Current Graduates from ASU at IntelSTATS

• Mehriban Aghagulova

Bio: Mehriban is a graduate student in the Bio-Data Science program at Arizona State University, with a background in Neuroscience, Medical Microbiology, and Business. Research experience has been gained in neurodegenerative disease, clinical research, and data analysis, including work on Parkinson’s disease mechanisms and breast cancer care workflows. At the Mostafa Lab, he is working on developing multimodal deep learning approaches for Alzheimer’s disease dementia assessment. His interests are centered on applying computational and data science approaches to biological data to better understand disease and contribute to biomedical research.

• Mary Jane Lindner

Mary Jane  is a graduate student in the Biological Data Science program at Arizona State University. She is working on single cell mRNA, and making Deep Learning model to discover biomarker genes. 

• Melissa Scott-Preusse

Bio: Melissa (Mel) Scott-Preusse is a graduate student in the Bio-Data Science program at Arizona State University and a Research Assistant IV in the Owen Laboratory at Cincinnati Children’s Hospital Medical Center. Her research combines developmental biology, computational genomics, and retinal disease, with special interest in developing quantitative approaches to understand vascular phenotypes. Her current graduate research project, DeepVessels, focuses on developing and validating a deep-learning pipeline for robust segmentation and quantitative analysis of retinal vasculature. 

• Mohsina Jannat

Bio: Mohsina Jannat is in Bio Data Science grduate program at Arizona State University, where she conducts research on deep learning approaches for diabetic retinopathy detection under the supervision of Dr. Fahad Mostafa. Her work focuses on AI-driven retinal image analysis, including diabetic retinopathy severity grading, lesion segmentation, and uncertainty quantification. She develops and evaluates EfficientNetB1- and U-Net–based models using the APTOS and IDRiD datasets and applies Monte Carlo dropout to identify uncertain predictions that may require expert review. Her broader research interests include interpretable and uncertainty-aware AI methods for medical imaging, with the goal of advancing reliable automated screening tools for retinal disease. Mohsina holds a B.Sc. in Agriculture and an M.S. in Agronomy from Bangladesh Agricultural University

• Jenika Maala

Bio: Jenika Maala is currently a graduate student pursuing a Master’s in Bio Data Science at Arizona State University, with a strong interest in investigating machine learning in healthcare research. Her background as a Clinical Research Coordinator working on pediatric neuro-oncology clinical trials inspired me to explore how data science can improve disease detection and clinical decision-making, working at Stanford Medicine. Her current research focuses on Alzheimer’s disease, specifically investigating which patient characteristics are associated with high-confidence versus low-confidence false-positive predictions in machine-learning models. By examining demographic and clinical factors, she hopes to better understand why certain patients are incorrectly classified as having Alzheimer’s disease. Through this project, she aims to identify potential sources of misclassification, improve model reliability, and contribute to the development of more accurate and interpretable predictive tools.

• Radiya Imran

Bio: Radiya Imran is an aspiring PhD student in biostatistics who earned her BS and MS degrees in Statistics from Arizona State University. She recently joined Dr. Mostafa’s lab as a researcher, where she contributes to a project on machine learning for cardiovascular disease risk assessment. The project combines predictive modeling, uncertainty quantification, and explainable AI to examine heart disease risk factors and differences between male and female patients, with the goal of making predictions more reliable and interpretable.

Recent Graduates from ASU IntelSTATS  Lab

• Arthur Yu, Thesis title: "Interpretable Bootstrap Weighted Oblique Random Forests for Multiclass Classification with Application to Biomedical Data" (2026)

• Catalina Amurrio Zamora, Thesis title: "Cross-Tissue Cellular Responses on a Dehydrated Placenta-Derived Extracellular Matrix Scaffold Revealed by Quantitative Imaging and Unsupervised Clustering" (2026)

• Nosizo Lukhele, "Enhancing Early Detection and Risk Stratification of Diabetes Using Explainable Machine Learning Approaches" (2026)

• Kushagra Sharma, "Early Dementia Diagnosis in Older Adults through Machine Learning: A Cross-Sectional fMRI Data Analysis" (2025)