🔍 As a dedicated Data Scientist, I combine healthcare expertise with advanced data science skills. My journey began during my medical training, where I earned my MD and became a board-certified Anesthesiologist. This phase of my career involved providing patient care in the ICU and operating room, as well as actively engaging in clinical research, which led to significant contributions to peer-reviewed publications in the medical field.
📊 Transitioning into data science, I applied my strong analytical skills and attention to detail. I completed extensive formal training in data science and gained hands-on experience across diverse projects, focusing on the collection, analysis, and interpretation of complex datasets to derive actionable insights. This blend of rigorous training and practical experience has equipped me to tackle real-world data challenges with precision and innovation.
💡 I am passionate about harnessing the power of data to uncover insights and inform decisions. With a solid foundation in research methodology and a data-driven approach, I am committed to leveraging my expertise to transform patient care and tackle challenges across various industries.
🌐 Feel free to connect with me here or on LinkedIn, or explore my GitHub repository for a deeper look at my work and projects.
- Programming Languages: Python, R, SQL: (MySQL, PostgreSQL, SQL Server)
- R Libraries: Tidyverse, ggplot2, igraph, statnet, rsiena
- Data Analysis Libraries: NumPy, Pandas, SciPy
- Visualization Tools: Tableau, Matplotlib, Plotly, Seaborn
- Statistical Analysis: Power analysis, Effect sizes, Multivariate analysis, Predictive modeling techniques (e.g., ANOVA, regression), Social network analysis, Meta-analysis
- Machine Learning Frameworks: TensorFlow, Scikit-learn, XGBoost, PyTorch
- Big Data Technologies: AWS, Hadoop, Spark, Hive, Docker
Data Scientist | Automated Detection of Traumatic Injuries in CT SCAN
Nov 2023
- Developed a Convolutional Neural Network (CNN) using PyTorch for detecting and classifying traumatic abdominal injuries in CT scans, addressing a critical challenge in emergency medicine for prompt diagnosis.
- Applied to a diverse dataset from the RSNA Abdominal Trauma Detection Challenge, encompassing various cases of blunt force abdominal trauma.
- Achieved high model accuracy in classifying injuries in abdominal organs, with notable results including 98.57% for bowel injury and over 90% for various states of liver and kidney damage.
Feel free to reach out to me via LinkedIn or email.
“Data!data!data!" he cried impatiently. "I can't make bricks without clay.” ― Arthur Conan Doyle, The Adventure of the Copper Beeches - a Sherlock short story