/med
The medical thread.
I formally studied Medicine before moving fully into machine learning, and I've kept medical sciences as a serious intellectual interest. That background still shapes how I think about biomedical AI, diagnostics, and useful health systems.
This page is where that thread lives, separate from the engineering work but never far from it.
What I keep coming back to
- Clinical decision support that respects the way clinicians actually reason, not just dashboards.
- Variant interpretation for rare disease, building on the work I did at Mendelics for Brazil's national newborn screening program.
- Protein language models as a substrate for downstream variant and drug-design tasks.
- Health systems that scale to public-health reality, not just demos.
- ADHD & mental health screening: practical tooling like adhd-screening.org.
Currently
MSc in Health Informatics at Karolinska Institutet, Stockholm. Thesis topic still in flux; happy to talk to anyone working at the seam between ML and clinical care.
Selected work along this line
- Suicide Mortality among Indigenous Peoples in Brazil, 2010-24: A Nationwide Registry-Based Study, SSRN preprint; poster at CBP 2026.
- Prediction of Gain or Loss of Function in Missense Variants, SBSI 2025.
- Graph neural networks as a potential tool in improving virtual screening programs, Frontiers in Chemistry, 2022.
- Mendelics: SOTA variant prediction in production for "Teste da Bochechinha"; SARS-CoV-2 pipeline for Instituto Butantan.
- MIT CSAIL: protein language models for variant prediction and drug-design retrieval.
Reading list / influences
Notes on books, papers, and people that shape how I think about this space, coming soon.
If any of this overlaps with what you're working on, write to maricatovictor [at] gmail.com.