Satwik P.

• Designed and deployed ML models using Python, TensorFlow, and Scikit-learn to predict early onset of chronic diseases from EHR, lab results, imaging scans, and demographics, improving accuracy by 21%. • Developed data ingestion pipelines using Apache Airflow and AWS Glue to process large-scale healthcare datasets, including DICOM imaging files from EMR/EHR systems, ensuring HIPAA compliance. • Engineered data preprocessing workflows in Pandas, PySpark, and OpenCV to enhance model training efficiency and reduce processing time by 35%. • Implemented NLP algorithms in SpaCy & Hugging Face Transformers to extract clinical entities and medical terminologies from physician notes, integrating results into the predictive model pipeline. • Developed and trained CNN-based deep learning models for automated medical image classification, leveraging transfer learning techniques to improve diagnosis accuracy and reduce radiologist review time. • Deployed trained ML models as RESTful APIs using Flask & Docker on AWS SageMaker, enabling real-time predictions and image-based diagnostics for clinical decision support systems. • Created interactive dashboards in Power BI to visualize patient risk scores, imaging analysis results, KPIs, and model performance metrics for stakeholders and healthcare providers. • Collaborated with data scientists, clinicians, and compliance teams to ensure model transparency, bias mitigation, and alignment with FDA & HIPAA guidelines for AI in healthcare.