Harun Y.

If you need healthcare data pipelines, analytics systems, AI-powered workflows, or biostatistical analysis, I can help you develop a reliable solution tailored to your project. I combine healthcare data engineering and biostatistics with clinical research experience demonstrated by 62 medical articles indexed in PubMed. I CAN HELP YOU WITH: Data Engineering & AI • Build and maintain production ETL/ELT pipelines • Develop and manage Apache Airflow and Google Cloud Composer workflows • Design BigQuery pipelines, SQL transformations, and analytics systems • Integrate EHR platforms, third-party APIs, and external data sources • Automate manual file transfers and system-to-system data movement • Extract structured clinical data from PDFs, scanned documents, and laboratory reports • Build controlled AI-agent workflows for healthcare data • Automate KPI dashboards and recurring reports • Develop machine-learning solutions for healthcare analytics Biostatistics & Clinical Research • Analyze clinical, observational, and survey data using Python or IBM SPSS • Prepare descriptive statistics and hypothesis tests • Perform linear and logistic regression analyses • Conduct survival analysis • Apply parametric methods, including t-tests, ANOVA, ANCOVA, MANOVA, and repeated-measures ANOVA • Apply nonparametric methods, including Mann–Whitney U, Kruskal–Wallis, Wilcoxon signed-rank, and Friedman tests • Interpret statistical findings in their clinical and scientific context • Create publication-ready tables, figures, and statistical summaries • Review statistical methods and results sections for manuscripts • Communicate findings clearly to clinicians, researchers, and nontechnical stakeholders Send me a brief description of your project. For statistical work, you may also share the research question, dataset structure, or a de-identified sample. I can provide a complimentary preliminary scope review and suggest practical solution options. If one of those approaches fits your needs, we can then discuss the implementation details. WHY WORK WITH ME? My background combines production data engineering with genuine clinical and research experience. Before moving into technology, I worked as a medical doctor and researcher who published 62 medical articles indexed in PubMed. This experience enables me to understand both the technical architecture and the real-world meaning of healthcare data. I know that a statistically correct result must also be clinically meaningful and that a technically functional system must be reliable, maintainable, and appropriate for its healthcare environment. I can work directly with medical terminology, research questions, clinical outcomes, and study documentation without requiring clients to translate the clinical context into purely technical language. Selected experience: • Built AI-assisted workflows that extract laboratory data from unstructured PDF reports and load structured results into BigQuery • Developed and maintained healthcare data pipelines integrating multiple EHR and external data sources • Optimized Google Cloud Composer workloads to improve reliability and control infrastructure costs • Developed machine-learning and anomaly-detection pipelines for IoT monitoring data • Conducted biostatistical analyses for clinical research and peer-reviewed publications Core technologies: Python, SQL, Apache Airflow, Google Cloud Composer, BigQuery, dbt, GCP, Docker, Pandas, NumPy, scikit-learn, XGBoost, LangChain, Agno, Kafka, REST APIs and IBM SPSS.