A ModelOps-based Framework for Intelligent Medical Knowledge Extraction

TL;DR

This paper introduces a ModelOps-based framework that automates and simplifies medical knowledge extraction from healthcare texts, making it accessible for researchers and non-AI experts like doctors.

Contribution

It presents a low-code, reusable system for medical knowledge extraction that includes dataset abstraction, model management, and a dataset similarity-based model recommendation method.

Findings

Enhanced model development efficiency

Simplified model access for non-AI users

Effective model recommendation based on dataset similarity

Abstract

Extracting medical knowledge from healthcare texts enhances downstream tasks like medical knowledge graph construction and clinical decision-making. However, the construction and application of knowledge extraction models lack automation, reusability and unified management, leading to inefficiencies for researchers and high barriers for non-AI experts such as doctors, to utilize knowledge extraction. To address these issues, we propose a ModelOps-based intelligent medical knowledge extraction framework that offers a low-code system for model selection, training, evaluation and optimization. Specifically, the framework includes a dataset abstraction mechanism based on multi-layer callback functions, a reusable model training, monitoring and management mechanism. We also propose a model recommendation method based on dataset similarity, which helps users quickly find potentially suitable models for a given dataset. Our framework provides convenience for researchers to develop models and simplifies model access for non-AI experts such as doctors.