Artificial intelligence-driven structurization of diagnostic information in free-text pathology reports

Pericles S Giannaris; Zainab Al-Taie; Mikhail Kovalenko; Nattapon Thanintorn; Olha Kholod; Yulia Innokenteva; Emily Coberly; Shellaine Frazier; Katsiarina Laziuk; Mihail Popescu; Chi-Ren Shyu; Dong Xu; Richard D Hammer; Dmitriy Shin

doi:10.4103/jpi.jpi_30_19

ORIGINAL ARTICLE

Year : 2020 | Volume : 11 | Issue : 1 | Page : 4

Artificial intelligence-driven structurization of diagnostic information in free-text pathology reports

Pericles S Giannaris¹, Zainab Al-Taie², Mikhail Kovalenko¹, Nattapon Thanintorn³, Olha Kholod¹, Yulia Innokenteva⁴, Emily Coberly³, Shellaine Frazier³, Katsiarina Laziuk³, Mihail Popescu⁵, Chi-Ren Shyu⁶, Dong Xu⁷, Richard D Hammer⁸, Dmitriy Shin⁹
¹ Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211; Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, Columbia, MO 65212, United States
² Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, United States; Department of Computer Science, College of Science for Women, University of Baghdad, Baghdad, Iraq
³ Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, Columbia, MO 65212, United States
⁴ Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, United States
⁵ Department of Health Management and Informatics, School of Medicine, University of Missouri, Columbia, MO 65212; Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211; Department of Electrical Engineering and Computer Science, College of Engineering, University of Missouri, Columbia, MO 65211, United States
⁶ Institute for Data Science and Informatics; Department of Electrical Engineering and Computer Science, College of Engineering, University of Missouri, Columbia, MO 65211, United States
⁷ Department of Electrical Engineering and Computer Science, College of Engineering; Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, United States
⁸ Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, Columbia, MO 65212; Institute for Data Science and Informatics, University of Missouri, Columbia, MO 65211, United States
⁹ Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, Columbia, MO 65212; Institute for Data Science and Informatics; Department of Electrical Engineering and Computer Science, College of Engineering, University of Missouri, Columbia, MO 65211, United States

Correspondence Address:
Dr. Dmitriy Shin
Department of Pathology and Anatomical Sciences, School of Medicine, University of Missouri, Columbia, MO 65212
United States

Source of Support: None, Conflict of Interest: None

Check

DOI: 10.4103/jpi.jpi_30_19

Background: Free-text sections of pathology reports contain the most important information from a diagnostic standpoint. However, this information is largely underutilized for computer-based analytics. The vast majority of NLP-based methods lack a capacity to accurately extract complex diagnostic entities and relationships among them as well as to provide an adequate knowledge representation for downstream data-mining applications. Methods: In this paper, we introduce a novel informatics pipeline that extends open information extraction (openIE) techniques with artificial intelligence (AI) based modeling to extract and transform complex diagnostic entities and relationships among them into Knowledge Graphs (KGs) of relational triples (RTs). Results: Evaluation studies have demonstrated that the pipeline's output significantly differs from a random process. The semantic similarity with original reports is high (Mean Weighted Overlap of 0.83). The precision and recall of extracted RTs based on experts' assessment were 0.925 and 0.841 respectively (P <0.0001). Inter-rater agreement was significant at 93.6% and inter-rated reliability was 81.8%. Conclusion: The results demonstrated important properties of the pipeline such as high accuracy, minimality and adequate knowledge representation. Therefore, we conclude that the pipeline can be used in various downstream data-mining applications to assist diagnostic medicine.

[FULL TEXT] [PDF]*

Table of Contents

Similar in PUBMED

Search Pubmed for

Search in Google Scholar for

Related articles

Citation Manager

Access Statistics

Reader Comments

Email Alert *

Add to My List *

* Requires registration (Free)

Article Access Statistics

Viewed	1914

Printed	28

Emailed	0

PDF Downloaded	284

Comments	[Add]