To say that this semester has flown by would be an understatement. These past few months have been a collection of zoom meetings, certification trainings, and paper presentations, but – aside from a six-week long sinus infection – have been enjoyably engaging. Starting as a newbie in the lab in August, I have now become a real asset on the projects I am working on. More importantly, however, I have been pushed to explore new areas within my field of research while also being able to apply the skills I had already developed in past academic and clinical experiences.
Perhaps my biggest challenge this semester was my introduction into the world of machine learning, an area of artificial intelligence using examples to create and hone models that then automatically analyze new data (Squarcina). I have a strong background in statistics and neuroscience, but I cannot say the same for computer science. As such, I was very nervous to begin working in a lab where many people do come from a computer science background. However, everyone was very encouraging, to the point that I felt comfortable enough to sign up to present a paper on “Alzheimer’s Disease Diagnosis via Deep Factorization Machine Models” (Ronge). If that tells you almost nothing, don’t worry, I was in the same boat. Anyway, I read the paper – googling every third word – and realized that, apart from the incredibly complicated formulas listed in the methods section, I could actually grasp what the researchers had worked on: a new and better way to analyze factors important to the identification and diagnosis of mild cognitive impairment and Alzheimer’s Disease!


I successfully presented the paper in front of about a dozen people and am now a lot less terrified about actually working with machine learning in the future. From this, I have realized the following: If you are in a team that successfully creates a supportive learning environment, you won’t be afraid to push yourself and do things you aren’t already brilliant at.
The two other big things I am currently working on are a literature review of research on the gut microbiome, aging, and mood disorders, and data collection for a new project working to improve patient experience for patients with loneliness, anxiety, and/or mild cognitive impairment. I am thoroughly enjoying it, as it is allowing me to explore concepts I am learning about in my Neuroscience classes while also engaging with patients over the phone or Zoom. In the future, I hope to pursue a Bachelor of Philosophy (BPhil) through the honors college as a way to take my research to an even higher level. I have this fellowship to thank for getting me to that point of ambition, and encourage everyone to find similar opportunities in their areas of interest.
Citations:
Ronge, Raphael, Kwangsik Nho, Christian Wachinger, and Sebastian Pölsterl. “Alzheimer’s Disease Diagnosis via Deep Factorization Machine Models.” Machine Learning in Medical Imaging, 2021, 624–33. https://doi.org/10.1007/978-3-030-87589-3_64.
Squarcina, Letizia, Filippo Maria Villa, Maria Nobile, Enrico Grisan, and Paolo Brambilla. “Deep Learning for the Prediction of Treatment Response in Depression.” Journal of Affective Disorders 281 (2021): 618–22. https://doi.org/10.1016/j.jad.2020.11.104.
One Comment Add yours