BHAVYA RANI A S

Seasoned IT professional with 12+ years of experience, starting as a QA specialist with expertise in manual and automation testing of web, client/server, mobile applications, and standalone medical healthcare devices. Proficient in developing automated testing frameworks, performance testing, and risk management. Transitioned into Data Science, Machine Learning, and MLOps through successful POCs in previous organizations, demonstrating hands-on experience in predictive analytics, regression, classification, and statistical analysis using Python and SQL. Recently completed PG Diploma from IIIT Bangalore and MS in AI/ML from Liverpool John Moores University, UK. Known for critical thinking, problem-solving, and driving continuous improvement initiatives.

• Certified course on Managerial Skills enhancement from personal mastery.
• Python and Selenium Automation testing course from Besant technologies.
• Java and Selenium Automation testing course from Besant technologies.
• Manual Testing Course and QTP course from Qspiders.
• A Six months' course from NIIT that includes Web Component Development using Java Technologies - Java, J2EE, Programming languages - C, C++, Introduction to Oracle 9i-SQL (Oracle Work Force Development Program).

1. Project: AI-Powered Anomaly Detection for Patient Monitor Data (GE HEALTHCARE):Developed an AI-based model at GE Healthcare that analyzes real-time patient monitoring data such as heart rate, ECG, SpO2, etc., to detect anomalies indicating early warning signs of critical health conditions. The solution leveraged unsupervised learning techniques (e.g., clustering, Isolation Forest) and supervised classification models to identify abnormal patterns in patient vitals, enabling timely alerts to healthcare professionals for proactive interventions.

2. Project: AI-Powered Adverse Event Detection from Drug Reports(GENPACT):Designed and implemented an AI model to analyze pharmacovigilance reports (e.g., FDA Adverse Event Reporting System - FAERS) for detecting potential adverse drug reactions (ADRs). Utilized Natural Language Processing (NLP) techniques to extract key entities (drug names, reactions, patient demographics) from unstructured text data and applied machine learning classification models to identify patterns indicative of adverse events. The system aimed to support pharmacovigilance teams in early detection of safety signals, improving drug safety monitoring and regulatory compliance.

3.Project: AI-Powered Patient Health Risk Prediction for Home Hospital Applications(BIOFOURMIS):Developed and deployed an AI/ML model to predict patient health risk levels within Home Hospital applications. The model analyzed real-time vital signs (heart rate, blood pressure, oxygen saturation, etc.) combined with patients' historical health records to assess the likelihood of health deterioration. This proactive system enabled healthcare providers to identify at-risk patients early, facilitating timely interventions and improving patient outcomes.