Search Articles

View query in Help articles search

Search Results (1 to 4 of 4 Results)

Download search results: CSV END BibTex RIS


Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study

Moving Biosurveillance Beyond Coded Data Using AI for Symptom Detection From Physician Notes: Retrospective Cohort Study

We sought to validate and test an open-source artificial intelligence (AI)–based NLP pipeline that includes a large language model (LLM) to detect COVID-19 symptoms from physician notes. As a formative use case, we sought to illustrate how this pipeline could detect COVID-19 symptoms and differentiate symptom patterns across SARS-Co V-2 variant eras in pediatric patients. We specifically study patients presenting to the emergency department (ED) who can be sentinel cases in an outbreak.

Andrew J McMurry, Amy R Zipursky, Alon Geva, Karen L Olson, James R Jones, Vladimir Ignatov, Timothy A Miller, Kenneth D Mandl

J Med Internet Res 2024;26:e53367

The Journey of Data Within a Global Data Sharing Initiative: A Federated 3-Layer Data Analysis Pipeline to Scale Up Multiple Sclerosis Research

The Journey of Data Within a Global Data Sharing Initiative: A Federated 3-Layer Data Analysis Pipeline to Scale Up Multiple Sclerosis Research

Furthermore, the initiative set a methodological standard in global health research by introducing a data analysis pipeline with applications beyond MS. This paper delves deep into GDSI’s comprehensive RWD analysis pipeline, offering an end-to-end approach that spans from introducing a data dictionary to meticulous data acquisition, and ultimately, to deriving insightful clinical interpretations.

Ashkan Pirmani, Edward De Brouwer, Lotte Geys, Tina Parciak, Yves Moreau, Liesbet M Peeters

JMIR Med Inform 2023;11:e48030

Using a Secure, Continually Updating, Web Source Processing Pipeline to Support the Real-Time Data Synthesis and Analysis of Scientific Literature: Development and Validation Study

Using a Secure, Continually Updating, Web Source Processing Pipeline to Support the Real-Time Data Synthesis and Analysis of Scientific Literature: Development and Validation Study

These components were comprised of a real-time data extraction pipeline that was implemented by using Mirror Web’s digital archiving technology, a data lake storage repository and workflow orchestration platform (Amorphic) that was developed by Cloudwick, a natural language search engine that was implemented by using Amazon Kendra, and a document curation pathway that was implemented by using Amazon Sage Maker Ground Truth.

Uddhav Vaghela, Simon Rabinowicz, Paris Bratsos, Guy Martin, Epameinondas Fritzilas, Sheraz Markar, Sanjay Purkayastha, Karl Stringer, Harshdeep Singh, Charlie Llewellyn, Debabrata Dutta, Jonathan M Clarke, Matthew Howard, PanSurg REDASA Curators, Ovidiu Serban, James Kinross

J Med Internet Res 2021;23(5):e25714

Developing a Reproducible Microbiome Data Analysis Pipeline Using the Amazon Web Services Cloud for a Cancer Research Group: Proof-of-Concept Study

Developing a Reproducible Microbiome Data Analysis Pipeline Using the Amazon Web Services Cloud for a Cancer Research Group: Proof-of-Concept Study

A reliable and validated microbiome data analysis pipeline operating through the AWS cloud could be used to provide a consistent communication platform for research collaborators to share information on data processing, data analysis, and research findings. Thus, the AWS pipeline could increase both the reproducibility of microbiome studies and the proficiency of the research team [22].

Jinbing Bai, Ileen Jhaney, Jessica Wells

JMIR Med Inform 2019;7(4):e14667