Meysam Ahangaran

Education:
B.S. in Computer Engineering (Software) from Sharif University of Technology
M.S. in Computer Engineering (Artificial Intelligence) from Sharif University of
Technology
Ph.D. in Computer Engineering (Artificial Intelligence and Robotics) from Iran University of Science and Technology (IUST)
From 2022 to 2025, I served as a Postdoctoral Associate in the Computational Biomedicine Research Group within the Department of Computing and Data Sciences at Boston University. My research focuses on applying Artificial Intelligence, including Machine Learning, Deep Learning, and Large Language Models, to analyze multimodal medical data such as imaging, voice recordings, clinical records, and neuropsychological assessments. My key contributions include:

1) Deep Learning Framework for Differential Dementia Diagnosis: conducted comprehensive statistical analyses of findings derived from a multimodal deep learning model tailored to perform differential diagnosis of dementia and published the results in Nature Medicine (https://doi.org/10.1038/s41591-024-03118-z)

2) Privacy-Preserving Voice-Based Cognitive Assessment: developed a computational framework that balances speaker de-identification and cognitive integrity in cognitive assessments. The project was conducted in collaboration with Boston University and Massachusetts Institute of Technology (MIT), with funding from the Gates Ventures Foundation. Published as the findings in Alzheimer’s & Dementia (https://doi.org/10.1002/alz.70032)

3) Framework to Address Data Readiness in Machine Learning (DREAMER): developed a Python-based computational framework (DREAMER) designed to facilitate automated assessment of data readiness for machine learning applications and published the results in BMC Medical Informatics and Decision Making (https://doi.org/10.1186/s12911-024-02544-w)

4) Deep Learning for Kidney Biopsy Images Assessment: implemented deep learning framework leveraging the fine-tuned Meta-SAM model for real-time quantitative assessment of kidney biopsy adequacy from smartphone-captured images and published the findings in Kidney International Reports (https://doi.org/10.1016/j.ekir.2024.06.019)