Grant Number:	5U01CA274576-02 Interpret this number
Primary Investigator:	Long, Qi
Organization:	University Of Pennsylvania
Project Title:	Robust Privacy Preserving Distributed Analysis Platform for Cancer Research: Addressing Data Bias and Disparities
Fiscal Year:	2024

Project Summary Privacy-preserving distributed analysis has gained increasing interests in the broad biomedical research community in recent years, as it can a) eliminate the need to create, maintain, and secure access to central data repositories, b) minimize the need to disclose protected health information outside the data-owning entity, and c) mitigate many security, proprietary, privacy and other concerns. As such, it offers great promises in lowering regulatory and other hurdles for collaboration across multiple institutions and enhancing the public trust in biomedical research. Equally important, analysis of health data from multiple institutions across the US would yield more robust and generalizable findings. This is particularly relevant in cancer disparities research as the sample size for minority groups can be very small from one institution. However, there remain significant methodological gaps in the current state-of-the-art for privacy-preserving distributed analysis. Most notably, missing data present significant challenges, as they are ubiquitous in biomedical data including, but not limited to, electronic health records (EHR). It is well known that missing data is a major source of bias in EHR. For example, patients from minority groups and those who have less access to private insurance tend to have more missing data in their EHR. Biased data as a result of missing data are known to yield unfair statistical and machine learning models, which in turn can perpetuate and exacerbate health inequities and disparities. There has been no work on principled approaches for properly handling missing data in distributed analysis beyond our recent works. In addition, it is well-known that distributed analysis is still at risk of revealing important individual-level information and lacks rigorous guarantee in the sense of differential privacy, the prevailing notion and metric for privacy protection. To address these significant limitations, we propose three specific aims. In Aim 1, we will refine and develop state-of-the-art imputation methods for handling missing data in distributed analysis and develop advanced functionalities for enhanced privacy protection through differential privacy control and homomorphic encryption. Building on the methods developed in Aim 1, we will develop an open-source and open-access distributed analysis platform that includes a robust system architecture and user-friendly GUI in Aim 2. We will assess and validate our distributed analysis platform using real-world use cases in cancer disparities research in Aim 3. With the enhanced privacy protection, our proposed distributed analysis platform will have the potential to further enhance public trust and lowerhurdles for collaboration across multiple institutions in cancer research. As such, our platform will enable researchers to use more information and less biased data in cancer research, enhance the validity, robustness and generalizability of research findings, and offer research substantial benefits in areas including, but not limited to, cancer disparities and informatics practice.




Deep learning-based approaches for multi-omics data integration and analysis.
Authors: Ballard J.L. , Wang Z. , Li W. , Shen L. , Long Q. .
Source: Biodata Mining, 2024-10-02 00:00:00.0; 17(1), p. 38.
EPub date: 2024-10-02 00:00:00.0.
PMID: 39358793
Related Citations

DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation.
Authors: Wu Y. , Keoliya M. , Chen K. , Velingker N. , Li Z. , Getzen E.J. , Long Q. , Naik M. , Parikh R.B. , Wong E. .
Source: Proceedings Of Machine Learning Research, 2024 Jul; 235, p. 53597-53618.
PMID: 39205826
Related Citations

Filling the gaps: leveraging large language models for temporal harmonization of clinical text across multiple medical visits for clinical prediction.
Authors: Choi I. , Long Q. , Getzen E. .
Source: Medrxiv : The Preprint Server For Health Sciences, 2024-05-07 00:00:00.0; , .
EPub date: 2024-05-07 00:00:00.0.
PMID: 38765975
Related Citations

SADI: Similarity-Aware Diffusion Model-Based Imputation for Incomplete Temporal EHR Data.
Authors: Dai Z. , Getzen E. , Long Q. .
Source: Proceedings Of Machine Learning Research, 2024 May; 238, p. 4195-4203.
PMID: 39267895
Related Citations

SAFER: sub-hypergraph attention-based neural network for predicting effective responses to dose combinations.
Authors: Tang Y.C. , Li R. , Tang J. , Zheng W.J. , Jiang X. .
Source: Research Square, 2024-04-30 00:00:00.0; , .
EPub date: 2024-04-30 00:00:00.0.
PMID: 38746131
Related Citations

Deep learning to predict rapid progression of Alzheimer's disease from pooled clinical trials: A retrospective study.
Authors: Ma X. , Shyer M. , Harris K. , Wang D. , Hsu Y.C. , Farrell C. , Goodwin N. , Anjum S. , Bukhbinder A.S. , Dean S. , et al. .
Source: Plos Digital Health, 2024 Apr; 3(4), p. e0000479.
EPub date: 2024-04-10 00:00:00.0.
PMID: 38598464
Related Citations

SPeC: A Soft Prompt-Based Calibration on Performance Variability of Large Language Model in Clinical Notes Summarization.
Authors: Chuang Y.N. , Tang R. , Jiang X. , Hu X. .
Source: Journal Of Biomedical Informatics, 2024 Mar; 151, p. 104606.
EPub date: 2024-02-05 00:00:00.0.
PMID: 38325698
Related Citations

Disentangling Accelerated Cognitive Decline from the Normal Aging Process and Unraveling Its Genetic Components: A Neuroimaging-Based Deep Learning Approach.
Authors: Dai Y. , Hsu Y.C. , Fernandes B.S. , Zhang K. , Li X. , Enduru N. , Liu A. , Manuel A.M. , Jiang X. , Zhao Z. , et al. .
Source: Journal Of Alzheimer's Disease : Jad, 2024; 97(4), p. 1807-1827.
PMID: 38306043
Related Citations

PFERM: A Fair Empirical Risk Minimization Approach with Prior Knowledge.
Authors: Hou B. , Mondragón A. , Tarzanagh D.A. , Zhou Z. , Saykin A.J. , Moore J.H. , Ritchie M.D. , Long Q. , Shen L. .
Source: Amia Joint Summits On Translational Science Proceedings. Amia Joint Summits On Translational Science, 2024; 2024, p. 211-220.
EPub date: 2024-05-31 00:00:00.0.
PMID: 38827072
Related Citations

Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization.
Authors: Xiao J. , Sun R. , Long Q. , Su W.J. .
Source: Proceedings Of Machine Learning Research, 2024; 247, p. 5074-5075.
PMID: 39206101
Related Citations

Fair Canonical Correlation Analysis.
Authors: Zhou Z. , Tarzanagh D.A. , Hou B. , Tong B. , Xu J. , Feng Y. , Long Q. , Shen L. .
Source: Advances In Neural Information Processing Systems, 2023 Dec; 36, p. 3675-3705.
PMID: 38665178
Related Citations

Predicting multiple sclerosis severity with multimodal deep neural networks.
Authors: Zhang K. , Lincoln J.A. , Jiang X. , Bernstam E.V. , Shams S. .
Source: Bmc Medical Informatics And Decision Making, 2023-11-09 00:00:00.0; 23(1), p. 255.
EPub date: 2023-11-09 00:00:00.0.
PMID: 37946182
Related Citations

Characterizing Treatment Non-responders vs. Responders in Completed Alzheimer's Disease Clinical Trials.
Authors: Wang D. , Ling Y. , Harris K. , Schulz P.E. , Jiang X. , Kim Y. .
Source: Medrxiv : The Preprint Server For Health Sciences, 2023-10-30 00:00:00.0; , .
EPub date: 2023-10-30 00:00:00.0.
PMID: 37961216
Related Citations

DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Research.
Authors: Chuang Y.N. , Wang G. , Chang C.Y. , Lai K.H. , Zha D. , Tang R. , Yang F. , Reyes A.C. , Zhou K. , Jiang X. , et al. .
Source: Proceedings Of The ... Acm International Conference On Information & Knowledge Management. Acm International Conference On Information And Knowledge Management, 2023 Oct; 2023, p. 5021-5025.
EPub date: 2023-10-21 00:00:00.0.
PMID: 38832084
Related Citations

Disentangling accelerated cognitive decline from the normal aging process and unraveling its genetic components: A neuroimaging-based deep learning approach.
Authors: Dai Y. , Hsu Y.C. , Fernandes B.S. , Zhang K. , Li X. , Enduru N. , Liu A. , Manuel A.M. , Jiang X. , Zhao Z. .
Source: Research Square, 2023-09-08 00:00:00.0; , .
EPub date: 2023-09-08 00:00:00.0.
PMID: 37720047
Related Citations

Fairness-Aware Class Imbalanced Learning on Multiple Subgroups.
Authors: Tarzanagh D.A. , Hou B. , Tong B. , Long Q. , Shen L. .
Source: Proceedings Of Machine Learning Research, 2023 Aug; 216, p. 2123-2133.
PMID: 38601022
Related Citations

Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching.
Authors: Yuan J. , Tang R. , Jiang X. , Hu X. .
Source: Amia ... Annual Symposium Proceedings. Amia Symposium, 2023; 2023, p. 1324-1333.
EPub date: 2024-01-11 00:00:00.0.
PMID: 38222339
Related Citations

Sensitive Data Detection with High-Throughput Machine Learning Models in Electrical Health Records.
Authors: Zhang K. , Jiang X. .
Source: Amia ... Annual Symposium Proceedings. Amia Symposium, 2023; 2023, p. 814-823.
EPub date: 2024-01-11 00:00:00.0.
PMID: 38222389
Related Citations

Leveraging informative missing data to learn about acute respiratory distress syndrome and mortality in long-term hospitalized COVID-19 patients throughout the years of the pandemic.
Authors: Getzen E. , Tan A.L. , Brat G. , Omenn G.S. , Strasser Z. , Consortium for Clinical Characterization of COVID-19 by EHR (4CE) (Collaborative Group/Consortium) , Long Q. , Holmes J.H. , Mowery D. .
Source: Amia ... Annual Symposium Proceedings. Amia Symposium, 2023; 2023, p. 942-950.
EPub date: 2024-01-11 00:00:00.0.
PMID: 38222425
Related Citations

Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?
Authors: Chen S. , Zheng Q. , Long Q. , Su W.J. .
Source: Journal Of Machine Learning Research : Jmlr, 2023; 24, .
PMID: 39105110
Related Citations