Skip to main content
An official website of the United States government
Grant Details

Grant Number: 5R01CA236468-04 Interpret this number
Primary Investigator: Chen, Jinbo
Organization: University Of Pennsylvania
Project Title: Data and Information Integration for Risk Prediction in the Era of Big Data
Fiscal Year: 2022


Abstract Toward precision medicine and precision disease prevention, the overarching goal of this proposal is to develop innovative statistical methods for accurate risk prediction. We address three challenges that plague studies on the value of candidate risk predictors that adds to established predictors for improved predictive accuracy: there is often a lack of independent validation data, the source population for the study sample and the target population of prediction are often different, no statistical methods are currently available for developing risk prediction models using individually-matched case-control data, and there is a lack of statistical methods for helping assess study feasibility beyond standard power calculation for testing predictor-outcome association. On the other hand, data and information that are external to the study may well exist and can be exploited to alleviate these challenges. For example, a model with only standard predictors often exists and has been validated, and the distribution of standard risk predictors in the target population of prediction is often available. We propose that external data and information can be exploited to address the above-mentioned challenges for candidate predictor evaluation, and develop innovative statistical methods to bring this idea to fruition. Considering prediction of a binary outcome, we propose a novel method to building logistic prediction models that are guaranteed to calibrate well in the target population, an innovative method for risk prediction with individually matched case-control data, and a method to project the added value of candidate predictors to help assess study feasibility. Our methods, accompanied by user-friendly software, will facilitate cost effective and timely predictor evaluation for predicting binary outcomes. Our methods were motivated by and will be applied to several PI Chen's collaborative studies.


Towards optimal model evaluation: enhancing active testing with actively improved estimators.
Authors: Lee J. , Kolla L. , Chen J. .
Source: Scientific reports, 2024-05-09; 14(1), p. 10690.
EPub date: 2024-05-09.
PMID: 38724626
Related Citations

A constrained maximum likelihood approach to developing well-calibrated models for predicting binary outcomes.
Authors: Cao Y. , Ma W. , Zhao G. , McCarthy A.M. , Chen J. .
Source: Lifetime data analysis, 2024-05-08; , .
EPub date: 2024-05-08.
PMID: 38717617
Related Citations

Robust estimation of mean-variance relation.
Authors: Li M. , Ma Y. .
Source: Statistics in medicine, 2024-01-30; 43(2), p. 419-434.
EPub date: 2023-11-22.
PMID: 37994214
Related Citations

A robust approach for electronic health record-based case-control studies with contaminated case pools.
Authors: Dai G. , Ma Y. , Hasler J. , Chen J. , Carroll R.J. .
Source: Biometrics, 2023 Sep; 79(3), p. 2023-2035.
EPub date: 2022-07-22.
PMID: 35841231
Related Citations

Two-phase stratified sampling and analysis for predicting binary outcomes.
Authors: Cao Y. , Haneuse S. , Zheng Y. , Chen J. .
Source: Biostatistics (Oxford, England), 2023-07-14; 24(3), p. 585-602.
PMID: 34923588
Related Citations

Breast density quantitative measures and breast cancer risk among screened Black women.
Authors: Mahmoud M.A. , Ehsan S. , Pantalone L. , Mankowski W. , Conant E.F. , Kontos D. , Chen J. , McCarthy A.M. .
Source: JNCI cancer spectrum, 2023-07-03; 7(4), .
PMID: 37289565
Related Citations

Goodness-of-fit two-phase sampling designs for time-to-event outcomes: a simulation study based on New York University Women's Health Study for breast cancer.
Authors: Lee M. , Chen J. , Zeleniuch-Jacquotte A. , Liu M. .
Source: BMC medical research methodology, 2023-05-19; 23(1), p. 119.
EPub date: 2023-05-19.
PMID: 37208600
Related Citations

Development of Machine Learning Algorithms Incorporating Electronic Health Record Data, Patient-Reported Outcomes, or Both to Predict Mortality for Outpatients With Cancer.
Authors: Parikh R.B. , Hasler J.S. , Zhang Y. , Liu M. , Chivers C. , Ferrell W. , Gabriel P.E. , Lerman C. , Bekelman J.E. , Chen J. .
Source: JCO clinical cancer informatics, 2022 Dec; 6, p. e2200073.
PMID: 36480775
Related Citations

Validation of Breast Cancer Risk Models by Race/Ethnicity, Family History and Molecular Subtypes.
Authors: McCarthy A.M. , Liu Y. , Ehsan S. , Guan Z. , Liang J. , Huang T. , Hughes K. , Semine A. , Kontos D. , Conant E. , et al. .
Source: Cancers, 2021-12-23; 14(1), .
EPub date: 2021-12-23.
PMID: 35008209
Related Citations

Risk factors for an advanced breast cancer diagnosis within 2 years of a negative mammogram.
Authors: McCarthy A.M. , Ehsan S. , Appel S. , Welch M. , He W. , Bahl M. , Chen J. , Lehman C.D. , Armstrong K. .
Source: Cancer, 2021-09-15; 127(18), p. 3334-3342.
EPub date: 2021-06-01.
PMID: 34061353
Related Citations

Phenotyping issues for exploring electronic health records to design clinical trials.
Authors: Schnall J. , Zhang L. , Chen J. .
Source: Clinical trials (London, England), 2020 Aug; 17(4), p. 402-404.
EPub date: 2020-06-10.
PMID: 32522027
Related Citations

Novel two-phase sampling designs for studying binary outcomes.
Authors: Wang L. , Williams M.L. , Chen Y. , Chen J. .
Source: Biometrics, 2020 Mar; 76(1), p. 210-223.
EPub date: 2019-11-14.
PMID: 31449330
Related Citations

Precision prophylaxis: Identifying the optimal timing for risk-reducing salpingo-oophorectomy based on type of BRCA1 and BRCA2 cluster region mutations.
Authors: Solsky I. , Chen J. , Rebbeck T.R. .
Source: Gynecologic oncology, 2020 Feb; 156(2), p. 363-376.
EPub date: 2020-01-07.
PMID: 31918993
Related Citations

Phenotype validation in electronic health records based genetic association studies.
Authors: Wang L. , Damrauer S.M. , Zhang H. , Zhang A.X. , Xiao R. , Moore J.H. , Chen J. .
Source: Genetic epidemiology, 2017 Dec; 41(8), p. 790-800.
EPub date: 2017-10-11.
PMID: 29023970
Related Citations

Back to Top