Ó³»­´«Ã½

Valentina D’souza is a machine learning engineer at the Ó³»­´«Ã½, working with the Machine Learning for Health (ML4H) team. D’souza's work focuses on leveraging machine learning techniques to analyze complex biomedical data, including real-world sensor data such as Fitbit records, to drive advancements in disease prediction and risk stratification. She is particularly interested in applying large language models to interpret unstructured medical data, further enhancing the predictive power of computational models in healthcare. 

D’souza holds a master’s degree in biomedical engineering with a focus on data science from Johns Hopkins University, where her research focused on accelerating parameter quantification for CEST (chemical exchange saturation transfer) MRI images using machine learning. She also holds a bachelor’s degree in biomedical engineering from The University of Mumbai, India.