EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Collaborative learning from distributed data with differentially private synthetic data

Lukas Prediger, Joonas Jälkö, Antti Honkela, Samuel Kaski

BMC Medical Informatics and Decision Making · 2024

DOI: 10.1186/s12911-024-02563-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BMC Medical Informatics and Decision Making, 2024. Verfasst von Lukas Prediger und 3 weiteren Autor:innen. Beteiligte Einrichtung: Aalto University, Espoo, 00076, Finland. lukas.m.prediger@aalto.fi. Hauptthemen laut MEDLINE: Information Dissemination. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Council of Finland, European Union, Strategic Research Council (SRC) established within the Research Council of Finland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthetic data sets in place of the original data for collaborative learning on real-world health data from the UK Biobank.

Methods

We perform an empirical evaluation based on an existing prospective cohort study from the literature. Multiple parties were simulated by splitting the UK Biobank cohort along assessment centers, for which we generate synthetic data using differentially private generative modelling techniques. We then apply the original study’s Poisson regression analysis on the combined synthetic data sets and evaluate the effects of 1) the size of local data set, 2) the number of participating parties, and 3) local shifts in distributions, on the obtained likelihood scores.

Results

We discover that parties engaging in the collaborative learning via shared synthetic data obtain more accurate estimates of the regression parameters compared to using only their local data. This finding extends to the difficult case of small heterogeneous data sets. Furthermore, the more parties participate, the larger and more consistent the improvements become up to a certain limit. Finally, we find that data sharing can especially help parties whose data contain underrepresented groups to perform better-adjusted analysis for said groups.

Conclusions

Based on our results we conclude that sharing of synthetic data is a viable method for enabling learning from sensitive data without violating privacy constraints even if individual data sets are small or do not represent the overall population well. Lack of access to distributed sensitive data is often a bottleneck in biomedical research, which our study shows can be alleviated with privacy-preserving collaborative learning methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Information DisseminationHumansUnited KingdomCooperative BehaviorConfidentialityPrivacyBiological Specimen BanksProspective Studies

Stichwörter der Autor:innen

Collaborative learningDifferential privacyHealth informaticsSynthetic data

Autor:innen und Institutionen

  • Aalto University, Espoo, 00076, Finland. lukas.m.prediger@aalto.fi.
  • Aalto University, Espoo, 00076, Finland.
  • University of Helsinki, Helsinki, 00014, Finland.
  • University of Manchester, Manchester, M13 9Pl, UK.

Förderung

  • Research Council of Finland
  • European Union
  • Strategic Research Council (SRC) established within the Research Council of Finland
  • UK Research and Innovation

Zitieren

APA

Prediger, L., Jälkö, J., Honkela, A., & Kaski, S. (2024). Collaborative learning from distributed data with differentially private synthetic data. BMC Medical Informatics and Decision Making. https://doi.org/10.1186/s12911-024-02563-7

Vancouver

Prediger L, Jälkö J, Honkela A, Kaski S. Collaborative learning from distributed data with differentially private synthetic data. BMC Medical Informatics and Decision Making. 2024. doi:10.1186/s12911-024-02563-7

BibTeX
@article{Prediger2024,
  author = {Prediger, Lukas and Jälkö, Joonas and Honkela, Antti and Kaski, Samuel},
  title = {Collaborative learning from distributed data with differentially private synthetic data},
  journal = {BMC Medical Informatics and Decision Making},
  year = {2024},
  doi = {10.1186/s12911-024-02563-7}
}
Kostenlos starten →