi-institutional approach is strongly encouraged in order to reach more numerous samples for data mining and more reliable statistics. For these purposes, shared ontologies need to be developed for data management to ensure database semantic coherence in accordance with the various centers’ ethical and legal policies. Therefore, we propose a privacy-preserving distributed approach as a preliminary data analysis tool to identify possible compliance issues and heterogeneity from the agreed multi-institutional research protocol before training a clinical prediction model. This kind of preliminary analysis appeared fast and reliable and its results corresponded to those obtained using the traditional centralized approach. A real time interactive dashboard has also been presented to show analysis results and make the workflow swifter and easier.

KW - Data mining

KW - Distributed learning

KW - Distributed preliminary analysis

KW - Healthcare

KW - Privacy-preserving

UR - http://www.scopus.com/inward/record.url?scp=85048326517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048326517&partnerID=8YFLogxK

U2 - 10.20368/1971-8829/1454

DO - 10.20368/1971-8829/1454

M3 - Article

AN - SCOPUS:85048326517

VL - 14

SP - 71

EP - 81

JO - Journal of E-Learning and Knowledge Society

JF - Journal of E-Learning and Knowledge Society

SN - 1826-6223

IS - 1

ER -