Predicting Long-term Survival After Allogeneic Hematopoietic Cell Transplantation in Patients With Hematologic Malignancies: Machine Learning-Based Model Development and Validation.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: JMIR Publications Country of Publication: Canada NLM ID: 101645109 Publication Model: Electronic Cited Medium: Print ISSN: 2291-9694 (Print) NLM ISO Abbreviation: JMIR Med Inform Subsets: PubMed not MEDLINE
    • Publication Information:
      Original Publication: Toronto : JMIR Publications, [2013]-
    • Abstract:
      Background: Scoring systems developed for predicting survival after allogeneic hematopoietic cell transplantation (HCT) show suboptimal prediction power, and various factors affect posttransplantation outcomes.
      Objective: A prediction model using a machine learning-based algorithm can be an alternative for concurrently applying multiple variables and can reduce potential biases. In this regard, the aim of this study is to establish and validate a machine learning-based predictive model for survival after allogeneic HCT in patients with hematologic malignancies.
      Methods: Data from 1470 patients with hematologic malignancies who underwent allogeneic HCT between December 1993 and June 2020 at Asan Medical Center, Seoul, South Korea, were retrospectively analyzed. Using the gradient boosting machine algorithm, we evaluated a model predicting the 5-year posttransplantation survival through 10-fold cross-validation.
      Results: The prediction model showed good performance with a mean area under the receiver operating characteristic curve of 0.788 (SD 0.03). Furthermore, we developed a risk score predicting probabilities of posttransplantation survival in 294 randomly selected patients, and an agreement between the estimated predicted and observed risks of overall death, nonrelapse mortality, and relapse incidence was observed according to the risk score. Additionally, the calculated score demonstrated the possibility of predicting survival according to the different transplantation-related factors, with the visualization of the importance of each variable.
      Conclusions: We developed a machine learning-based model for predicting long-term survival after allogeneic HCT in patients with hematologic malignancies. Our model provides a method for making decisions regarding patient and donor candidates or selecting transplantation-related resources, such as conditioning regimens.
      (©Eun-Ji Choi, Tae Joon Jun, Han-Seung Park, Jung-Hee Lee, Kyoo-Hyung Lee, Young-Hak Kim, Young-Shin Lee, Young-Ah Kang, Mijin Jeon, Hyeran Kang, Jimin Woo, Je-Hwan Lee. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 07.03.2022.)
    • References:
      Bone Marrow Transplant. 2014 Mar;49(3):332-7. (PMID: 24096823)
      Biol Blood Marrow Transplant. 2017 Nov;23(11):1839-1846. (PMID: 28797781)
      Blood. 2005 Oct 15;106(8):2912-9. (PMID: 15994282)
      Ann Intern Med. 2006 Mar 21;144(6):407-14. (PMID: 16549853)
      J Clin Oncol. 2015 Oct 1;33(28):3144-51. (PMID: 26240227)
      Blood Adv. 2019 Nov 26;3(22):3626-3634. (PMID: 31751471)
      Blood. 2014 Jun 5;123(23):3664-71. (PMID: 24744269)
      Cancer. 2009 Oct 15;115(20):4715-26. (PMID: 19642176)
      Cancer Med. 2019 Sep;8(11):5058-5067. (PMID: 31305031)
    • Contributed Indexing:
      Keywords: algorithm; bias; hematologic malignancies; hematopoietic cell transplantation; machine learning; malignancy; model; outcome; prediction; stem cell; survival; transplant; validation
    • Publication Date:
      Date Created: 20220307 Latest Revision: 20220324
    • Publication Date:
      20240829
    • Accession Number:
      PMC8938832
    • Accession Number:
      10.2196/32313
    • Accession Number:
      35254275