Objective To investigate the impact of large language models on medical record coding,providing insights for the medical record management industry and professionals to better understand,familiarize with,and utilize large language models.Methods The study compared the time consumption,completion rate,and accuracy rate of coding 93 rare diseases u-sing ICD-10 codes between manual search and multiple large language models,elucidating the influence of large language models on medical record coding.Results In terms of coding time consumption,Model A and Model B required the least time,comple-ting all coding in 8 minutes,which is 90 times faster than manual search.Regarding completion rate,all models except Model C(91.4％)achieved 100％.In terms of accuracy rate,Model A was the highest(87.1％),surpassing manual search coding(84.9％).Model B and Model C had similar accuracy rates,47.3％and 43.5％respectively,while Model D had the lowest(0％).Conclusion There is a significant difference in coding accuracy among different large language models,but the accura-cy of Model A has already surpassed that of manual search coding.This demonstrates the powerful capabilities and potential of large language models in medical record coding.In the future,AI based on large language models may replace much of the manu-al work in disease coding.

Background and Aims:Chronic skin ulcers are a significant disease affecting patients'daily lives and psychological well-being.Abnormalities in the cells and extracellular matrix within the tissue may disrupt the balance of the microenvironment,hindering the normal skin repair process and leading to delayed healing of the ulcer.There is currently a lack of research on the mechanisms underlying the development of chronic ulcers and their diagnostic biomarkers.Single-cell sequencing,a newly developed high-throughput sequencing method in recent years,uses gene sequencing at the single-cell resolution to precisely reveal disease mechanisms and has been applied in various diseases.This study used single-cell transcriptome sequencing(scRNA-Seq)to investigate the cellular heterogeneity in chronic skin ulcer tissue to elucidate the potential molecular mechanisms behind delayed healing and provide new insights for clinical treatment.Methods:The scRNA-Seq technology was used to compare the differences in cell subpopulations and gene expression between chronic ulcer tissue and normal skin tissue.Single cells were sorted using a microfluidic platform,and cDNA libraries were constructed for subsequent differential gene analysis and functional enrichment analysis.Results:scRNA-Seq analysis revealed significant immune-metabolic remodeling features in chronic ulcer tissue:the number of B cells,monocytes,and macrophages in ulcer tissue increased by 2.1 to 3.5 times compared to the normal tissue control.This was accompanied by widespread activation of collagen synthesis genes(COL1A1/COL3A1)and synergistic suppression of immune regulators(e.g.,granzyme family GZMA/GZMB/H).Cross-cell subpopulation functional network analysis showed that hypoxia response mediated by the HIF-1 signaling pathway and PI3K/Akt pathway abnormalities formed a positive feedback loop,exacerbating the imbalance in the secretion of inflammatory factors(CXCL3/8,TGFBI)and compensatory upregulation of mitochondrial oxidative phosphorylation.Conclusion:Chronic skin ulcers exhibit significant differences in cellular heterogeneity and gene expression,suggesting that chronic ulcers are not simply tissue defects but a complex pathological process dominated by chronic inflammation and immune dysregulation.The coordinated dysregulation of multiple cell subpopulations in the ulcer microenvironment,along with persistent inflammatory responses and metabolic abnormalities,is interconnected through the HIF-1/TNF/MAPK pathway network.Downregulation of granzyme gene family members and abnormal histone modifications may contribute to immune clearance defects,providing a theoretical basis for developing novel therapies targeting epigenetic regulation or mitochondrial function.

Background and Aims:Chronic skin ulcers are a significant disease affecting patients'daily lives and psychological well-being.Abnormalities in the cells and extracellular matrix within the tissue may disrupt the balance of the microenvironment,hindering the normal skin repair process and leading to delayed healing of the ulcer.There is currently a lack of research on the mechanisms underlying the development of chronic ulcers and their diagnostic biomarkers.Single-cell sequencing,a newly developed high-throughput sequencing method in recent years,uses gene sequencing at the single-cell resolution to precisely reveal disease mechanisms and has been applied in various diseases.This study used single-cell transcriptome sequencing(scRNA-Seq)to investigate the cellular heterogeneity in chronic skin ulcer tissue to elucidate the potential molecular mechanisms behind delayed healing and provide new insights for clinical treatment.Methods:The scRNA-Seq technology was used to compare the differences in cell subpopulations and gene expression between chronic ulcer tissue and normal skin tissue.Single cells were sorted using a microfluidic platform,and cDNA libraries were constructed for subsequent differential gene analysis and functional enrichment analysis.Results:scRNA-Seq analysis revealed significant immune-metabolic remodeling features in chronic ulcer tissue:the number of B cells,monocytes,and macrophages in ulcer tissue increased by 2.1 to 3.5 times compared to the normal tissue control.This was accompanied by widespread activation of collagen synthesis genes(COL1A1/COL3A1)and synergistic suppression of immune regulators(e.g.,granzyme family GZMA/GZMB/H).Cross-cell subpopulation functional network analysis showed that hypoxia response mediated by the HIF-1 signaling pathway and PI3K/Akt pathway abnormalities formed a positive feedback loop,exacerbating the imbalance in the secretion of inflammatory factors(CXCL3/8,TGFBI)and compensatory upregulation of mitochondrial oxidative phosphorylation.Conclusion:Chronic skin ulcers exhibit significant differences in cellular heterogeneity and gene expression,suggesting that chronic ulcers are not simply tissue defects but a complex pathological process dominated by chronic inflammation and immune dysregulation.The coordinated dysregulation of multiple cell subpopulations in the ulcer microenvironment,along with persistent inflammatory responses and metabolic abnormalities,is interconnected through the HIF-1/TNF/MAPK pathway network.Downregulation of granzyme gene family members and abnormal histone modifications may contribute to immune clearance defects,providing a theoretical basis for developing novel therapies targeting epigenetic regulation or mitochondrial function.

Objective To investigate the impact of large language models on medical record coding,providing insights for the medical record management industry and professionals to better understand,familiarize with,and utilize large language models.Methods The study compared the time consumption,completion rate,and accuracy rate of coding 93 rare diseases u-sing ICD-10 codes between manual search and multiple large language models,elucidating the influence of large language models on medical record coding.Results In terms of coding time consumption,Model A and Model B required the least time,comple-ting all coding in 8 minutes,which is 90 times faster than manual search.Regarding completion rate,all models except Model C(91.4％)achieved 100％.In terms of accuracy rate,Model A was the highest(87.1％),surpassing manual search coding(84.9％).Model B and Model C had similar accuracy rates,47.3％and 43.5％respectively,while Model D had the lowest(0％).Conclusion There is a significant difference in coding accuracy among different large language models,but the accura-cy of Model A has already surpassed that of manual search coding.This demonstrates the powerful capabilities and potential of large language models in medical record coding.In the future,AI based on large language models may replace much of the manu-al work in disease coding.

【Objective】 To analyze the polymorphisms of GYPA and GYPB mRNA spliceosomes associated with MNS blood group, and to explore the mechanism of subcellular localization of GPA and GPB protein isomerism encoded by various spliceosomes as well as the expression of MNS blood group antigen. 【Methods】 Ten blood samples of voluntary blood donors were randomly selected. The total mRNA of peripheral blood was extracted and reversed into cDNA. Nested PCR was used to amplify reading open frame of GYPA and GYPB gene, and sequencing was performed by Sanger. The base sequence obtained was compared with GYPA(NCBI: NM_002099) and GYPB(NCBI: Nm_002100.5). After the wild type and various splicing isomer of the open reading frame of GYPA and GYPB had been obtained, they were fused with the encoding gene of green fluorescent protein (GFP) by fusion PCR technology, then cloned and transfected into HEK293 cells for over expression. The subcellular localization of GPA-GFP and GPB-GFP fused fluorescent proteins was monitored by focusing laser scanning microscope. 【Results】 Exon-1 and Exon-2 were missing in GYPA mRNA of the 2 samples, and 2~26 amino acids were missing in the predicted GPA isomer, and the full length sequence of GYPB mRNA was complete. GYPA mRNA was intact in 6 samples, exon-2 was missing in GYPB mRNA, 13~45 amino acids were missing in the predicted GPB protein isomer, and other exon sequences were intact. One sample had intact GYPA mRNA, and 364~385 bases in exon-5 of GYPB mRNA were replaced by AG, indicating truncation of amino acid signal peptide. The GYP mRNA sequences of other samples were complete. The fluorescence signal of GP-GFP fusion protein showed that all GPA and GPB glycoprotein isomers, cloned according to various RNA splicing, could demonstrate the orientation distribution on the cell membrane surface, while some alternative splicing leaded to different degrees of protein dispersion in the cell, and affected the distribution speed and proportion of protein on the cell surface, which might be one of the reasons for the strength variation of MNS antigen. 【Conclusion】 The GYP mRNA spliceosome is obviously polymorphic, but the partial deletion of GYP mRNA fragment does not affect the localization and distribution of the protein isomers encoded by GYP mRNA on the cell surface, which can ensure the expression of MNS antigen characteristics.