01 About
I study applied math on the pre-med track at Columbia, and have a large background in computer science. My research is focused on applied deep learning for medicine, notably in the neurodegenerative sector. I'm very interested in using AI to describe the heterogeneity of these diseases, which allows better diagnosis and treatment, and strengthens clinical trials.
I spent a year at the Laboratory of AI & Biomedical Science working on why Alzheimer's presents so differently between patients, using diffusion models to pull apart subtypes that a single diagnosis hides. I now work at the Goate lab at Icahn School of Medicine at Mount Sinai.
Lately, most of my time has been spent building Specht Labs, an early-stage deep tech startup where I serve as CTO. We are building the first Large Algorithmic Model. Check us out at spechtlabs.ai.
I grew up in Belgium, was born in Boulder, and moved to New York in 2025 for Columbia. I speak English and French natively, and a fun fact is that I have 4 passports.
02 Research
Circuits, Blocks, and Galois Groups in Structural Identifiability
2026Computes the input–output relations of rational ODE models as circuit polynomials of an algebraic matroid, without differential elimination, and studies the Galois group that permutes the parameter values a model cannot tell apart.
With Sanay Sehgal · Specht Labs · Differential algebra · Algebraic matroids · Galois theory
To what extent can science explore consciousness after clinical death?
2026A literature review of near-death experiences. Weighs the neuroscientific explanations (residual cortical activity, EEG surges before death, integrated information and global workspace theories) and the speculative Orch-OR hypothesis, and concludes that none yet accounts for every reported observation.
Literature review · Neuroscience · Consciousness · Translated from French
03 Selected projects
Disease Heterogeneity Using Diffusion
2026Identifying biologically distinct subtypes of Alzheimer's disease from multimodal neuroimaging and genetic data. Extends the Smile-GAN / Surreal-GAN / Gene-SGAN line of work with diffusion-based generative models for more stable subtype clustering.
PyTorch · Diffusion models · Multimodal neuroimaging · CUIMC
Clearchart
2026Rewrites discharge summaries, labs and radiology reports at a chosen reading level, and checks every number in the output against the source document.
React · LLM API · Prompt evaluation
Eye Age Clock
2026Predicts biological age by extracting microstructural biomarkers from retinal OCT images — the retina being the one place you can inspect neural tissue and microvasculature without cutting anything open.
PyTorch · Deep learning regression · Retinal OCT
MRI Tumor Classifier
2025Detects brain tumours from MRI at 91% accuracy, and 96% with a ResNet-18 add-on. Normalisation, augmentation and regularisation throughout, to keep the thing honest on scans it has never seen.
PyTorch · ResNet-18 · AdamW · Data augmentation
Autism Classifier
2025Classifies autism spectrum disorder from responses to a standardised questionnaire. Built alongside a speech-language pathologist, so the output stays interpretable to the clinician who has to use it.
Python · scikit-learn · pandas
Online Poker Java Game
2025Five-card draw video poker: full hand evaluation, betting and credit state, built as a desktop app in Java Swing.
Java · Swing · OOP
Works in Python · PyTorch · TensorFlow · scikit-learn · NumPy · Pandas · Diffusion models · CNNs · Java · C++ · SQL · Git · Docker · GCP
04 Experience
Co-Founder · Chief Technology Officer
Specht Labs · New York
Building the first Large Algorithmic Model (LAM). I lead the core algorithmic work and the engine; the proof of concept is in bioprocessing and biomanufacturing. Pilots with 10 research groups, among them Harvard, USC and Cornell. Our first model, Noether 1.0, releases early November.
Machine Learning Researcher
Icahn School of Medicine at Mount Sinai · Goate Lab
Research under PI Alison M. Goate.
Machine Learning Researcher
Columbia University Irving Medical Center · Laboratory of AI & Biomedical Science
Machine learning at the edge of neurodegenerative disease — finding biologically distinct subtypes of Alzheimer's in multimodal neuroimaging and genetic data. I designed loss functions for clustering, disentanglement and latent priors.
B.S. Applied Mathematics, Pre-Medical Track
Columbia University · New York
Rajasekharan Family Undergraduate Scholarship. Engineers Without Borders and Formula SAE on the side. Phi Gamma Delta fraternity.
Co-Founder · Head of IT & Marketing
FlyHigh Enterprise · Belgium
Turned decommissioned hot-air balloon tarps into consumer products. Roughly $13,000 in revenue, a slice of it to nonprofit partners, national press coverage, and second place out of 475 in the Belgian entrepreneurship competition.
Research Internships
TU Delft / QuTech · SONACA Aerospace · Université libre de Bruxelles
Microwave-to-optical quantum transducers at Quantum Delta NL. Aircraft and space structures at SONACA. Quantum optics and computational modelling in R and MATLAB at ULB.
Head of the European People's Party
Model European Parliament · Kerkrade, Netherlands
Main submitter on position papers, and led the European Parliament's largest party through the 2024 convention. Two Best Delegation awards.
Head of Delegation
THIMUN Foundation · The Hague, Netherlands
Main submitter on 2025 convention position papers.
Head of Research
European Youth Ambassadors · Wavre
Promoted awareness of the EU's role through schoolwide initiatives. Organised a fundraiser for the Restos du Cœur, raising over €2,000.
05 Honors & awards
- Rajasekharan Family Undergraduate ScholarshipColumbia Engineering
- Duke of Edinburgh International AwardDuke of Edinburgh
- National Entrepreneurship Competition — 2nd of 475LJE Mini-Entreprise
- Wallonia Entrepreneurship AwardWallonie Entreprendre
- Best Delegation, Model European Parliament ×2AFNORTH International School
06 Music
Fourteen years at the piano.
I've played piano since the age of five, and my favorite composer is Chopin. I've studied many of his études for competitions, my favorites being Op. 10 No. 12 and Op. 10 No. 4. I've also played the Fantaisie-Impromptu, Op. 25 No. 11, and La Campanella. I'm currently working on a few compositions and Liszt's Hungarian Rhapsody No. 2.
More performances →07 Reach out
If any of this looks interesting, please reach out by email.
© 2026 Davi Klitz · built in New York · last updated October 2026 ·