Healthc Inform Res.  2022 Jul;28(3):276-283. 10.4258/hir.2022.28.3.276.

Text Mining of Biomedical Articles Using the Konstanz Information Miner (KNIME) Platform: Hemolytic Uremic Syndrome as a Case Study

• Dorr RA
• Casal JJ
• Toriano R

• KMID: 2532455
• DOI: http://doi.org/10.4258/hir.2022.28.3.276

Abstract

Objectives
Automated systems for information extraction are becoming very useful due to the enormous scale of the existing literature and the increasing number of scientific articles published worldwide in the field of medicine. We aimed to develop an accessible method using the open-source platform KNIME to perform text mining (TM) on indexed publications. Material from scientific publications in the field of life sciences was obtained and integrated by mining information on hemolytic uremic syndrome (HUS) as a case study.
Methods
Text retrieved from Europe PubMed Central (PMC) was processed using specific KNIME nodes. The results were presented in the form of tables or graphical representations. Data could also be compared with those from other sources.
Results
By applying TM to the scientific literature on HUS as a case study, and by selecting various fields from scientific articles, it was possible to obtain a list of individual authors of publications, build bags of words and study their frequency and temporal use, discriminate topics (HUS vs. atypical HUS) in an unsupervised manner, and cross-reference information with a list of FDA-approved drugs.
Conclusions
Following the instructions in the tutorial, researchers without programming skills can successfully perform TM on the indexed scientific literature. This methodology, using KNIME, could become a useful tool for performing statistics, analyzing behaviors, following trends, and making forecast related to medical issues. The advantages of TM using KNIME include enabling the integration of scientific information, helping to carry out reviews, and optimizing the management of resources dedicated to basic and clinical research.

Keyword

Data Mining; Information Storage and Retrieval; Tutorial; Hemolytic Uremic Syndrome; Bibliography

Figure

• 

  Figure 1 Example of starting a workflow. (A) From the KNIME File menu, select “Install KNIME Extensions.” (B) To select the required text mining extension (KNIME Textprocessing), “text” can be typed in the text box. Similarly, the Vernalis KNIME Nodes and KNIME Indexing and Searching extensions must be installed. (C) The workflow starts with a search on the European PubMed Central (ePMC) site. Specific query terms should be typed in the General Query text box. In our example, the query terms were (“Haemolytic uraemic syndrome” OR “Hemolytic uremic syndrome”), corresponding to two different spellings for the same clinical syndrome. The years of publication were limited to 2020–2021. The Test Query button is used to check the number of hits. The node returns an XML document. (D) The XPath node allows selecting the fields of interest (see Column Name) from the XML document. (E) All the fields are indexed with the Table Indexer node. (F) The Index Query node creates a filtered data table, which is the input corpus for the following nodes. In the figure, only the articles published in 2020 are selected. Configuration windows C, D, E, and F are opened with a double left click on the node icon (blue arrow).

• 

  Figure 2 Example for obtaining a list of authors. The authorString table lists the authors signing the publication after running the Index Query node. All authors of a publication are in the same row (see entry detail). The transposition performed with the Transpose node and the splitting of a cell into its constituent components (Cell Splitter node) are used to obtain the individual list of authors (see output detail). The results of a node action can be viewed by opening a window with a right click on the node icon (green arrow). The orange arrow indicates a brief node description.

• 

  Figure 3 Example of automated and unsupervised detection of topics in abstracts about hemolytic uremic syndrome (HUS) and quantification of their characteristic words. The example shows the topics detected in publications on hemolytic uremic syndrome from 2020 to 2021 inclusive. A proposed text preprocessing method that facilitates subsequent analysis is also exemplified, eliminating characters and words without semantic importance, grouping by lemmatization and labeling the tokens. The result of topic detection (fork 1) is shown in tabular form but could also be presented in another graphical form. The word cloud (result of fork 2) represents the most abundant words in a bag of words; the larger its size, the higher its frequency of use. Words in a topic have the same color. Green arrow: output with right click, Orange arrow: brief node description.

• 

  Figure 4 Workflow with cross-referencing. The input table (see details at the top) contains the terms to be identified in the corpus by means of the Cross Joiner node. Unrecognized terms are excluded by applying a filter in the Row Filter node. The output shows the number of times that each FDA-approved drug was found in abstracts (see details at the bottom). Green arrow: output with right click, Orange arrow: brief node description, FDA: Food and Drug Administration.

Reference

References

1. Renganathan V. Text mining in biomedical domain with emphasis on document clustering. Healthc Inform Res. 2017; 23(3):141–6. https://doi.org/10.4258/hir.2017.23.3.141.

2. Tshitoyan V, Dagdelen J, Weston L, Dunn A, Rong Z, Kononova O, et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature. 2019; 571(7763):95–8. https://doi.org/10.1038/s41586-019-1335-8.

3. Viceconti M, Hunter P. The virtual physiological human: ten years after. Annu Rev Biomed Eng. 2016; 18:103–23. https://doi.org/10.1146/annurev-bioeng-110915-114742.

4. Hotho A, Nurnberger A, Paaß G. A brief survey of text mining. LDV Forum. 2005; 20(1):19–62.

5. Dorr RA, Casal JJ, Toriano R. Minería de texto en publicaciones científicas con autores argentinos [Text mining in scientific publications with Argentine authors]. Medicina (B Aires). 2021; 81(2):214–23.

6. Dorr RA, Silberstein C, Ibarra C, Toriano R. Obtaining new information on hemolytic uremic syndrome by text mining. Medicina (B Aires). 2022; 82(4):513–24. PMID: 35904906.

7. Jokiranta TS. HUS and atypical HUS. Blood. 2017; 129(21):2847–56. https://doi.org/10.1182/blood-2016-11-709865.

8. Exeni RA, Fernandez-Brando RJ, Santiago AP, Fiorentino GA, Exeni AM, Ramos MV, et al. Pathogenic role of inflammatory response during Shiga toxin-associated hemolytic uremic syndrome (HUS). Pediatr Nephrol. 2018; 33(11):2057–71. https://doi.org/10.1007/s00467-017-3876-0.

9. Newman D, Asuncion A, Smyth P, Welling M. Distributed algorithms for topic models. J Mach Learn Res. 2009; 10:1801–28.

10. Yao L, Mimno D, McCallum A. Efficient methods for topic model inference on streaming document collections. In : Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2009 Jun 28–Jul 1; Paris, France. p. 937–46. https://doi.org/10.1145/1557019.1557121.

11. Qundus JA, Peikert S, Paschke A. AI supported topic modeling using KNIME-workflows [Internet]. Ithaca (NY): arXiv.org;2021. [cited at 2022 May 2]. Available from: https://arxiv.org/abs/2104.09428.

12. Patel S, Patel A, Patel M, Shah U, Patel M, Solanki N, et al. Review and analysis of massively registered clinical trials of COVID-19 using the text mining approach. Rev Recent Clin Trials. 2021; 16(3):242–57. https://doi.org/10.2174/1574887115666201202110919.

13. Ordenes FV, Silipo R. Machine learning for marketing on the KNIME Hub: the development of a live repository for marketing applications. J Bus Res. 2021; 137:393–410. https://doi.org/10.1016/j.jbusres.2021.08.036.

14. Feltrin L. KNIME an open source solution for predictive analytics in the geosciences [software and data sets]. IEEE Geosci Remote Sens Mag. 2015; 3(4):28–38. https://doi.org/10.1109/MGRS.2015.2496160.

15. Vijayan R. Teaching and learning during the COVID-19 pandemic: a topic modeling study. Educ Sci. 2021; 11(7):347. https://doi.org/10.3390/educsci11070347.