Rameshbabu Manyam
Research Assistant Professor
Research Assistant Professor
Faculty, Biostatistics and Bioinformatics
My research interests include, but not limited to, data science, bigdata analytics, and risk prediction frameworks using machine learning algorithms and high-performance computing environment. Specific fileds of interest include longitudinal EMR data analytics using statistical, machine learning, ensemble learning, transfer learning, and federated learning algorithms (e.g., cox regression, support vector machines, decision trees - eXtreme Gradient Boosting: XGBoost, random survival forests, RSF and neural networks). I have over 25 years of professional experience working in several data-driven research projects (such as Real Time clinical data analytics, Children’s Health Exposure Analysis Resource (CHEAR), 'Emory Health and Exposome Research Center: Understanding Lifetime Exposures (HERCULES)', Tennessee's Longitudinal Data System (TLDS), Kennesaw's Teacher Quality Partnership, (TQP)), and built custom databases, software applications, and data visualization portals/dash boards. I have hands-on working knowledge with Emory healthcare data sources (such as Cerner’s Electronic Medical Records (EMR), EPIC’s Electronic Health Records (EHR) database systems, adult cardiac surgical database and clinical data warehouse). My most recent research projects include building institutional biobank for CURE COVID-19 biospecimens and metadata prospective cohort, and developing novel frameworks to predict the risk of readmission after coronary artery bypass grafting (CABG). My current collaborative research efforts focus on developing scalable, portable, and reproducible machine learning powered analytical frameworks - via feature engineering, hybrid feature selection, and ensemble learning methods (for instance, XGBoost and RSF) to predict 'time-to-event' outcomes, such as time to conception in fertility treatment, time to local reoccurance of tumor, time to readmission to hospital after discharge following CABG.
Recent honors and awards
- 2023 - 2024: Dean's Pilot Innovation Award, Rollins School of Public Health
- 2022 - 2023: Biostatistics and Bioinformatics Faculty Mentor Award, Emory University
- 2021 - 2022: Biostatistics and Bioinformatics Distinguished Teaching Award, Emory University
- 2020: Outstanding Graduate Student Award, Dept.of Computer Science, Georgia State Univeristy
- 2019: Three MInute (3 MT) Thesis Award, second prize, Georgia Sate University
Contact Information
1518 Clifton Road NE
Atlanta , GA 30322
1518-002-3AA
Phone: 404-727-4869
Fax: 404-727-1370
Email: rmanyam@emory.edu
Areas of Interest
- Cardiovascular Diseases
- Data Mining
- Data Science
- High Performance Computing
- Longitudinal Analysis
- Machine Learning
- Missing and Mismeasured Data
- Survival Analysis
- Systems Integration
Education
- PhD 2019, Georgia State University, Atlanta, GA, USA
- MS 2002, Georgia State University, Atlanta, GA, USA
- MTech 1993, Indian Institute of Technology (Banaras Hindu University), Varanasi, India
- BTech 1991, National Institute of Technology, Warangal, India
Courses Taught
- BIOS 585: Python Programming
- BIOS 584: Python Programming (Non-BIOS)
Affiliations & Activities
- Spring 2023: Python workshop in collaboration with the student organization, Rollins mHealth Collaborative (RmC)
- Fall 2022 : SQL workshop in collaboration with RmC
- Summer 2022: Python workshop in collaboration with RmC
Publications
- Manyam RB, Zhang Y, Binongo J, Rosenblum JM, Keeling WB., 2020, Unraveling the impact of time-dependent perioperative variables on 30-day readmission after coronary artery bypass surgery., Journal of Cardiovascular and Thoracic Surgery., doi: 10.1016/j.jtcvs.2020.09.076.,
- Manyam RB, Zhang Y, Binongo J, Rosenblum JM, Keeling WB, 2019, A New Scalable, Portable Predictive Analytics Framework for Predicting Time-to-event Outcomes in Healthcare., Paper presented at: 2nd Symposium on Machine Learning in Science and Engineering Symposium, June 9-12, 2019, Atlanta, GA, USA. ,
- Manyam RB, Zhang, Y, Binongo J, Rosenblum JM, Keeling, W B, 2019, A Simple, Scalable And Portable Machine Learning Model With Effective Feature Selection For Accurately Predicting 30-day Readmission After Discharge Following CABG., Paper accepted at: 100th Annual Meeting of the Association of American Thoracic Surgeons, May 22-23, 2020; Virtual; New York, NY, USA.,
- Manyam RB, Zhang Y, Binongo J, Rosenblum JM, Keeling, WB., 2019, Unraveling the impact of time-dependent perioperative variables on 30-day readmission following CABG., Paper presented at: 45th Annual Meeting of Western Thoracic and Surgical Association, June 26-29, 2019; Olympic Valley, CA, USA,
- Manyam RB, Zhang Y, Keeling WB, Binongo J, Kayatta, M, Carter, S., 2018, Deep Learning Approach for Predicting 30 Day Readmissions after Coronary Artery Bypass Graft Surgery, Paper presented at: Workshop on Machine Learning for Health, Thirty-second Conference on Neural Information Processing Systems (NeurIPS, 2018), December 8, 2018, Montreal, Canada.,