This web app presents a data-driven approach to predict heart transplantation survival probabilities over time. The prediction is soley based on medical information that is available at transplant time, as explained in detail in our Scientific Reports manuscript. The app presents two modules for performing the analysis:
(1) Manual Entry, where users can insert the values of predictor variables using several text boxes.
(2) CSV Entry, where users can upload the values of predictor variables using a comma seperated variable (CSV) file.
These modules can be accessed using the tabs on the side bar to the left. In addition, one can find more informations about our source code and research teams using the last two tabs at the left.

How to Use the App?

We have created a voice-over-screen video to demonstrate how the app can be used to achieve correct results (and no errors). We highly advise the reader to view the video prior to his/her's first use; the video is short and will reduce the start-up time for new users.

App Status

Version: 0.7.
Last Updated at August 24, 2019 by Fadel Megahed.
Status: No reported outages.

Application Maintainers

The maintainers can be contacted via email at:
Tessa Chen
Fadel Megahed


Data: Protected (click here for details).

Code and App:
CC0 - 'No Rights Reserved'.


  • This web app is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it, given that this app comes with a CCO license.

  • This version is a Beta Version. As of this moment, we have not included any Error Checks to the app. As such, the app will result in errors if the user inputs incomplete information. This issue may be addressed after we recieve feedback from the community to understand how to better design the error handling.

  • To reduce the likelihood of errors, please consult the "How to Use the App?" Section. If issues persist, please contact the maintainers. We will do our best to answer your emails within 2-5 business days.

We provide a csv with all possible values for each variable: here.

Categorical Inputs

Categorical Inputs

Categorical Inputs

Categorical Inputs

Categorical Inputs


Instructions for Automated Analysis:

A csv template for the analysis can be found: here. Additionally, we provide a csv with all possible values for each variable: here.


R Markdown Document

We have created an R Markdown document that contains all the details of our analysis (code, results and some commentary). We invite the user to examine it at: Markdown Website.

The Research Team

Hamidreza Ahady Dolatsara is currently an Assistant Professor in the Graduate School of Management in Clark University. He received his Ph.D. in Industrial & Systems Engineering at Auburn University. In addition, he received an MS in Information Systems from Auburn University and MS in Transportation Engineering from Western Michigan University. His research interests are in machine learning applications in healthcare, transportation, and finance.

Dr. Ying-Ju (Tessa) Chen is an Assistant Professor in the Department of Mathematics at the University of Dayton. Her expertise is in applied machine learning, high performance computing, statistical modeling, and survival analysis. She has 7 journal publications and her work has been funded by several foundations and government agencies.

Christy Evans is a fourth-year undergraduate Pre-Med student at Auburn University. She will begin her graduate studies in Industrial and Systems Engineering at Auburn University in Summer 2019. Her research interests include data analysis and process design as they pertain to her future medical studies.

Dr. Ashish Gupta is an Associate Professor of Analytics in the Raymond J. Harbert College of Business at Auburn University. Dr. Gupta’s research interests are in the areas of data analytics, healthcare informatics, sports analytics, organizational and individual performance.

Dr. Fadel M. Megahed is the Neil R. Anderson Endowed Assistant Professor in the Farmer School of Business at Miami University. His current research focuses on creating new tools to store, organize, analyze, model, and visualize the large heterogeneous data sets associated with modern manufacturing, healthcare and service environments. He has 30 published journal papers and 8 conference proceedings.


Data Collection

The UNOS registry (our data provider) was supported in part by Health Resources and Services Administration contract 234-2005-37011C. The content is the responsibility of the authors alone and does not necessarily reflect the views or policies of the Department of Health and Human Services, nor does mention of trade names, commercial products, or organizations imply endorsement by the U.S. Government.

Funding Sources

The modeling approach, analysis and computational resources were supported in part by the American Society of Safety Professionals Foundation [grant titled ''ASSIST: Advancing Safety Surveillance using Individualized Sensor Technology''], Ohio Supercomputer Center [Grants PMIU0138, PMIU0162, PMIU0166] and the National Science Foundation [CMMI-1635927]. Dr. Megahed's research was also partially supported by the Neil R. Anderson Endowed Assistant Professorship at Miami University.

App Hosting

The research team would like to thank the Department of Statistics at Miami University for hosting our application on their R Server.