Abstract:ObjectiveTo evaluate the recognition capability of AlI-enabled Cellsee CS-BMI automatic c ell morphology analyzer for pe-ripheral blood smears and its roles in assisting mamual clasification, and explore the application value of Al system in the diagnosisnetwork of tiered primary medlical units.Methods'The blood samples which triggered the re-examination rules were collected from sixprimary medical units, including the laboratory Department of Shanghai Jiahui International Hospital , and so on, from March to No-vember 2023.The smears of peripheral blood were prepared anmd Al analyzer was used for pre-classification to evaluate its recognition performance in identifying the samples with abnormal WBC and RBC. The sensitivity, specificity, and accuracy of WBC classificationby six junior and intermediate technicians , both with and without Al assistance,were analyzed.Additionally , the roles of the Al systemin tiered diagnosis of primary medical unis were also evaluated.Results The sensitivity，specificity ， and accuracy of Al system inrecognizing malignant primitive cells were 92.86% ，95.16% , and 95.10% ， respectively. The sensitivities of Al system in reoognizingimmature granulocytes , ractive lymphocytes， and nucleated RBCs were all greater than 90%. The sensitivity of Al system in identif-ying abnomal momphology of RBCs reached 99.59% ， along with rapid quantitative analysis for various anomalous types of RBCs. In AT-assisted mole, the sensitivity of recognition for all cell types was improved to varying degrees by junior and intermedliate technicians,and the sensitivity for recognizing malignant primitive cells，reactive lymphocytes， and immature granuloytes increased to 58.24%,53.39% , and 62.37% for junior technicians ， and to 92.06%，83.24%, and 83.12% for intemediate technicians，respectively.Theimprovements for jumior technicians were particularly significant ，with increases of 12.46%，10.61% ， and 3.71% for each cell type,respectively.Both groups achieved higher specificity and accuracy. Trough Al pre-classification and mamual review,a variety of pe-ripheral blood cellrelated diseases were acurately diagnosed in the tiered healthcare practice of primary medical units , including 339cases ( 11.13%) of red blood cell diseases , 5 cases (0.16%) of platelet diseases, 2 343 cases (76.90%）) of infection-related disea-ses, and 28 cases (0.92%) of malignant hematological diseases. In adldition ，332 cases ( 10.90%) which lacked an obvious relatedcause or required further examinations were identified as well. Conclusion Al pre-classification has demonstraled strong cell recogni-tion capabilities and may assist technicians in improving the sensitivity , specificity, and accauracy of blool cell classification. Al could enhance the diseasc-screening capabities in the tiered diagnosis network of pwrimary medlical units, presenting a broad application prospeet.