Photo by NeONBRAND on Unsplash

A few months ago, our lab (the BIG IDEAS lab at Duke) launched the dbdpED (Digital Biomarker Discovery – Education) initiative that aims to provide anyone with the tools to get started with digital biomarker discovery. With the help of GradEngage I have been working to expand the initiative to increase access to and awareness around digital biomarker research. To start it off, I have set up a virtual workshop with high school students at North Carolina School of Science and Math (NCSSM) in Durham where I will give them a glimpse into digital biomarker research. To organize the workshops, I have been working with Dr. Letitia Hubbard, who is currently teaching a bioinstrumentation course at NCSSM for high school students. Interestingly, Dr. Hubbard received her Ph.D in Biomedical Engineering from Duke University, where she was James B. Duke Scholar, a National Science Foundation Fellow, and a UNCF/Merck Graduate fellow. Her research focus at Duke was to study arrhythmias in the heart using computational models. It has been really great connecting with her and working with her closely to get insights on how to best structure the workshop.

My workshop aims to introduce students to wearable devices, the kind of data obtained from them, and how that data can be used. The real challenge has been framing it as a story as I take them through the process of wearable data analysis to make it all the more engaging. How can I make the analysis more relatable? How can I explain a concept in a way that is easy to understand? How do I structure the workshop to make it more riveting and pique the students’ interests? These are just some of the questions that have cropped up in my mind since I set out designing the workshop.

With this workshop and the subsequent ones, I aim to generate awareness around the field of digital biomarkers at an early age in students. I aim to give them insights into how wearables work and what can digital biomarker discovery help with. Digital biomarkers have never held more importance than they do now in the current difficult times. The COVID-19 pandemic, has underscored the need for timely detection of infection especially outside of clinical settings, to avoid further straining healthcare resources. Multiple studies have demonstrated that there are changes in physiological and behavioral parameters measured by smartwatches, including high resting heart rate (HR), decreased blood oxygen saturation, disturbed sleep, decreased physical activity, and changes in wear habits, that can indicate when the body is fighting off an infection, and before the onset of obvious symptoms. Using wearables like activity trackers for continuous COVID-19 management can nudge individuals towards a proactive, data-empowered, and personal-responsibility driven approach for COVID-19 infection management.

Confucius once said “I hear and I forget. I see and I remember. I do and I understand.” To ensure the students get the most out of this workshop, they will be working with the data themselves! I will be distributing modular codes and sample data to the students to encourage true exploration and better understanding. I will systematically take the students through multiple steps involved in wearable data analysis for digital biomarker discovery. Data from wearables can be exported into common file formats and loaded into software applications like google colab and jupyter notebooks for analysis. Once the data is loaded, it needs to be pre-processed to clean it up in preparation for further analysis. Data pre-processing can involve multiple steps depending on the data and analysis goals. I will introduce students to several of these steps and help them easily understand their purpose and utility. Exploratory Data Analysis is usually the next step where you can generate some insightful and easy to understand figures from your data. As the name suggests, it is aimed at exploring your data before delving into the analysis. This can help establish trends in your data and help you better understand your data.

We will then generate some cool visualizations from wearables data and look at the multiple ways the same data can be visualized depending on context. Along with all this, I also want to convey the challenges that accompany digital biomarker research, one of the most important ones being privacy concerns.

The process of putting together a lesson plan has been enlightening for how I can effectively communicate my research. I have realized it’s as much art as it is science. While some of the analysis I will use for the workshop comes from my own research, it has been really interesting trying to think of the different ways I can convey the same information depending on the audience and the different contexts it can be used in. With this initiative, I hope to make some young minds curious about this research area and maybe even inspire some of them to pursue a career in the field of digital biomarker research.