Natural language processing in diagnostic texts from nephropathology

• Verfasst von: Legnar, Maximilian [VerfasserIn]
• Verfasst von: Daumke, Philipp [VerfasserIn]
• Verfasst von: Hesser, Jürgen [VerfasserIn]
• Verfasst von: Porubsky, Stefan [VerfasserIn]
• Verfasst von: Popovic, Zoran V. [VerfasserIn]
• Verfasst von: Bindzus, Jan Niklas [VerfasserIn]
• Verfasst von: Siemoneit, Jörn-Helge [VerfasserIn]
• Verfasst von: Weis, Cleo-Aron Thias [VerfasserIn]
• Titel: Natural language processing in diagnostic texts from nephropathology
• Verf.angabe: Maximilian Legnar, Philipp Daumke, Jürgen Hesser, Stefan Porubsky, Zoran Popovic, Jan Niklas Bindzus, Joern-Helge Heinrich Siemoneit and Cleo-Aron Weis
• E-Jahr: 2022
• Jahr: 15 July 2022
• Umfang: 25 S.
• Fussnoten: Dieser Artikel gehört zum Special issue: Artificial Intelligence in pathological image analysis ; Gesehen am 05.12.2023
• Titel Quelle: Enthalten in: Diagnostics
• Ort Quelle: Basel : MDPI, 2011
• Jahr Quelle: 2022
• Band/Heft Quelle: 12(2022), 7, Artikel-ID 1726, Seite 1-25
• ISSN Quelle: 2075-4418
• DOI: doi:10.3390/diagnostics12071726
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: BERT
• Sach-SW: deep learning
• Sach-SW: machine learning
• Sach-SW: nephropathology
• Sach-SW: NLP
• Sach-SW: text analysis
• Sach-SW: text classification
• Sach-SW: topic modelling
• Sach-SW: transformer encoder
• K10plus-PPN: 187192023X

Abstract

Introduction: This study investigates whether it is possible to predict a final diagnosis based on a written nephropathological description—as a surrogate for image analysis—using various NLP methods. Methods: For this work, 1107 unlabelled nephropathological reports were included. (i) First, after separating each report into its microscopic description and diagnosis section, the diagnosis sections were clustered unsupervised to less than 20 diagnostic groups using different clustering techniques. (ii) Second, different text classification methods were used to predict the diagnostic group based on the microscopic description section. Results: The best clustering results (i) could be achieved with HDBSCAN, using BoW-based feature extraction methods. Based on keywords, these clusters can be mapped to certain diagnostic groups. A transformer encoder-based approach as well as an SVM worked best regarding diagnosis prediction based on the histomorphological description (ii). Certain diagnosis groups reached F1-scores of up to 0.892 while others achieved weak classification metrics. Conclusion: While textual morphological description alone enables retrieving the correct diagnosis for some entities, it does not work sufficiently for other entities. This is in accordance with a previous image analysis study on glomerular change patterns, where some diagnoses are associated with one pattern, but for others, there exists a complex pattern combination.