Clinical Outcome Prediction Using Multimodal Data

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 clinical outcome prediction (estimation of length of stay, mortality, readmissions, diagnosis, and procedure prediction). Data was collected in two different settings - during a pandemic (COVID-19) and under normal circumstances. The data contains structured (physiological characteristics, vitals, etc.) and unstructured (EHRs) information -- and we study patient flows, staff, physician, and nurse schedules and their impact on clinical outcomes (focusing primarily on length of stay) and overall healthcare scheduling. One of the datasets is proprietary, while the other is available from online sources.

The graduate student(s) who are expected to join the project will help process unstructured EHR data by careful extraction of features, performing statistical analysis, and finding how they affect the performance of the overall models for clinical outcome prediction. In particular, they will be involved with the following activities:

1. Become familiar with the overall architecture of the project, including the multimodal data collected.
2. Be familiar with Natural Language Processing techniques (including Large Language Models LLMs for Clinical Research) and use tools that are developed for processing clinical notes, EHRs, etc.
3. Will be involved in reading research papers, interpreting them, and using implementations as available from Github repositories.
4. Enthusiastically participate in brown bag sessions and group presentations.
5. Expected to work with graduate students (Master's and PhD) and undergraduate students who are involved in the project. Teamwork is highly encouraged, although some tasks will have to be accomplished individually. 
6. There will be group meetings every week to discuss project-related and unrelated issues.
7. The ideal student would work with us for at least TWO semesters (preferably more!), 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:

1. For UB students - Offer independent study/thesis credits as appropriate. 
2. For industry partners, this could be a way to participate in more rigorous, long-term, academic projects to keep abreast of state-of-the-art technology
3. 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. 
4. For external collaborators, there exist multiple opportunities for discussing how you can be involved with and contribute to our research (such as new projects and data sharing, problems that are of interest to industry, funding opportunities for new work and more!).

The projects are available immediately and are very hands-on, fast-paced, 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 several years. 

If the above is of interest, please send your resumes and a few paragraphs on why this is of interest to you and what you hope to accomplish through your participation to me (haimonti@buffalo.edu)

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

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

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