DreamNLP: Novel NLP System for Clinical Report Metadata Extraction using Count Sketch Data Streaming Algorithm: Preliminary Results

TL;DR

DreamNLP introduces a memory-efficient data streaming algorithm to extract key clinical report terms from large EHR datasets, aiding downstream medical analysis and machine learning applications.

Contribution

It presents a novel application of the Count Sketch algorithm for efficient term extraction in clinical reports, reducing computational resources needed.

Findings

Successfully identified important breast diagnosis features from EHRs

Demonstrated low-memory, scalable term extraction method

Potential to enhance machine learning in precision medicine

Abstract

Extracting information from electronic health records (EHR) is a challenging task since it requires prior knowledge of the reports and some natural language processing algorithm (NLP). With the growing number of EHR implementations, such knowledge is increasingly challenging to obtain in an efficient manner. We address this challenge by proposing a novel methodology to analyze large sets of EHRs using a modified Count Sketch data streaming algorithm termed DreamNLP. By using DreamNLP, we generate a dictionary of frequently occurring terms or heavy hitters in the EHRs using low computational memory compared to conventional counting approach other NLP programs use. We demonstrate the extraction of the most important breast diagnosis features from the EHRs in a set of patients that underwent breast imaging. Based on the analysis, extraction of these terms would be useful for defining important features for downstream tasks such as machine learning for precision medicine.