Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Prediction of Metastasis in Paragangliomas and Pheochromocytomas Using Machine Learning Models: Explainability Challenges.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read Online Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE
    • Publication Information:
      Original Publication: Basel, Switzerland : MDPI, c2000-
    • Subject Terms:
      Pheochromocytoma*/pathology ; Pheochromocytoma*/diagnosis ; Machine Learning* ; Paraganglioma*/pathology ; Paraganglioma*/diagnosis ; Adrenal Gland Neoplasms*/pathology ; Adrenal Gland Neoplasms*/diagnosis; Humans ; Algorithms ; Data Mining ; Neoplasm Metastasis
    • Abstract:
      One of the main issues with paragangliomas and pheochromocytomas is that these tumors have up to a 20% rate of metastatic disease, which cannot be reliably predicted. While machine learning models hold great promise for enhancing predictive accuracy, their often opaque nature limits trust and adoption in critical fields such as healthcare. Understanding the factors driving predictions is essential not only for validating their reliability but also for enabling their integration into clinical decision-making. In this paper, we propose an architecture that combines data mining, machine learning, and explainability techniques to improve predictions of metastatic disease in these types of cancer and enhance trust in the models. A wide variety of algorithms have been applied for the development of predictive models, with a focus on interpreting their outputs to support clinical insights. Our methodology involves a comprehensive preprocessing phase to prepare the data, followed by the application of classification algorithms. Explainability techniques were integrated to provide insights into the key factors driving predictions. Additionally, a feature selection process was performed to identify the most influential variables and explore how their inclusion affects model performance. The best-performing algorithm, Random Forest, achieved an accuracy of 96.3%, precision of 96.5%, and AUC of 0.963, among other metrics, combining strong predictive capability with explainability that fosters trust in clinical applications.
    • References:
      BMC Proc. 2014 Oct 13;8(Suppl 6 Proceedings of the Great Lakes Bioinformatics Confer):S2. (PMID: 25374611)
      Cancers (Basel). 2022 Jan 25;14(3):. (PMID: 35158861)
      Front Endocrinol (Lausanne). 2023 Mar 22;14:1137456. (PMID: 37033265)
      Am J Surg Pathol. 2002 May;26(5):551-66. (PMID: 11979086)
      Biomed Pharmacother. 2023 Nov;167:115500. (PMID: 37734265)
      Nat Rev Genet. 2009 Jan;10(1):57-63. (PMID: 19015660)
      N Engl J Med. 2019 Aug 8;381(6):552-565. (PMID: 31390501)
      Cell. 2000 Jan 7;100(1):57-70. (PMID: 10647931)
      Sci Rep. 2023 Jun 2;13(1):8984. (PMID: 37268685)
      Eur J Cancer. 2012 Jul;48(11):1739-49. (PMID: 22036874)
      Eur J Clin Invest. 2011 Oct;41(10):1121-8. (PMID: 21692797)
      Surgery. 2018 Sep;164(3):511-517. (PMID: 29929757)
      Am J Surg Pathol. 2009 Apr;33(4):599-608. (PMID: 19145205)
      PLoS One. 2024 Jun 13;19(6):e0305035. (PMID: 38870229)
      Lancet Digit Health. 2023 Sep;5(9):e551-e559. (PMID: 37474439)
      J Clin Endocrinol Metab. 2011 Mar;96(3):717-25. (PMID: 21190975)
      Entropy (Basel). 2020 Dec 25;23(1):. (PMID: 33375658)
      Ann Clin Biochem. 2013 Mar;50(Pt 2):147-55. (PMID: 23512172)
      Cancers (Basel). 2019 Feb 15;11(2):. (PMID: 30769931)
      Nat Rev Clin Oncol. 2019 Nov;16(11):703-715. (PMID: 31399699)
      Nat Rev Endocrinol. 2024 Mar;20(3):168-184. (PMID: 38097671)
      J Clin Endocrinol Metab. 2017 Apr 01;102(4):1122-1132. (PMID: 28324046)
      Life (Basel). 2021 Nov 04;11(11):. (PMID: 34833055)
      Stud Health Technol Inform. 2020 Jun 16;270:307-311. (PMID: 32570396)
      Endocr Relat Cancer. 2014 May 06;21(3):405-14. (PMID: 24521857)
      J Clin Endocrinol Metab. 2006 Nov;91(11):4505-9. (PMID: 16912137)
      Artif Intell Med. 2023 Sep;143:102616. (PMID: 37673561)
      J Endocr Soc. 2022 Jul 03;6(9):bvac105. (PMID: 35919261)
    • Contributed Indexing:
      Keywords: classification; data science; explainability; feature selection; machine learning; metastasis; tumor
    • Publication Date:
      Date Created: 20250712 Date Completed: 20250712 Latest Revision: 20250716
    • Publication Date:
      20250717
    • Accession Number:
      PMC12252517
    • Accession Number:
      10.3390/s25134184
    • Accession Number:
      40648440