ScolAI is a machine learning pipeline designed to automate the measurement of the Cobb angle, a key metric for diagnosing scoliosis. Manual Cobb angle measurements are time-intensive and prone to variability between clinicians, which can affect treatment decisions. Our approach uses AP X-rays from scoliosis patients and implements two main strategies: hip segmentation as a proxy task and direct angle regression. The segmentation model is built on a U-Net architecture, while the regression task leverages ConvNeXT, Swin Transformer, and ResNet-50 to predict Cobb angles from spinal X-rays. Our models demonstrate low error rates and strong generalization, setting the stage for future deployment on labeled spinal datasets. ScolAI holds promise for streamlining clinical workflows and improving consistency in scoliosis care.

India faces major healthcare access challenges, especially in rural areas with limited doctors and long travel times. Telemedicine bridges this gap, but current clinical history-taking at the community level is inefficient—CHWs often collect lengthy, unfocused histories before connecting with hub doctors. Our project leverages AI and Large Language Models (LLMs) to create an adaptive, efficient history-taking tool that guides CHWs to ask relevant questions based on patient responses. This system reduces consultation time, improves information quality, and helps doctors make quicker, more accurate decisions. We are developing and optimizing this tool using agent-based simulations and prompt engineering, and will evaluate its performance with both expert clinical reviewers and in a real-world pilot in rural Nashik, India. This innovation aims to enhance care quality, reduce delays, and ultimately scale across India’s public telemedicine ecosystem, including eSanjeevani.

In this project, we further developed our robust leader-follower protocol which autonomously coordinates a group, or swarm, of devices. The system is designed to seamlessly adapt to devices dropping out of the swarm unexpectedly and to any new devices joining the network. We focused on two main tasks this year: formal verification of the protocol and developing a demonstration with mobile robots. The formal verification proved that our protocol satisfies both safety and adaptability requirements.

At Design Day, we will have an interactive simulation, which shows how our protocol can coordinate up to 50 robots. We will also present a video of our robot demonstration, which uses five TurboPi robots as devices which autonomously work to each perform a task within different quadrants of a large grid.

DnATA is a DNA-based data storage platform designed to address the growing need for sustainable and durable data archiving. Our system uses a computational pipeline to convert digital files into DNA sequences, which are then stored and replicated inside bacterial cells. Leveraging natural bacterial replication reduces reliance on energy-intensive, short-lived conventional storage devices. By combining principles from synthetic biology, DnATA explores a novel biological approach to long-term archival data storage. While still in early stages, our work demonstrates the feasibility of encoding, storing, and retrieving digital information from cells, thereby opening new possibilities for secure, low-maintenance archival solutions.