Utilizing Supervised Machine Learning Models for Opioid Hotspot Prediction

Project Title

Utilizing Supervised Machine Learning Models for Opioid Hotspot Prediction

Faculty Mentor(s)

Project Description

Project Description: 

Our research attempts to train multiple supervised machine learning models using unrestricted datasets ranging from 2012 to 2021 in order to identify the most effective predictor model for opioid overdose death rates across U.S. counties. Currently, these models demonstrate the remarkable capability to predict rates up to three years in advance, providing a valuable tool for proactive public health interventions. We are also investigating the social, economic, and demographic features influencing these outcomes, aiming to prioritize and understand their significance. The ultimate goal is to use the predictions to guide strategic decision-making in the investment and allocation of public health services, particularly in hotspot counties, to proactively prevent future risk.

Why is your research important?

Our research holds significance in attempting to identify most affected hotspots by the opioid overdose rate through the application of machine learning models. The prediction of these models is aimed to guide the distribution of public health services strategically, minimizing the risk of future health crises. Concurrently, our research seeks to elevate public awareness and advocate for policy changes, particularly in addressing health crises.
 

What does the process of doing your research look like?

My research process was comprehensive, involving coding in the R language and an extensive review of literature from previous studies to gain a deeper insight into ongoing research in the field. Additionally, I dedicated considerable time to self-study. Weekly meetings with my mentor were critical for addressing questions and issues, and setting goals for consistent growth.

What knowledge has your research contributed to your field?

Our research findings highlight that among the models we trained, the random forest exhibited the best performance given the available data. The results also indicate that population, employee capacity, and annual payroll are some of the most significant socio-economic factors influencing the outcomes. This knowledge enhances our understanding of the complex dynamics associated with the subject matter.
 

In what ways have you showcased your research thus far?

I built an interactive R Shiny web page to showcase our research findings and presented the outcomes to a diverse audience, fostering discussion and knowledge dissemination.
 

How did you get involved in research? What drove you to seek out research experiences in college?

As a STRONG (Science and Technology Research Opportunities for a New Generation) scholar, I had the opportunity to be paired with my research mentor. My decision to engage in his research was driven by a keen interest in delving deeper into the fundamentals of data science and ML (machine learning). Importantly, I wanted to explore ML potential in preventing future risks and making a substantial impact across various fields.
 

What is your favorite aspect of the research process?

My favorite aspect of the research process lies in its ability to create a supportive network of individuals eager to assist in your learning journey. Engaging in research not only opens opportunities for cooperation, but it also highlights the interconnectedness of our study findings, serving as guiding lights for future discoveries.
 

How has working with your mentor impacted the development of your research project? How has it impacted you as a researcher?

Collaborating with my mentor has been crucial in developing my research journey, providing critical resources and assistance that are essential for its growth. His encouragement to develop inquiry, raise questions, and seek assistance as needed has created a supportive environment conducive to productive research.
 

How has the research you’ve conducted contributed to your professional or academic development?  

Professionally, my research has significantly helped to narrow down my specific interests in the field of machine learning and provided valuable insight into navigating a research environment. Academically, it let me build technical skills and a goal-setting strategy.
 

What advice would you give to a younger student wanting to get involved in research in your field?

Build a foundational understanding of the research concepts from the ground up. Contributing meaningfully to research is highly facilitated by a thorough comprehension of its fundamentals. Don't hesitate to inquire about the "whys" and "hows" in your research. Stay Curious!