• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Privacy-Preserving Logistic Regression for Medical Big Data

Research Project

Project/Area Number 15K00194
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Information security
Research InstitutionMeiji University

Principal Investigator

Kikuchi Hiroaki  明治大学, 総合数理学部, 専任教授 (20266365)

Co-Investigator(Kenkyū-buntansha) 康永 秀生  東京大学, 大学院医学系研究科(医学部), 教授 (90361485)
Co-Investigator(Renkei-kenkyūsha) Hashimoto Hideki  東京大学, 医学系研究科, 教授 (50317682)
Project Period (FY) 2015-04-01 – 2018-03-31
Project Status Completed (Fiscal Year 2017)
Budget Amount *help
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2017: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords医療情報 / ビッグデータ / プライバシー保護 / プライバシー / データマイニング / 垂直分割 / ロジスティック回帰 / 秘匿計算 / ロジステック回帰分析 / 疫学
Outline of Final Research Achievements

In this study, we propose a new secure protocols for privacy-preserving logistic regression of two vertically partitioned datasets. Our protocol is efficient in the sense that coefficients of logistic model are converged in few iterations by using the Iteratively Re-weighted Least Squares (IRLS). In the comparison to one of the existing work using the stochastic gradient descent (SGD), our protocol improved the performance of estimate from 30,000 to 7 iterations. We study the feasibility of the proposed protocol over the the Diagnosis Procedure Combination (DPC) database, a large-scale claim-based database of Japanese hospitals that contains confidential status of patients. Our scheme allows to estimate the probability of death with some patient information without revealing confidential data to the other party. Using the toy dataset and the trial implementation of the proposed scheme, we examine the accuracy of the proposed scheme and study the feasibility.

Report

(4 results)
  • 2017 Annual Research Report   Final Research Report ( PDF )
  • 2016 Research-status Report
  • 2015 Research-status Report
  • Research Products

    (4 results)

All 2017 2016

All Journal Article (1 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 1 results) Presentation (3 results) (of which Int'l Joint Research: 1 results)

  • [Journal Article] Efficient Privacy-Preserving Logistic Regression with Iteratively Re-weighted Least Squares,2016

    • Author(s)
      H. Kikuchi, H. Yasunaga, H. Matsui and C. I. Fan,
    • Journal Title

      11th Asia Joint Conference on Information Security (AsiaJCIS)

      Volume: 1 Pages: 48-54

    • DOI

      10.1109/asiajcis.2016.21

    • Related Report
      2016 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Privacy-Preserving Multiple Linear Regression of Vertically Partitioned Real Medical Datasets,"2017

    • Author(s)
      H. Kikuchi, C. Hamanaga, H. Yasunaga, H. Matsui and H. Hashimoto,
    • Organizer
      2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA)
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] プライバシーを保護した垂直分割線形回帰システムの実装とDPCデータセットを用いた評価2016

    • Author(s)
      濱永 千佳 , 菊池 浩明 , 康永 秀生 , 松居 宏樹 , 橋本 英樹
    • Organizer
      マルチメディア,分散協調とモバイルシンポジウム2016論文集
    • Place of Presentation
      鳥羽シーサイドホテル
    • Year and Date
      2016-07-06
    • Related Report
      2016 Research-status Report
  • [Presentation] 組織間での分散秘匿ロジスティック回帰 による脳卒中の分析2016

    • Author(s)
      菊池浩明,康永秀生, 松居宏樹,橋本秀樹
    • Organizer
      第26回日本疫学会学術総会講演集,p. 91, P1-026, 日本疫学会, 2016.
    • Place of Presentation
      米子コンベンションセンター
    • Year and Date
      2016-01-21
    • Related Report
      2015 Research-status Report

URL: 

Published: 2015-04-16   Modified: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi