Announcing Our 2022-2023 Translational Health Data Science Fellows

DataLab is excited to announce our 2022-2023 cohort of Translational Health Data Science Fellows. This program provides advanced master’s and doctoral students with the opportunity to participate in mentored research that advances their graduate progress and contributes to the development and/or implementation of data science applications to the human health sciences. This fellowship is open to students from interdisciplinary fields ranging from computer science, engineering, social sciences, biomedicine, informatics, to public health and beyond. This 9-month fellowship program is supported by CITRIS, CTSC, and the Department of Public Health Sciences in collaboration with DataLab.

2022-2023 Fellows

Chitrabhanu Gupta, Electrical and Computer Engineering

Mentors: Dr. Chen-Nee Chuah (Electrical and Computer Engineering) and Dr. Jason Adams (Internal Medicine)

Deep learning has been very successful in predictive analytics across a number of domains, but it usually requires large volumes of data. Clinical datasets are often very small and heterogenous and thus difficult to work with in this domain. Meta-learning strategies have excelled at predictive analytics despite these small datasets. With guidance from Dr. Chen-Nee Chuah and Dr. Jason Adams, Chitrabhanu is investigating meta-learning for predictive analytics with small, heterogeneous datasets of one-dimensional medical signals.

Chitrabhanu Gupta is a PhD student in Electrical and Computer Engineering passionate about healthcare. Chitrabhanu’s research aims to mitigate common problems in clinical data science such as small datasets and access barriers to data owing to information sensitivity.

Saeedeh Komijani, Computer Science

Mentors: Dr. Julie Schweitzer (Psychiatry and Behavioral Science), Dr. Dipak Ghosal (Computer Science), and Dr. Prerona Mukherjee (Psychiatry and Behavioral Science)

Irritability is an extreme emotional reaction expressed with anger, aggression, and violence, and it is associated with social impairments and suicidality. Irritability also predicts risky behaviors such as low academic performance, substance abuse, and criminality. It is hypothesized that irritability is determined by interactions between reward/emotion and cognitive control systems. Saeedeh is working with Dr. Julie Schweitzer, Dr. Dipak Ghosal, and Dr. Prerona Mukherjee to integrate cognitive and clinical measures and machine learning techniques to investigate whether impairments in cognitive control and reward processing systems can predict irritability and sex differences.

Saeedeh Komijani is a PhD student in Computer Science at UC Davis studying statistical and machine learning approaches for complex and multimodal clinical data for children and young adults with Attention-Deficit/Hyperactive-Disorder (ADHD).

Brittany Morgan, Public Health Sciences

Mentors: Dr. Beatriz Martínez López (Veterinary Medicine), Dr. Laura Fejerman (Public Health Sciences), and Dr. Larissa May (Emergency Medicine)

Populations are the quintessential complex system. Various elements and factors (i.e., humans, animals, built and natural environments, governments, cultures, food, healthcare, education, etc.) connect and form relationships, giving rise to the larger system in which we all live: a complex system which makes studying population health problems difficult. With mentors Dr. Beatriz Martínez López, Dr. Laura Fejerman, and Dr. Larissa May, Brittany combines systems science and epidemiologic approaches to explore the systems, structures, and processes that lead to geographic inequalities in community-acquired Methicillin-resistant Staphylococcus aureus (MRSA) infections.

Brittany Morgan is a PhD Candidate in Public Health Sciences. An epidemiologist by training, she has a diverse background, but the recurrent theme of her research has been her deep desire to make a difference by addressing health disparities. She is most excited to work on research problems requiring a robust theoretical grounding and an understanding of the causal architecture shaping the health of populations. 

April Vang, Statistics

Mentors: Dr. Luis G. Carvajal-Carmona (Biochemistry and Molecular Medicine) and Dr. Laura Fejerman (Public Health Sciences)

Gastric cancer is a leading cause of cancer incidence and mortality in Latin Americans and U.S. Latinos. Each year more than one million new gastric cancer cases are diagnosed worldwide, and more than 700,000 patients succumb to this disease. There has historically been a disparity in gastric cancer research in Latinos who are diagnosed at later stages and have worse outcomes compared to Non-Latino Whites. A polygenic risk score (PRS) is an estimate of an individual’s genetic liability to having gastric cancer, calculated according to their genotype and relevant genome-wide association studies. Guided by Dr. Luis G. Carvajal-Carmona and Dr. Laura Fejerman, April applies supervised machine learning methods to variant selection and PRS modeling in hopes of increasing the understanding of gastric cancer etiology by identifying genetic risk factors and molecular-outcome associations in Latinos.

April Vang is a master’s student in Statistics at UC Davis. Her work investigates the application of disease gene mapping techniques and modeling, analysis of cancer registry data, and genetic epidemiological analysis in marginalized communities.