Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am a Data Scientist with a solid background in biomedical science and specialized expertise in machine learning and natural language processing. I've developed end-to-end ML pipelines using Python and R, utilizing models like XGBoost and PubMedBERT to tackle healthcare challenges effectively. I have a talent for communicating complex technical findings through interactive dashboards and deploying scalable models on AWS. I am passionate about transforming complex biomedical data into actionable insights that can drive healthcare improvements. I enjoy collaborating across disciplines to build interpretable and reproducible ML pipelines and look forward to leveraging my skills to make a substantial impact in healthcare data science.…I am a Data Scientist with a solid background in biomedical science and specialized expertise in machine learning and natural language processing. I've developed end-to-end ML pipelines using Python and R, utilizing models like XGBoost and PubMedBERT to tackle healthcare challenges effectively. I have a talent for communicating complex technical findings through interactive dashboards and deploying scalable models on AWS. I am passionate about transforming complex biomedical data into actionable insights that can drive healthcare improvements. I enjoy collaborating across disciplines to build interpretable and reproducible ML pipelines and look forward to leveraging my skills to make a substantial impact in healthcare data science.

Hala Arar





I am a Data Scientist with a solid background in biomedical science and specialized expertise in machine learning and natural language processing. I've developed end-to-end ML pipelines using Python and R, utilizing models like XGBoost and PubMedBERT to tackle healthcare challenges effectively. I have a talent for communicating complex technical findings through interactive dashboards and deploying scalable models on AWS. I am passionate about transforming complex biomedical data into actionable insights that can drive healthcare improvements. I enjoy collaborating across disciplines to build interpretable and reproducible ML pipelines and look forward to leveraging my skills to make a substantial impact in healthcare data science.…I am a Data Scientist with a solid background in biomedical science and specialized expertise in machine learning and natural language processing. I've developed end-to-end ML pipelines using Python and R, utilizing models like XGBoost and PubMedBERT to tackle healthcare challenges effectively. I have a talent for communicating complex technical findings through interactive dashboards and deploying scalable models on AWS. I am passionate about transforming complex biomedical data into actionable insights that can drive healthcare improvements. I enjoy collaborating across disciplines to build interpretable and reproducible ML pipelines and look forward to leveraging my skills to make a substantial impact in healthcare data science.

Available to hire

I am a Data Scientist with a solid background in biomedical science and specialized expertise in machine learning and natural language processing. I’ve developed end-to-end ML pipelines using Python and R, utilizing models like XGBoost and PubMedBERT to tackle healthcare challenges effectively. I have a talent for communicating complex technical findings through interactive dashboards and deploying scalable models on AWS.

I am passionate about transforming complex biomedical data into actionable insights that can drive healthcare improvements. I enjoy collaborating across disciplines to build interpretable and reproducible ML pipelines and look forward to leveraging my skills to make a substantial impact in healthcare data science.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Work Experience

Data Scientist/Research Assistant – AI Driven Genomic Classification at University of British Columbia

July 1, 2025 - Present

Designed XGBoost and adversarial large language models to classify gene variants from structured patient data, improving classification consistency across variant types. Engineered features aligned with ACMG guidelines and collaborated with geneticists to build interpretable, reproducible machine learning pipelines for clinical deployment.

Data Scientist – Capstone Project at University of Helsinki

May 1, 2025 - Present

Built and fine-tuned a PubMedBERT NLP model to classify 2 million biomedical abstracts into 10 protein function categories, increasing indirect mechanism detection by 70% and achieving an 88% F1-score. Co-developed an R Shiny app for interactive visualization and interpretation of results, which reduced researcher review time and improved interdisciplinary communication.