A Review on Donor Selection in Hematopoietic Stem Cell Transplantation (HSCT)

In the healthcare industry today, machine learning techniques are extensively employed for disease detection, prognosis, and therapy. These methods find use in the domain of Hematopoietic Stem Cell Transplantation (HSCT), a treatment for hematological malignancies that may prove to be curative. A thorough analysis of the use of machine learning (ML) techniques in the context of HSCT was carried out in this article. Using the databases from IEEE Xplore, Web of Science, PubMed, and Scopus, a systematic review of English papers was carried out. Hematopoietic stem cell transplantation (HSCT), machine learning and artificial intelligence were among the search terms used. This review included a methodical analysis of machine learning methods used in HSCT. The evidence is not strong enough to establish what minimal data variables are needed, or what ML technique is best to utilize in the HCT situation. In recent years, stem cell therapy has become a focus of very promising and progressive scientific research. There are great expectations for the development of treatments. A framework/model will be developed to match the HLA (Human Leukocyte Antigen) between unrelated donor and patient in Hematopoietic Stem Cell Transplantation (HSCT). Stem cell recordings are collected from donors at the Biomedical Research Center and the data are analyzed. Final results will help determine donor eligibility.