Adam L
- Research Program Mentor
PhD at Johns Hopkins University
Expertise
Epilepsy, computational neuroscience, machine learning and causal inference
Bio
Currently, I am a Postdoctoral Research Scientist at Columbia University in the Causal Artificial Intelligence Lab, directed by Dr. Elias Bareinboim. I am an NSF-funded Computing Innovation Research Fellow. I did my PhD in biomedical engineering, specializing in computational neuroscience and machine learning at Johns Hopkins University. I worked with Dr. Sridevi V. Sarma in the Neuromedical Control Systems group. I also jointly obtained a MS in Applied Mathematics and Statistics with a focus in statistical learning theory, optimization and matrix analysis. I was fortunate to be a NSF-GRFP fellow, Whitaker International Fellow, Chateaubriand Fellow and ARCS Chapter Scholar during my time at JHU. My PhD thesis work focused on developing algorithms for seizure localization in drug-resistant epilepsy patients. My interest in engineering and medicine started at UCSD, where I graduated in 2015 with a double major in Bioengineering and Mathematics. It was there under the guidance of many great faculty, such as Dr. Todd Coleman, that I became interested in applied mathematics, data analytics and machine learning in healthcare. It led me to pursue a PhD, with the ultimate goal of bringing together technology expertise with biomedical domain knowledge to solve challenging medical problems. My research interests are broadly in the intersection areas of neuroscience, statistical machine learning, causal inference, control theory and dynamical systems. I am also extremely passionate about open-source everything. I'm originally from Los Angeles, CA and consider myself a true CA native even though I wasn't born there. I have a range of hobbies, including, but not limited to: running, gymming (weight lifting), reading, hacking, traveling and photography.Project ideas
Epilepsy and its genetic components
Epilepsy is a disease characterized by consistent seizures seen as chaotic brain electrical waves. A literature review of its genetic components and how it relates to the electrical manifestation as seen by the brain waves would be valuable. There are known genetic risk factors. In addition, gene expression measured by RNA transcription can vary based on varying types of epilepsy. These different components are all genetic variations of how epilepsy manifests. In addition, there are varying presentations of epilepsy in terms of what type of brain waves are seen, where in the brain the epilepsy is believed to originate from, and also what structural abnormalities there might be.
Causality vs correlation - A basic tutorial on causal inference for the public
Causality is the desire of many scientific disciplines. Correlations are easier to analyze typically, but are not equivalent to causation. This is exemplified in the following phrase: "correlation does not imply causation". Causality is typically measured in medicine, policy and science via a randomized control trial, where something is randomized and then its effect on something else is measured. For example, randomizing who gets a COVID-19 vaccine and comparing people with vaccines vs without will determine the causal effect of the vaccine on preventing COVID. Modern causal inference allows one to encode causality as a graph, represented by nodes and edges in a pictorial representation. This enables scientists, policy makers and leaders to not only encode their causal assumptions for a specific problem, but also provide general algorithms for determine if someone can determine a causal effect from purely observations. A break down of graphical notions of causality in laymen terms would be useful for education at the high school and undergraduate level. Successful completion of this project could go on to inspire and educate people on causal inference. A successful project would take the basics of causal inference and break it down into a paper and/or series of short posts that introduce the topics.