Dr. Patil is a former postdoctoral research fellow at the Harvard Chan School of Public Health Department of Biostatistics/Dana-Farber Cancer Institute Department of Biostatistics and Computational Biology with Giovanni Parimigiani. He completed his PhD in Biostatistics from the Johns Hopkins Bloomberg School of Public Health with Jeff Leek. His professional interests include personalized medicine, genomics, prediction, data visualization, and study reproducibility/replicability.
Dr. Patil is currently working on:
- Multi-study prediction
- Statistical definitions for reproducibility and replicability.
- Stable and interpretable prediction methods for gene expression data. The contexts are cancer risk classifcation and survival prediction.
- Assessing the additional value a genomic signature can provide beyond standard clinical measurements in a randomized trial setting.
- Interactive health visualizations executable in one line from R.
- Automated analysis templates with the ability to compare results after parameters have been changed.
- Johns Hopkins University, PhD Field of Study: Biostatistics
- New York University, BA Field of Study: Mathematics
- Published on 7/16/2021
Tieskens KF, Patil P, Levy JI, Brochu P, Lane KJ, Fabian MP, Carnes F, Haley BM, Spangler KR, Leibler JH. Time-varying associations between COVID-19 case incidence and community-level sociodemographic, occupational, environmental, and mobility risk factors in Massachusetts. BMC Infect Dis. 2021 Jul 16; 21(1):686. PMID: 34271870.
- Published on 7/12/2021
Zhang Y, Patil P, Johnson WE, Parmigiani G. Robustifying genomic classifiers to batch effects via ensemble learning. Bioinformatics. 2021 07 12; 37(11):1521-1527. PMID: 33245114.
- Published on 2/17/2021
Tieskens K, Patil P, Levy JI, Brochu P, Lane KJ, Fabian MP, Carnes F, Haley BM, Spangler KR, Leibler JH. Time-varying associations between COVID-19 case incidence and community-level sociodemographic, occupational, environmental, and mobility risk factors in Massachusetts. Res Sq. 2021 Feb 17. PMID: 33619475.
- Published on 1/17/2020
Nudel J, Bishara AM, de Geus SWL, Patil P, Srinivasan J, Hess DT, Woodson J. Development and validation of machine learning models to predict gastrointestinal leak and venous thromboembolism after weight loss surgery: an analysis of the MBSAQIP database. Surg Endosc. 2021 01; 35(1):182-191. PMID: 31953733.
- Published on 1/1/2020
Ramchandran M, Patil P, Parmigiani G. Tree-Weighting for Multi-Study Ensemble Learners. Pac Symp Biocomput. 2020; 25:451-462. PMID: 31797618.
- Published on 8/1/2019
Patil P, Peng RD, Leek JT. Publisher Correction: A visual tool for defining reproducibility and replicability. Nat Hum Behav. 2019 Aug; 3(8):886. PMID: 31358976.
- Published on 7/1/2019
Patil P, Peng RD, Leek JT. A visual tool for defining reproducibility and replicability. Nat Hum Behav. 2019 07; 3(7):650-652. PMID: 31209370.
- Published on 3/12/2018
Patil P, Parmigiani G. Training replicable predictors in multiple studies. Proc Natl Acad Sci U S A. 2018 03 13; 115(11):2578-2583. PMID: 29531060.
- Published on 7/1/2016
Patil P, Peng RD, Leek JT. What Should Researchers Expect When They Replicate Studies? A Statistical View of Replicability in Psychological Science. Perspect Psychol Sci. 2016 07; 11(4):539-44. PMID: 27474140.
- Published on 3/31/2016
Patil P, Colantuoni E, Leek JT, Rosenblum M. Genomic and clinical predictors for improving estimator precision in randomized trials of breast cancer treatments. Contemp Clin Trials Commun. 2016 Aug 15; 3:48-54. PMID: 29736456.
News & In the Media
- Published on May 28, 2021