Yashwanth Ravipati

About Me 🧍🏽

Self Portrait

Hey there! Thanks so much for stopping by my page. I’m a sophomore at Harvard studying Computer Science & Economics, and I’m passionate about AI, machine learning, statistics, and global health.

I grew up just outside Chicago, in Long Grove, Illinois, and went to Adlai E. Stevenson High School. Between tennis matches, running a small shoe-resale venture, geeking out over aviation, and building Swift apps, I quickly fell in love with engineering, emerging technologies, sports, and investing.

After mustering up the courage to send a cold email, a professor welcomed me to Boston for my high school summers, where I worked on AI tools to streamline clinical workflows at Mass General Brigham. Those projects have moved into real surgical pathways, and I’ve been grateful to publish and present my work in awesome journals, from JAMA and Nature Communications to the IEEE and AMIA conferences.

Back in Cambridge, I split my time between campus research and the Harvard Business School. At HBS, I’m building analytics tools to unpack private-equity subscription lines and deal structures, helping researchers understand how leverage shapes macroeconomic trends.

Beyond the lab and code, I’m involved with the Behavioral Strategy Group, collaborating with Fortune 500 companies on product strategy and personalization—and even leading our recruiting efforts to bring on great analysts. I’m also part of Harvard Undergraduate Capital Partners, where I conduct due diligence for VCs scouting emerging talent.

Technical Contributions 💻

AI in Medicine (AIM) Lab
Mass General Brigham, Harvard Medical School — Undergraduate Researcher (May 2022 – Present)

  • Researched novel computational methods to accelerate the application of AI in clinical practice alongside a team of physicians, residents, and AI/ML PhDs & Post-docs.
  • Developed longitudinal foundation models for brain MRI images to precisely model tumor growth over time, identifying prognostic markers and informing therapeutic pathways.
  • Designed and developed a fully automated deep learning platform for sarcopenia assessment and survival outcome analysis using imaging biomarkers in head and neck cancer patients; currently undergoing clinical trials.
  • Extended the automated platform to temporalis muscle quantification for studying growth trajectories in children and assessing prognostic value in pediatric glioblastoma treatment.
  • Evaluated deep learning frameworks—including 3D U-Net, M-Net, nnU-Net (2D & 3D), and Swin Transformer—for tumor and lymph node auto-segmentation in PET/CT datasets.
  • Published in JAMA Network Open, Nature Communications, Springer Nature Lecture Notes in Computer Science; presented posters at ASTRO 2023 & 2024 conferences.

Medical & Imaging Informatics
UCLA Department of Medical and Imaging Informatics — Student Researcher (Dec 2021 – Jan 2024)

  • Developed novel ML algorithms and evaluated state-of-the-art deep-learning architectures for EEG signal processing in BCIs to restore communication in patients with brainstem injuries.
  • Conducted studies to detect Freezing of Gait in Parkinson’s patients from EEG motor imagery data with high accuracy.
  • Presented oral talks at the AMIA 2023 Annual Symposium and the 11th IEEE-EMBS Neural Engineering Conference.

Harvard Business School
Boston, MA — Research Assistant (Jan 2025 – Present)

  • Focused on trends in private equity subscription lines: analyzed 20+ years of deal structure and valuation data to assess macroeconomic impacts of increased lending leverage and technology sector trends.
  • Produced code for data analysis & developed financial models for capital deployment strategies and scenario planning, reducing analysis time by 50% for HBS research workflows.

Side Projects 👨🏽‍💻

Publications 📖

First/Co-first Authored

Co-authored

Links 🔗