As an integral part of the team, I contribute to the development of a versatile data platform tailored for Real-World Data (RWD). Leveraging a robust IT stack including Databricks, AWS, PySpark, Terraform, and GitLab, my work focuses on designing systems that efficiently process and ingest diverse file formats, including DICOM. This platform serves as a vital resource for data scientists and machine learning engineers, enabling them to access and analyze high-quality data across various domains. My contributions are crucial in enhancing data analytics capabilities and supporting the advancement of data-driven decision-making in healthcare and beyond. 🚀

As the Data Manager for Real-world Research Networks, I am proud to have been responsible for streamlining the biobank data quality through effective data cleaning and preprocessing techniques in Python. 🐍 This led to enhanced data integrity and actionable insights for decision-making, enabling us to make better use of our Real-World Data (RWD) and derive meaningful insights from it.Managing the end-to-end MRI image pipeline workflow, from data ingestion to publication, has been a challenging yet rewarding experience. I've worked tirelessly to ensure seamless data processing and analysis for timely results, implementing rigorous quality control measures to maintain data integrity throughout the entire process. 💻My expertise in Python, SQL, AWS, and Databricks has been instrumental in developing and maintaining robust Python scripts that optimize, automate, and enhance various aspects of the MRI image pipeline. This has significantly improved the efficiency of our workflows, enabling us to derive even more value from our RWD.Conducting comprehensive data analysis and visualization has enabled stakeholders to better understand complex data sets and make informed decisions based on accurate and complete biobank data. 📊 This has been a rewarding experience, and I'm proud to have played a role in contributing to the reliability and accuracy of insights derived from the data.

As a Computational Biologist / Data Scientist / Postdoctoral Scholar, I'm thrilled to have had the opportunity to work on in-depth analysis and interpretation of whole genome sequencing (WGS) data from cancer samples. 🧬 This involved employing custom-built genome analysis software to unveil the impact of genetic variations on disease development, which was incredibly rewarding.Using my expertise in data science techniques, I was able to manage, integrate, and mine vast omics datasets from various cancer types, facilitating the understanding of molecular landscapes in tumors and identifying key similarities and differences among them. This led to a better comprehension of the testing scale at UAB, and I'm proud to have contributed to this effort. 🙌I also executed a comparative analysis of tumor and normal RNA sequencing (RNA-Seq) data in cancer cases, utilizing custom-built pipelines to pinpoint molecular variations associated with disease development. Applying differential gene expression and transcriptome analysis to cancer cases using comprehensive total and small RNA-Seq studies, along with custom-built pipelines, helped to enhance tumor classification and advance the understanding of disease progression. This included the identification of variant accumulation and the impact of tumor progression drivers. 🔬It's been an incredible journey, and I'm grateful to have had the opportunity to contribute to the field of computational biology and data science. I look forward to continuing to explore new and exciting ways to apply these techniques in the fight against cancer.

As a Computational and Statistical Modeling of Hospital Big Data / Postdoctoral Scholar, I had the pleasure of working with de-identified hospital Big Data from medical data warehouses (MDW) within the Pathology department, enhancing data-driven decision-making and patient outcomes. 📈Streamlining EMR data processing was a key aspect of my role, and I used my expertise in R to expertly clean, preprocess, transform, and remove duplicate records. This helped to ensure that the data we were working with was accurate and reliable, which was crucial to the success of our analyses.Utilizing visualization libraries such as igraph, ggnet2, and visNetwork allowed me to generate insightful graph networks and uncover valuable patterns within the data. This helped us to identify areas for improvement and develop new strategies for improving patient outcomes. 🔍Spearheading sample collection, identification, reporting, treatment, and patient quality metrics was another important aspect of my role. By ensuring that we had accurate and comprehensive data for further analysis and research, we were able to make significant strides in our understanding of hospital Big Data and its potential impact on patient care.Finally, I evaluated and measured the impact of quality improvement measures within the hospital, contributing to potential nationwide improvements in healthcare standards and patient care. This was a rewarding experience, and I'm proud to have played a role in advancing the field of computational and statistical modeling of hospital Big Data. 🏥

I taught classes in Applied Thermodynamics and Programming Techniques.

As a Medical Informatics Analyst at the A.C. Camargo Cancer Center in Sao Paulo, I played a crucial role in the development of the "Recruit" software, which streamlined clinical trial recruitment processes through the use of ontologies. 🚀 This resulted in improved patient matching and trial efficiency, which was a significant accomplishment and helped to ensure that patients received the best possible care.In addition to my work on the Recruit software, I provided essential support for the Biobank's in-house software. This critical system manages the registration and requests for tumor samples, facilitating seamless research operations. My contributions to this system helped to ensure that the Biobank was able to operate at peak efficiency, providing researchers with the data and samples they needed to make important strides in the fight against cancer.Collaborating with researchers to identify suitable patients for clinical trials was another important aspect of my role. Leveraging EHR data and other data sources, I helped to establish a robust patient-finding pipeline that significantly accelerated the trial recruitment process. This was an exciting and rewarding experience, and I'm proud to have played a role in helping to bring potentially life-saving treatments to patients in need. 💪