Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Correspondence
  • Published:

Registries and artificial intelligence: investing in the future of hematopoietic cell transplantation

Bone Marrow Transplantation volume 54, pages 477–480 (2019)Cite this article

Subjects

Utilization of “Big data” is revolutionizing almost every aspect of medicine. The future of medical practice will be highly dependent on the tools provided by artificial intelligence (AI) approaches, including machine learning (ML). AI offers the ability of performing tasks that would require human intelligence, however, on larger sets of data and patterns. These approaches have developed from our usual statistical methods and their use is emerging as a solution to many medical challenges [1]. The field of hematopoietic cell transplant (HCT) has advanced in many avenues over the last few decades. Despite these advances, the field of HCT is still facing many challenges, which contribute to morbidity and mortality in transplant recipients. These challenges include pre-transplant and post-transplant issues, such as HLA-matching donor-recipient pairs, graft-versus-host-disease (GVHD), risk stratification modeling etc. Difficulty solving these challenges is attributed to discrepancies in research endpoints, lack of standardization, and difficulty in recruiting sufficient number of patients in single center trials [2]. AI-based solutions arrived at by ML offer a real opportunity in tackling many of these challenges, owing to its ability to deal with a vast amount of data and extrapolating meaningful information from it. Some legitimate concerns have been raised including “deskilling” physicians and ethical issues [3, 4].

The use of AI in HCT, however, is still limited. To illustrate that, we systematically searched, using Boolean logic, the following databases: Ovid MEDLINE(R) In-Process & Other Non-Indexed Citations and Ovid MEDLINE(R) from 1946 to March 2018 as well as EMBASE. Our search mainly targeted GVHD, which is the major challenge facing allogeneic HCT recipients. The search yielded only four peer-reviewed publications that investigated the use of AI (Refer to Figure 1 in the supplementary material). This illustrates the current early state of research in this field compared with other medical disciplines.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

References

  1. Beam A, Kohane I. Big data and machine learning in health care. JAMA. 2018;319:1317–8.

    Article  Google Scholar 

  2. Pasquini MC, Logan B, Jones RJ, Appelbaum FR, Bolaños-Meade J, Flowers MED, et al. Blood and marrow transplant clinical trials network report on development of novel endpoints and selection of promising approaches for graft-versus-host disease prevention trials. Biol Blood Marrow Transplant. 2018;24:1274–80.

    Article  Google Scholar 

  3. Cabitza F, Rasoini R, Gensini GF. Unintended consequences of machine learning in medicine. JAMA. 2017;318:517–8.

    Article  Google Scholar 

  4. Char D, Shah N, Magnus D. Implementing machine learning in health are — addressing ethical challenges. New Engl J Med. 2018;378:981–3.

    Article  Google Scholar 

  5. Gandelman JS, Byrne MT, Mistry AM, Polikowsky H, Diggins KE, Chen H, et al. Machine learning reveals patient phenotypes and stratifies outcomes in chronic graft-versus host disease. Biol Blood Marrow Transplant. 2018;24:S65.

    Article  Google Scholar 

  6. Buturovic L, Shelton J, Spellman S, Wang T, Friedman L, Loftus D, et al. Evaluation of a machine learning-based prognostic model for unrelated hematopoietic cell transplantation donor selection. Biol Blood Marrow Transplant. 2018;24:1299–306.

    Article  Google Scholar 

  7. Shouval R, Labopin M, Bondi O, Mishan-Shamay H, Shimoni A, Ciceri F, et al. Prediction of allogeneic hematopoietic stem cell transplantation mortality 100 days after transplantation using a machine learning algorithm: a European Group for Blood and Marrow Transplantation Acute Leukemia Working Party Retrospective Data Mining Study. J Clin Oncol. 2015;33:3144–51.

    Article  Google Scholar 

  8. Hussain F, Chaudhri N, Alfraih F, Aljurf M. Current concepts on hematopoietic stem cell transplantation outcome registries; Emphases on resource requirements for new registries. Hematol/Oncol Stem Cell Ther. 2017;10:203–10.

    Article  Google Scholar 

  9. Somashekhar S, Sepúlveda M, Puglielli S, Norden A, Shortliffe E, Rohit Kumar C, et al. Watson for Oncology and breast cancer treatment recommendations: agreement with an expert multidisciplinary tumor board. Ann Oncol. 2018;29:418–23.

    Article  CAS  Google Scholar 

  10. Powles J, Hodson H. Google DeepMind and healthcare in an age of algorithms. Health Technol. 2017;7:351–67.

    Article  Google Scholar 

  11. CancerLinQ Engages Leading Technology Companies Tempus and Precision HealthAI to Accelerate Data-Driven Insights to Oncologists and the Cancer Care Community [Internet]. ASCO. 2018 [Accessed 2 July 2018]. Available from: https://www.asco.org/about-asco/press-center/news-releases/cancerlinq-engages-leading-technology-companies-tempus-and

  12. Schmidt C. M.D. Anderson breaks with IBM Watson, raising questions about artificial intelligence in oncology. J Natl Cancer Inst. 2017;109:djx113.

Download references

Author information

Authors and Affiliations

  1. College of Medicine, Alfaisal University, Riyadh, Saudi Arabia

    Ibrahim N. Muhsen

  2. Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA

    Madan Jagasia

  3. Bone Marrow Transplant program, Massey Cancer Center, VCU, Richmond, VA, USA

    Amir Ahmed Toor

  4. Oncology Center, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia

    Shahrukh K. Hashmi

  5. Division of Hematology, Department of Medicine, Mayo Clinic, Rochester, MN, USA

    Shahrukh K. Hashmi

Authors
  1. Ibrahim N. Muhsen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Madan Jagasia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Amir Ahmed Toor
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shahrukh K. Hashmi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

IM, MJ, AAT, and SKH participated in writing and revising the manuscript.

Corresponding author

Correspondence to Shahrukh K. Hashmi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Muhsen, I.N., Jagasia, M., Toor, A.A. et al. Registries and artificial intelligence: investing in the future of hematopoietic cell transplantation. Bone Marrow Transplant 54, 477–480 (2019). https://doi.org/10.1038/s41409-018-0327-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41409-018-0327-x

This article is cited by

Search

Advanced search

Quick links