Background: Iron deficiency (ID) and hemoglobinopathies are highly prevalent in Southeast Asia. Accurate estimation of reference intervals (RIs) for red cell parameters is complicated by the need to exclude individuals with these conditions from the reference population. Indirect RI estimations using machine learning could help overcome these challenges. Methods: We developed a binary classification model using eXtreme Gradient Boosting (XGB) to distinguish normal individuals from those with ID, hemoglobinopathies, or other anemias. The model was trained on an annotated dataset comprising 5,520 complete blood count (CBC) results and validated with a holdout dataset of 2,367 CBC results. An independent dataset of 64,100 CBC results was used to identify individuals predicted to be normal, from which RIs were estimated using the refineR algorithm. Results: The XGB model achieved an area under the ROC of 0.97 (95% confidence interval: 0.96–0.97) for distinguishing between individuals with normal versus abnormal values. Among individuals within the independent dataset, 40,300 (62.9%) were predicted to be normal. The refineR-based reference limits (RLs) derived from this subset approximated those obtained through a direct approach. Improvements in the accuracy of indirect RL estimates were most evident for hematocrit, hemoglobin, and red cell concentrations. Conclusions Combining XGB with refineR to indirectly derive RIs for red cell parameters improved the accuracy and yielded results comparable with those of directly derived RIs. A further benefit was the capacity to generate sex- and age-specific ranges, which has remained difficult to achieve through direct approaches.

Objective To investigate the role and molecular mechanism of exosomal miR-224-5p in colorectal cancer (CRC).Methods The miR-224-5p expression in CRC patient tissues and cell-derived exosomes was measured by laser capture microdissection and qRT-PCR, respectively. Dual-luciferase reporter gene assay was used to determine the target gene of miR-224-5p. The protein expressions of p53 and unc-51 like kinase 2 (ULK2) in CRC cells were detected by western blot. Flow cytometry was used to detect cell cycle and apoptosis. Cell proliferation was measured by CCK8 and EdU assay.Results The miR-224-5p expression was upregulated in CRC tissues and increased progressively with the rise of CRC stage. CRC cells secreted extracellular miR-224-5p mainly in an exosome-dependent manner, and then miR-224-5p could be transferred to surrounding tumor cells to regulate cell proliferation in the form of autocrine or paracrine. Moreover, ULK2 was characterized as a direct target of miR-224-5p and was downregulated in CRC tissues. Interestingly, ULK2 inhibited CRC cell proliferation in a p53-dependent manner. Furthermore, exosome-derived miR-224-5p partially reversed the proliferation regulation of ULK2 on CRC cells.Conclusion Our findings demonstrate that exosome-transmitted miR-224-5p promotes p53-dependent cell proliferation by targeting ULK2 in CRC, which may offer promising targets for CRC prevention and therapy.