Anand Subramanian

Digging into the details behind the prompting framework Anand Subramanian · Follow Published in Towards Data Science · 13 min read · 21 hours ago — Illustration of the various components of the Medprompt Strategy (Image taken from Fig:6 from the Medprompt paper [1] (https://arxiv.org/abs/2311.16452) In my first blog post, I explored prompting and its significance in the context of Large Language Models (LLMs). Prompting is crucial for obtaining high-quality outputs from LLMs, as it

Building automated clinical coding systems with LLMs Anand Subramanian · Follow Published in Towards Data Science · 16 min read · 3 hours ago — Clinical coding isn’t common parlance, but it significantly impacts everyone who interacts with the healthcare system in most countries. Clinical coding involves translating and mapping medical information from patient health records, such as diagnoses and procedures, into standardized numeric or alphanumeric codes. These codes are crucial for billing, healthcare analytics,

How can an LLM be applied effectively for biomedical entity linking? Anand Subramanian · Follow Published in Towards Data Science · 26 min read · 3 hours ago — Photo by Alina Grubnyak on Unsplash Biomedical text is a catch-all term that broadly encompasses documents such as research articles, clinical trial reports, and patient records, serving as rich repositories of information about various biological, medical, and scientific concepts. Research papers in the biomedical field present