Hi, I'm Sam

Hi, I’m Sam.A Machine Learning Scientist focused on explainable AI and compliance automation in healthcare.
My background in computational linguistics shapes how I approach AI: through language, reasoning, and human context.
I’ve built ontology-driven models for medical text screening, compliance tools for GDPR Article 9, and AI assistants that work with, not over, domain experts.
My goal is to make AI trustworthy, auditable, and usable in real-world settings.

Research Background

MPhil, Computational Linguistics — University of Bergen (2024)• Thesis: Ontology-enhanced ML for Medical Literature Screening → reduced review time from 6 months → 1 week.• Experience mentoring graduate students and teaching technical topics.•Legal-AI startup experience (Innovation Norway–supported).
Focus areas: ontology-enhanced ML, leakage-safe evaluation, calibration, iterative human-in-the-loop reviews, and reproducible pipelines.

• Learn More

Projects

Featured Projects1. Medical Intervention Text Triage (Systematic Reviews)Reduced manual literature screening time by ~85% through ontology-augmented classifiers (SNOMED).
Outcome: Cut prescreening from ~6 months to ~1 week in pilot settings.
Approach: Started from a simple baseline, performed error analysis, and introduced targeted model complexity with a full audit trail for transparency.
Assurance: External cohort checks and reviewer-level agreement testing.
Stack: Python, scikit-learn, spaCy, SNOMED CT ontology.2. GDPR Article 9 Compliance Checker (Healthcare AI)Open-source rule engine for scanning healthcare privacy documents and DPIAs against 42 GDPR Article 9 requirements on special-category data.
Outcome: Automatically detects missing legal bases and documentation gaps.
Approach: YAML-based rule logic with evidence extraction and versioned decisions for transparency.
Assurance: Keyword-driven scoring contextualized for focused DPIAs (10–30 % typical coverage); explicit limitations documented (semantic scope, English-only).
Stack: Python, Streamlit, PyMuPDF, YAML, Pandas.3. Legal AI Analysis System (Oslo Startup)Production-grade ML system for regulatory text analysis, deployed at 25+ documents per week.
Outcome: Reduced manual review load and ensured reproducible outputs for compliance teams.
Assurance: Version-controlled models, traceable rationales, and governance hooks to meet audit standards.
Stack: Python, FastAPI, Azure AI Projects, GitHub Actions.4. Customer Analytics with Uncertainty (Selected Non-Medical)Built explainable churn prediction models with calibrated confidence intervals.
Outcome: Delivered interpretable drivers of churn and improved decision confidence in retention models.
Assurance: Leakage detection, stability testing, and calibration across time splits.
Stack: Python, scikit-learn, SHAP, XGBoost.5. Human–AI Creative Analysis (Research)Studied 1,298 prompt–image interactions in generative models to understand creative decision patterns.
Outcome: Produced reproducible methodology for prompt analysis and interpretability insights into multimodal model behavior.
Assurance: Versioned datasets and transparent evaluation scripts.
Stack: Python, Hugging Face Transformers, CLIP, Pandas.Core Tools & Methods
Programming / Data: Python, R, Bash, SQL
ML / NLP: PyTorch, Hugging Face, spaCy, scikit-learn
Regulatory / Audit: YAML-based rule engines, PyMuPDF, pdfminer
MLOps / Deployment: Streamlit, FastAPI, Azure AI Projects, GitHub Actions
Research / Reproducibility: Jupyter, Pandas, Prompt auditing, Versioned datasets

• View GitHub

Beyond the CodeOutside work, you’ll find me at a jazz jam, learning new recipes, or discussing sci-fi at book clubs.
I’ve lived in Ghana and Norway, with time in China and Europe—perspectives I bring to building globally aware, inclusive AI.
Currently learning Norwegian (and a bit of German + Japanese).

Contact

Let's Connect - Open to partnerships on explainable AI, clinical NLP, or regulatory ML.📧 [email protected]
💼 linkedin.com/in/sammens
🔗 github.com/SamInMotionInterested in production-oriented roles at the intersection of compliance, healthcare AI, and explainable ML open to relocation within the Nordics..

• Get in Touch

• Message
• Email

Built with Carrd — Content © Samuel Okoe-Mensah 2025.