Data scientist with a background in biostatistics, healthcare research, and open-source software development. I build analytical pipelines and statistical tools for complex, multi-site data problems in clinical and neuroimaging contexts.
I am the creator and maintainer of neuroHarmonize, a Python toolkit for harmonizing neuroimaging datasets across scanners and sites using ComBat-based methods. The package has been adopted by hundreds of researchers worldwide and has accumulated 500+ citations. Selected publications that use or extend this work:
- Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan, NeuroImage (first author)
- Disentangling Alzheimer's disease neurodegeneration from typical brain ageing using machine learning, Brain Communications
- MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14,468 individuals worldwide, Brain
- The Brain Chart of Aging: machine-learning analytics reveals links between brain aging, white matter disease, amyloid burden, and cognition, Alzheimer's & Dementia
Most recently, I've been a data scientist at the University of Pittsburgh / Children's Hospital of Pittsburgh, where I served as lead biostatistician for a CDC-sponsored surveillance study tracking respiratory viruses in pediatric populations. Before that, I completed my MS in Biostatistics at the University of Colorado–Denver, co-authoring 10+ manuscripts and developing statistical methods for clinical and epidemiological research across pulmonary, transplant, and critical care medicine.
Earlier in my career, I was a data analyst at the University of Pennsylvania School of Medicine, working in the Davatzikos Lab on multi-center MRI harmonization and ML-based biomarkers of neurodegeneration. That work on ComBat harmonization for neuroimaging became neuroHarmonize.
Full publication list: ncbi.nlm.nih.gov/myncbi/raymond.pomponio.1