Using Patient Similarity Networks to Model Hospital Length of Stay

Estimating hospital length of stay.

Modeling Hospital Length of Stay Using Patient Similarity Networks 

Project description

A research project is currently underway in the Department of Management Science and Systems at the State University of New York at Buffalo -- the goal of which is to use graph neural networks to classify patients based on their length of stay in hospital(s). Data was collected in two different settings - during Covid and normal times -- and we study patient flows, staff, physician and nurse schedules and their impact on length of stay and overall healthcare scheduling. One of the datasets is proprietary, while the other is available from online sources.

The undergraduate/graduate student(s) who are expected to join the project will help design the graph neural network(s) by careful examination and processing of healthcare data. In particular, they will be involved with possibly the following activities:
a. Become familiar with the overall architecture of the project, the multimodal data collected and required for the design of the graph neural networks(s).
b. Be familiar with Natural Language Processing techniques and use tools which are developed for processing clinical notes, EHRs etc.
c. Design visualization interface(s) in which the results from analytics can be displayed (such as a Python Django frontend and PSQL database)
d. Occasionally participate in client / stakeholder meetings.
f. Will be involved in reading research papers, interpreting them and using implementations as available from Github repositories.
g. Enthusiastically participate in brown bag sessions and group presentations.
h. Expected to work with graduate students (Masters and PhD) and undergraduate students who are involved in the project. Team work is highly encouraged although some tasks will have to be accomplished
i.There will be individual meetings with the project leads every week to discuss project related and unrelated issues.
j. The ideal student would work with us for at least TWO semesters, including winter or summer break as appropriate.

What we offer: This is an UNFUNDED project. However we do have the opportunity to do any of the following:
a. Offer independent study / thesis credits as appropriate.
b. Offer volunteer letters for student(s) on OPT, with the assumption that the student(s) will contribute actively to the project, be evaluated on a regular basis as required by the SOM, and follow all the rules deemed appropriate by the HR at SOM. This is a fast paced research project and we do need active contributions!
c. Recommendation letters, ONLY after the student has made substantial contributions to the project, worked for at least two semesters and ideally has co-authored a paper with any of the faculty members involved in the project.

The project is available immediately and is a very hands-on project with a lot of opportunity to develop skills pertaining to real world data processing, programming (Java, Python or R), visualization, use of machine learning knowledge acquired in the curriculum. It is anticipated that the project will continue for at least a year or longer.

If the above is of interest, please send your resumes and a few paragraphs on why this is of interest to you, to Haimonti Dutta (

Project outcome

  • Research Papers
  • Products such as tools that visualize data, and predictions 

Project details

Timing, eligibility and other details
Length of commitment One Year (10-12 Months)
Start time Spring (January/February)
In-person, remote, or hybrid? In-Person 
Level of collaboration Small Group (2-3 Students)
Benefits Academic Credit 
Who is eligible  Undergraduate students who have the Ability to Code in R, Python; Ability to analyze, preprocess and clean large datasets; Ability to develop visualization modules 

Core partners

  • CS, Math, Statistics, Operations Research and Management Sciences 

Project mentor

Haimonti Dutta

Associate Professor

Management Science and Systems

Phone: (484) 432-1484


Start the project

  1. Email the project mentor using the contact information above to express your interest and get approval to work on the project. (Here are helpful tips on how to contact a project mentor.)
  2. After you receive approval from the mentor to start this project, click the button to start the digital badge. (Learn more about ELN's digital badge options.) 

Preparation activities

Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase. 

  • Write code for data cleaning and statistical analysis
  • Develop visualization modules 


health care, machine learning, operations research, optimization, management science and systems