Automated readings of imaging reports by natural language processing (NLP) supplemented by clinical data predict disease course in children and adults with Crohn's disease: report from the epi-IIRN.

Ohad Atia^1,2,3, Gili Kurtser¹, Gili Focht¹, Elad Sinai¹, Amir Ben-Tov^2,4, Galia Zacay^2,5, Eran Matz⁶, Shir Zekaria⁷, Haggai Bar-Yoseph⁸, Zvi Badash⁹, Naama Gavrielov⁹, Iris Dotan^2,10, Talar Hagopian^1,11, Ruth Cytter-Kuint^1,11, Moti Freiman⁹, Dan Turner^1,11

¹Shaare Zedek Medical Center, Jerusalem, Israel.

²Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel.

³Schneider- Children's Medical Center.

⁴Maccabi Research an Innovation Center Maccabi Healthcare Services.

⁵Meuhedet Health Services.

⁶Leumit Health Services, Tel Aviv, Israel.

⁷Clalit Health Services, Clalit Research Institute Tel Aviv, Israel.

⁸Department of Gastroenterology, Rambam Health Care Campus & Bruce Rappaport School of Medicine.

⁹Technion Israel Institute of Technology, Haifa, Israel.

¹⁰Division of Gastroenterology, Rabin Medical Center, Petah Tikva, Israel.

¹¹The Hebrew University of Jerusalem, Israel.

PubMed DOI

Abstract

INTRODUCTION: The implementation of imaging features in administrative databases and electronic health records is limited by non-standardized free-text radiology reports. We developed a natural language processing (NLP) tool to automatically extract imaging-based variables from radiological reports and integrate them with clinical data to predict disease course in children and adults with Crohn's…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.