Abstract The integration of artificial intelligence with bone marrow cytology represents a significant trend in the application of AI image recognition technology within the medical sector. Despite the current high accuracy of AI in cell identification, there remains a clinical need for fully automated AI cell recognition equipment that spans from sample processing to result generation. The source of the sample’s origin as an influencing factor on the final results is a crucial consideration in equipment design. In this research, patient bone marrow fluid samples were processed into various types of anticoagulated bone marrow smears—EDTAK anticoagulated, sodium citrate anticoagulated, heparin lithium anticoagulated, and sodium citrate anticoagulated—and non-anticoagulated, and subsequently analyzed by AI devices. The findings revealed a significant lack of consistency in cell classification ratios and the total number of cells recognized between anticoagulated and non-anticoagulated bone marrow smear samples. This aspect must be taken into account when designing a fully automated AI-based bone marrow cell recognition device. Similar content being viewed by others Author information Authors and Affiliations Corresponding authors Ethics declarations Competing interests The authors declare no competing interests. Additional information Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Rights and permissions Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless