DefinePK

Abstract

This project introduces a framework for appropriately adapting and adjusting machine learning (ML) techniques used to construct electrocardiogram (ECG)-based schemes. With more qualified training data given to corresponding machine learning schemes, the precision on ML-based ECG mechanisms are increased in consequence. In the proposed framework four new measure metrics are introduced to evaluate the quality of the ML training and testing data, all proposed mechanisms, metrics, and sample data with demonstrations using various ML techniques, is developed. For developing ML based ECG. The system uses retrieval-augmented generation (RAG) to provide a lightweight LLM with relevant cardiology knowledge at inference time, enabling it to diagnose cardiac conditions from ECG data without task-specific training. We extend the original methodology by deploying a small, open-source LLM (Versatile--Llama 3B) locally using the Ollama platform, ensuring patient data never leaves the premises. The proposed system aims to replicate these benefits in a secure environment. We detail the existing solutions, the proposed architecture, its advantages in privacy and cost, system requirements, and a comprehensive methodology. The outcome is an on-premise ECG diagnostic assistant that leverages both the efficiency of a small LLM and the accuracy of domain-specific retrieval, demonstrating a feasible path toward AI-assisted cardiac diagnosis without compromising data security