E-Book

E-Book 3rd Congress

  • Using artificial intelligence to diagnose hematological neoplasms
  • Mobina Nakhaei Shamahmood,1 Mahsa Taheri,2 Mahtab Sayadi,3,*
    1. Student research committee, school of Allied medical science, Birjand university of medical science, Birjand, Iran
    2. Student research committee, school of Allied medical science, Birjand university of medical science, Birjand, Iran
    3. Cellular and Molecular Research Center, Birjand University of Medical Sciences, Birjand, Iran.


  • Introduction: Morphological examination is essential for the diagnosis of hematological diseases. However, traditional manual operation is time-consuming and labor-intensive. Artificial intelligence (AI) is now systematically finding its way into hematological cancer diagnostic and The future of clinical diagnosis and treatment of hematological diseases will inevitably involve the integration of artificial intelligence (AI)-based systems into routine practice to support the decision-making of hematologists.. The aim of this study was to investigate the use of artificial intelligence for better and easier diagnosis of hematological neoplasms.
  • Methods: for this systematic review study we searched in PubMed, Google Scholar, Scopus, Embase, Medline, and Cochrane databases until October 2023. Also A search was carried out in Medline and in MedRxive and BioRxive and 21 articles related to this topic were used.
  • Results: Today, the use of artificial intelligence in hematology laboratories is limited. Approved devices are mainly limited to the morphological analysis of blood smears. Digital imaging has made it possible to use faster, more efficient and standardized methods to perform morphological analyzes of peripheral blood smears and classify blood cells, which will be of great use in the diagnosis of hematological neoplasms. However, this technology is far from gold standard. However, even the best tool can become unusable if it is used inadequately or the results are misinterpreted. Therefore, to fully evaluate and correctly apply newly developed AI-based systems, a hematologist must have a basic understanding of general machine learning concepts.
  • Conclusion: AI-based technologies have evolved rapidly over the last five years, producing a range of narrow AI applications that can be used at all stages of patient management in hematology from analyzing peripheral blood differentials to gene profiling. In the future, we envision a scenario in which AI-based algorithms could help integrate complex data with practical applications in patient care in an efficient and innovative way. Such a model is still a long way off, but it certainly deserves discussion and further research.
  • Keywords: Artificial intelligence,Hematological diagnostics,Neoplasms