The diagnosis of hematological disorders is currently established from the combined results of different tests, including those assessing morphology (M), immunophenotype (I), cytogenetics (C), and molecular biology (M) (collectively known as the MICM classification). In this workflow, most of the results are interpreted manually (i.e., by a human, without automation), which is expertise-dependent, labor-intensive, time-consuming, and with inherent interobserver variability. Also, with advances in instruments and technologies, the data is gaining higher dimensionality and throughput, making additional challenges for manual analysis. Recently, artificial intelligence (AI) has emerged as a promising tool in clinical hematology to ensure timely diagnosis, precise risk stratification, and treatment success. In this review, we summarize the current advances, limitations, and challenges of AI models and raise potential strategies for improving their performance in each sector of the MICM pipeline. Finally, we share perspectives, highlight future directions, and call for extensive interdisciplinary cooperation to perfect AI with wise human-level strategies and promote its integration into the clinical workflow.

In light of the lack of reliable molecular markers for odontogenic myxoma (OM), the detection of copy number variation (CNV) may present a more objective method for assessing ambiguous cases. In this study, we employed multiregional microdissection sequencing to integrate morphological features with genomic profiling. This allowed us to reveal the CNV profiles of OM and compare them with dental papilla (DP), dental follicle (DF), and odontogenic fibroma (OF) tissues. We identified a distinct and robustly consistent CNV pattern in 93.75% (30/32) of OM cases, characterized by CNV gain events in chromosomes 4, 5, 8, 10, 12, 16, 17, 20, and 21. This pattern significantly differed from the CNV patterns observed in DP, DF, and OF. The Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis indicated potential links between this CNV patterns and the calcium signaling pathway and salivary secretion, while Gene Ontology (GO) term analysis implicated CNV patterns in tumor adhesion, tooth development, and cell proliferation. Comprehensive CNV analysis accurately identified a case that was initially disputable between OF and OM as OM. Our findings provide a reliable diagnostic clue and fresh insights into the molecular biological mechanism underlying OM.
Humans ; DNA Copy Number Variations ; Odontogenic Tumors/diagnosis* ; Myxoma/genetics* ; Female ; Male ; Adult ; Adolescent ; Middle Aged ; Dental Papilla ; Young Adult ; Fibroma/genetics* ; Dental Sac ; Child

Objective The aim of this study is to analyze the association between IgM anti-mitochon-drial antibody subtypeⅡ(AMA-M2-IgM) and the anti-centromere antibody IgG (ACA-IgG) in primary biliary cirrhosis (PBC) patients, and to investigate the clinical significance of M2-IgM and ACA-IgG in the diagnosis of PBC. Methods We selected 36 cases of PBC patients as research subjects whose AMA-IgG and AMA-M2-IgG were both negative. The M2-IgM positive rate in the ACA-IgG positive group and negative group was compared. We also analyzed the course of disease, pathological changes and the positive conversion rate of M2-IgG between the M2-IgM positive group and negative group. Results There were 9 cases of M2-IgM positive patients (64%) and 5 cases of M2-IgM negative patients (36%) in the ACA-IgG positive group. In the ACA-IgG negative group we found 3 cases of M2-IgM positive patients (14%) and 19 cases of M2-IgM negative patients (86%). So the M2-IgM positive rate in the ACA-IgG positive group was significantly higher than that of the ACA-IgG negative group (P=0.003). According to the tracking detection results, the M2-IgG positive conversion rate in the M2-IgM positive group was 67% (8 patients), which was significantly higher than the M2-IgM negative group 8%, (2 patients) (P=0.001). Conclusion M2-IgM is a specific antibody for PBC in the early stage, which presents earlier than M2-IgG. In the PBC patients whose AMA-IgG and AMA-M2-IgG antibodies are both negative, the M2-IgM positive rate is closely related to the ACA-IgG, so the ACA-IgG detection is very important in the early diagnosis of PBC. Therefore, we speculated that patients with ACA-IgG antibody are more susceptible to PBC.

Objective To observe the effects of Dengzhanhua Capsule on kidney tissue inflammatory cytokines in chronic renal failure rats;To explore its possible mechanism for the efficacy in chronic renal failure. Methods Sixty SD rats were randomly divided into normal control group, model group, benazepril group and Dengzhanhua group, 15 rats in each group. Chronic renal failure rat model was established by Platt 5/6 nephrectomized. Benazepril (0.29 mg/100 g) was given to rats in the benazepril group by gastrogavage. Dengzhanhua Capsule (0.3 g/100 g) was given to rats in the Dengzhanhua group by gastrogavage. Normal saline was given to rats in the normal group and the model group by gastrogavage. The whole treatment period was twelve weeks. Expressions of TGF-β1 and PAI-1 were determined by semi-quantitative RT-PCR after treatment. Concentrations of kidney tissue inflammatory cytokines IL-6 and TNF-α were determined by ELISA. Results Expressions of TGF-β, PAI-1 and IL-6, TNF-αin benazepril group and Dengzhanhua group were significantly lower than those in model group (P<0.05). Compared with benazepril group, it was significantly lower in Dengzhanhua group (P<0.05). Conclusion Dengzhanhua Capsule can reduce kidney tissue inflammatory in chronic renal failure rats, and inhibit renal fibrosis.