As a major global public health concern,cancer has witnessed a continues rise in both incidence and mortality rates.It pose not only a severe threat to human health but also a heavy burden on socioeconomic systems.Despite remarkable advancements in oncology research,critical challenges such as tumor heterogeneity,drug resistance,and limitations in early screening and diagnostic technologies remain to be addressed.Against this backdrop,artificial intelligence(AI),with its unique advantages in big data analysis,pattern recognition,and predictive modeling,has opened new avenues for cancer research.By integrating multi-modal data,including omics,imaging,and clinical information,AI not only accelerates investigations into fundamental tumor mechanisms but also demonstrates immense potential in areas such as early screening,biomarker discovery,and personalized treatment.These advancements have fostered a deeper integration of precision medicine and oncology.This review provides a comprehensive overview of the most recent progresses in the application of AI in cancer diagnosis and treatment research,with a focus on its practical value across diverse data types and clinical scenarios,as well as future directions for its development.

Objective:To analyze the changes in the number of patients, incidence, mortality rate, disability-adjusted life year (DALY), years lived with disability (YLD), and years of life lost due to premature mortality (YLL) globally and in China from 1990 to 2021, and to predict future trends in the number of patients and DALY of inflammatory bowel disease (IBD) globally and in China.Methods:Descriptive epidemiology was applied. Data on globally and Chinese IBD burden indicators, including prevalence, incidence, mortality, DALY, YLL, and YLD were collected from the Global Burden of Disease (GBD) 2021 Database from 1990 to 2021, and the trends in the changes and distributions of age and gender were analyzed. The age-standardized rate was standardization based on the world standard population age structure estimated by GBD. Auto-regressive integrated moving average model was used to predict the number of IBD patients and DALY globally and in China from 2022 to 2030.Results:In 1990 and 2021, the global number of IBD patients was 2.170 2 and 3.830 1 million, respectively, while in China which was 62 100 and 168 100, respectively. The global crude incidence rate and age-standardized incidence rate were 3.74/100 000, 4.22/100 000, 4.75/100 000, and 4.45/100 000, respectively. The crude incidence rate and age-standardized incidence rate in China were 0.71/100 000, 0.74/100 000 and 1.75/100 000, 1.40/100 000, respectively. In 1990 and 2021, the global crude mortality rate and age-standardized mortality rate of IBD were 0.40/100 000, 0.60/100 000 and 0.54/100 000, 0.52/100 000, respectively; the crude mortality rate and age-standardized mortality rate in China were 0.37/100 000, 0.75/100 000 and 0.40/100 000, 0.33/100 000, respectively. Compared with those in 1990, the global crude DALY, YLD and YLL of IBD all increased in 2021, which were 1 510.8 thousand person-years vs. 948.9 thousand person-years, 579.2 thousand person-years vs. 330.9 thousand person-years, 931.6 thousand person-years vs. 618.0 thousand person-years; the age-standardized DALY, YLD and YLL all decreased, which were 18.07/100 000 vs. 21.54/100 000, 6.79/100 000 vs. 7.27/100 000, 11.27/100 000 vs. 14.27/100 000, respectively. Compared with those in 1990, the crude YLD and the age-standardized YLD in China both increased (26.9 thousand person-years vs. 10.1 thousand person-years, 1.47/100 000 vs. 0.91/100 000), while the crude DALY, the age-standardized DALY, crude YLL and the age-standardized YLL all decreased (136.9 thousand person-years vs. 162.2 thousand person-years, 7.68/100 000 vs. 18.38/100 000, 110 thousand person-years vs. 152 thousand person-years, 6.21/100 000 vs. 17.47/100 000).From 1990 to 2021, male and female age-standardized incidence and prevalence of IBD were all in upward trend. The difference in the incidence of IBD between males and females was relatively small, and the global age-standardized incidence of IBD in males were slightly higher than those in females, while in China the rates are similar between the two genders. The global and Chinese age-standardized prevalence in females were slightly higher than those in males. From 1990 to 2021, the estimated annual percentage change (EAPC) of age-standardized IBD incidence in global and China were 0.24 (95% confidence interval (95% CI): 0.16 to 0.31) and 1.55 (95% CI: 1.25 to 1.86), respectively; the EAPC of age-standardized DALY in global and China were -0.50 (95% CI: -0.58 to -0.41) and -2.71 (95% CI: -2.99 to -2.43), respectively. The age distribution of disease onset shifted towards middle-aged and old population. It was predicted that by 2030, the annual number of new IBD cases in global would increase to 410 100, while in China, it would decrease to 21 184. Furthermore, the global DALY of IBD would increase to 1 670 527 person-year, and in China which would be 140 563 person-year. Conclusions:From 1990 to 2021, the global and Chinese number of patients and the incidence of IBD both sustained increase. The age of IBD onset towards older population. The incidence trend of IBD was aging, with significant gender bias. The global community and China continue to face many severe challenges in IBD.

Objective:To analyze the clinical significance of molecular classification and hereditary phenotype in endometrial carcinoma (EC) based on high throughput sequencing (NGS).Methods:97 EC samples were collected retrospectively from December 2019 to October 2022 in China-Japan Friendship Hospital. NGS technique was used to analyze the molecular classification, POLE hypermutation, microsatellite high Instability/mismatch repair dysfunction (MSI-H/MMRd), P53 protein abnormality (P53 abn), and non-specific molecular profile (NSMP). Lynch syndrome related genes and BRCA1/2 genes were detected by NGS and their genetic characteristics were analyzed. Results:Of the 97 EC cases, 77 were endometrial adenocarcinoma and 20 were other pathological subtypes. The proportions of the four molecular subtypes were 9.3% (9/97) POLE hypermutation, 16.5% (16/97) MSI-H, 17.5% (17/97) P53 abn and 56.7% (55/97) NSMP, respectively. There were significant differences in age, histological type, lymph node metastasis, pathological stage and other parameters among the four molecular types ( P＜0.05). 8.2% (8/97) were multiple molecular typing and four multiple molecular typings detected, including POLEmut-MSI-H, POLEmut-P53abn, MSI-H-P53abn, P53abn-P53abn, which accounted for 1.0% (1/97), 3.1% (3/97), 1.0% (1/97) and 3.1% (3/97), respectively. The consistent rate of MSI-H and MMR protein expression was 92.9% ( Kappa=0.818, P＜0.001). The coincidence rate between TP53 gene sequencing and P53 protein expression was 88.9% ( Kappa=0.661, P＜0.001). In MSI-H type, 25.0% (4/16) were diagnosed as Lynch syndrome, and 75.0% (12/16) were diagnosed as Lynch like syndrome. 7.2% (7/97) BRCA2 somatic variation was detected, while BRCA1/2 germline variation was not detected in 97 cases. Conclusions:EC molecular classification has feasibility and clinical value. High throughput sequencing can detect low frequency mutations of TP53 gene, suggesting that it can provide more accurate molecular information and more accurate molecular typing effect. It is suggested to further detect Lynch syndrome related genes in patients with MSI-H, so as to carry out genetic management for patients and their families and achieve better therapeutic effect.

This study was aimed at investigating the infection status of orf virus(ORFV)and the genetic evolution characteristics of epidemic ORFV isolates from Anhui province.A total of 303 clinical samples collected from major meat sheep breeding cities in An-hui during 2021-2023 were subjected to ORFV detection with fluorescence quantitative PCR(qPCR).The full-length B2L and F1L genes of ORFV in the positive samples were amplified through conventional PCR and sequenced.Genetic evolution analysis of the B2L and F1L genes was conducted after sequencing.The qPCR results indicated a total ORFV positivity rate in the clinical samples of 48.8%(148/303).Multiple sequence comparisons indicated that the B2L genes of 56 sample isolates shared 96.7%-100.0%DNA and 97.4%-100.0%amino acid sequence identity.Moreover,the F2L genes of 56 sample isolates shared 95.1%-100.0%DNA and 95.0%-100.0%amino acid sequence identity.The genetic evolution tree constructed with the B2L gene DNA sequences indicated sample iso-lates and 21 reference strains located in subgroup 1,and 26 sheep-derived sample isolates and 17 reference strains located in sub-group 2.Among them,the goat-derived sample isolate FY-TYA was located in the same sub-branch as the human-derived reference strain Gansu,whereas the goat-derived sample isolate FY-XQC was located in the same sub-branch as the reference strains China Vaccine and OV-HLJ-04.The genetic evolution tree constructed with the F1L gene DNA sequences showed,the goat sample isolates FY-XQA and FY-XQC were located in the same sub-branch as the sheep-derived reference strain Xinjiang.ORFV infection was rela-tively widespread in the major meat sheep breeding areas of Anhui province,and the DNA and amino acid sequences of the B2L and F1L genes of current circulating ORFV isolates showed different degrees of genetic variation,among which F1L gene had a high de-gree of variation.Furthermore,some goat-derived sample isolates were closely related to human,vaccine,and sheep-derived refer-ence strains.These results may serve as a reference for the prevention and control of ORFV infection in Anhui province.

The classical latent structure method does not consider the influence of primary and secondary symptoms,syndromes and symptoms in the analysis and modeling of syndromes.In this paper,based on the data of damp-heat in intestine and stomach syndrome involving 1087 diabetic patients,the classical latent structure analysis was used to obtain the quantitative syndrome diagnostic rules.Then,using Constrained Latent Tree Analysis(CLTA),the quantitative syndrome diagnostic rules containing primary and secondary symptoms were obtained as follows,primary symptoms include halitosis(2.3),yellow tongue coating(2),abdominal distension(2.3),greasy tongue coating(2.1),loose stool or loose stool(1.5),red tongue(1.3),smooth pulse(1.4).Secondary symptoms include epigastric distension(1.1).Compared with the traditional latent structure analysis method,the rules established by CLTA are more compatible with the concept of differentiating primary and secondary symptoms and the common practice of TCM.The quantitative syndrome diagnostic rules of damp-heat in intestine and stomach syndrome constructed by the CLTA method have considerable objectivity in the modeling process.The diagnostic rules established were also compatible with the qualitative concept of TCM theory in stratifying primary and secondary symptoms.Finally,the diagnostic rules are obtained by logistic regression analysis,and the accuracy of the three rules is compared.The results show that the rule recognition accuracy obtained by CLTA is the highest.Therefore,the syndrome diagnostic rules of damp-heat in intestine and stomach obtained from the analysis of CLTA are in line with the constraint semantics of primary and secondary diseases and the theory of traditional Chinese medicine.

The classical latent structure method does not consider the influence of primary and secondary symptoms,syndromes and symptoms in the analysis and modeling of syndromes.In this paper,based on the data of damp-heat in intestine and stomach syndrome involving 1087 diabetic patients,the classical latent structure analysis was used to obtain the quantitative syndrome diagnostic rules.Then,using Constrained Latent Tree Analysis(CLTA),the quantitative syndrome diagnostic rules containing primary and secondary symptoms were obtained as follows,primary symptoms include halitosis(2.3),yellow tongue coating(2),abdominal distension(2.3),greasy tongue coating(2.1),loose stool or loose stool(1.5),red tongue(1.3),smooth pulse(1.4).Secondary symptoms include epigastric distension(1.1).Compared with the traditional latent structure analysis method,the rules established by CLTA are more compatible with the concept of differentiating primary and secondary symptoms and the common practice of TCM.The quantitative syndrome diagnostic rules of damp-heat in intestine and stomach syndrome constructed by the CLTA method have considerable objectivity in the modeling process.The diagnostic rules established were also compatible with the qualitative concept of TCM theory in stratifying primary and secondary symptoms.Finally,the diagnostic rules are obtained by logistic regression analysis,and the accuracy of the three rules is compared.The results show that the rule recognition accuracy obtained by CLTA is the highest.Therefore,the syndrome diagnostic rules of damp-heat in intestine and stomach obtained from the analysis of CLTA are in line with the constraint semantics of primary and secondary diseases and the theory of traditional Chinese medicine.

As a major global public health concern,cancer has witnessed a continues rise in both incidence and mortality rates.It pose not only a severe threat to human health but also a heavy burden on socioeconomic systems.Despite remarkable advancements in oncology research,critical challenges such as tumor heterogeneity,drug resistance,and limitations in early screening and diagnostic technologies remain to be addressed.Against this backdrop,artificial intelligence(AI),with its unique advantages in big data analysis,pattern recognition,and predictive modeling,has opened new avenues for cancer research.By integrating multi-modal data,including omics,imaging,and clinical information,AI not only accelerates investigations into fundamental tumor mechanisms but also demonstrates immense potential in areas such as early screening,biomarker discovery,and personalized treatment.These advancements have fostered a deeper integration of precision medicine and oncology.This review provides a comprehensive overview of the most recent progresses in the application of AI in cancer diagnosis and treatment research,with a focus on its practical value across diverse data types and clinical scenarios,as well as future directions for its development.

This study was aimed at investigating the infection status of orf virus(ORFV)and the genetic evolution characteristics of epidemic ORFV isolates from Anhui province.A total of 303 clinical samples collected from major meat sheep breeding cities in An-hui during 2021-2023 were subjected to ORFV detection with fluorescence quantitative PCR(qPCR).The full-length B2L and F1L genes of ORFV in the positive samples were amplified through conventional PCR and sequenced.Genetic evolution analysis of the B2L and F1L genes was conducted after sequencing.The qPCR results indicated a total ORFV positivity rate in the clinical samples of 48.8%(148/303).Multiple sequence comparisons indicated that the B2L genes of 56 sample isolates shared 96.7%-100.0%DNA and 97.4%-100.0%amino acid sequence identity.Moreover,the F2L genes of 56 sample isolates shared 95.1%-100.0%DNA and 95.0%-100.0%amino acid sequence identity.The genetic evolution tree constructed with the B2L gene DNA sequences indicated sample iso-lates and 21 reference strains located in subgroup 1,and 26 sheep-derived sample isolates and 17 reference strains located in sub-group 2.Among them,the goat-derived sample isolate FY-TYA was located in the same sub-branch as the human-derived reference strain Gansu,whereas the goat-derived sample isolate FY-XQC was located in the same sub-branch as the reference strains China Vaccine and OV-HLJ-04.The genetic evolution tree constructed with the F1L gene DNA sequences showed,the goat sample isolates FY-XQA and FY-XQC were located in the same sub-branch as the sheep-derived reference strain Xinjiang.ORFV infection was rela-tively widespread in the major meat sheep breeding areas of Anhui province,and the DNA and amino acid sequences of the B2L and F1L genes of current circulating ORFV isolates showed different degrees of genetic variation,among which F1L gene had a high de-gree of variation.Furthermore,some goat-derived sample isolates were closely related to human,vaccine,and sheep-derived refer-ence strains.These results may serve as a reference for the prevention and control of ORFV infection in Anhui province.

Objective To explore differentially expressed proteins in the serum exosomes of acute myeloid leukemia(AML)patients and healthy controls by using the proteomics method,and provide new biomarker for the diagnosis and treatment of AML.Methods A total of 76 AML patients diagnosed and treated in the First People's Hospital of Honghe State from November 2022 to June 2024 were selected as the experimental group,and 60 healthy physical examination participants were selected as the control group.Tandem Mass Tag(TMT)labeled proteomics was used to identify the differences in protein expression in serum exosomes between the experimental and control groups,and the identified differentially expressed proteins were subjected to bioinformatics analysis.Western-Blot was used to verify the differentially expressed proteins.Results Comparedwith healthy controls,146 aberrantly expressed proteinswere detected in serum exosomes of AML patients,of which 89 were up-regulated and 57 were down-regulated.Among them,Alpha-1-antichymotrypsin(α1-ACT),Angiogenin(ANG),Vitronectin(VIT),Clusterin(Clu),Fibronectin(FN),Keratin type I cytoskeletal-18(KRT18),and actinin alpha4(ACTN4)showed changed significantly.Gene ontology(GO)and Kyoto encyclopedia of genes and genomes(KEGG)enrichment analysis indicated that differentially expresseproteins were involved in biological processes such as neutrophil immunity,neutrophil degranulation,neutrophil activation immune response,and protein activation cascade,significantly enriched in 25 biological pathways including complement and coagulation cascades,extracellular matrix(ECM)-receptor interaction,and hypoxia-inducible factor-1(HIF-1)signaling pathways.Western-blot validation results showed that compared with the control group,the expression levels of ANG,Clu and FN in the serum exosomes of AML patients were significantly increased,while the expression level of ACTN4 was significantly decreased,with statistically significant differences(t=-11.854～18.569,all P<0.05).The expression levels of ANG and FN were correlated with white blood cell count(F=8.888,7.818,all P<0.05)and cytogenetics(F=8.619,7.983,P<0.05).The expression level of Clu protein was correlated with white blood cell count(F=2.571,P<0.05),but not significantly associated with cytogenetics(F=1.886,P>0.05).ANG,FN and Clu showed no significant correlation with FAB classification(F=0.175,0.434,0.042,all P>0.05).Conclusion The expression of exosomal proteins in the serum of AML patients compared to healthy individuals are significant differences,which may serve as serological markers for the diagnosis and treatment of AML.

Objective To investigate the expression changes of serum circRNA membrane bound O-acyltransferase 2(circRNA MBOAT2)and circRNA recombinant actinin 4(circRNA ACTN4)in patients with cholangiocarcinoma and their relationship with prognosis.Methods 96 patients with cholangiocarcinoma treated at the First Hospital of Handan City from January 2020 to January 2022 in Department of Hepatobiliary Surgery were regarded as as the cholangiocarcinoma group.Additionally,85 patients with intraductal stones and 90 healthy volunteers were collected as the stone group and control group,respectively.Quantitative real-time reverse transcription PCR(qRT-PCR)was applied to detect the expression levels of circRNA MBOAT2 and circRNA ACTN4.χ2 test was applied to analyze the relationship between circRNA MBOAT2 and circRNA ACTN4 and clinical pathological features.Pearson was applied to analyze the correlation between circRNA MBOAT2 and circRNA ACTN4 in patients with cholangiocarcinoma.ROC was applied to analyze the diagnostic value of circRNA MBOAT2 and circRNA ACTN4 in the occurrence of cholangiocarcinoma.COX was applied to analyze the influencing factors of poor prognosis in patients with cholangiocarcinoma.Kaplan-Meier method was applied for survival analysis.Results circRNA MBOAT2(1.24±0.38)and circRNA ACTN4(1.27±0.42)in cholangiocarcinoma group were higher than those in stone group(1.02±0.31,1.05±0.34)and control group(0.83±0.24,0.78±0.21),and the stone group was higher than that in control group,with statistically significance(t=5.016～14.025,all P<0.05).There was a positive correlation between circRNA MBOAT2 and circRNA ACTN4 in patients with cholangiocarcinoma group(r=0.428,P<0.05).Combined diagnosis of MBOAT2 and ACTN4 was better than single diagnosis of cholangiocarcinoma(Z=4.063,4.004,all P<0.05);circRNA MBOAT2 and circRNA ACTN4 were correlated with clinical staging and lymph node status(t=5.091～5.984,all P<0.05).Positive lymph node status and elevated levels of circRNA MBOAT2 and circRNA ACTN4 were independent risk factors for mortality(HR=1.527,1.582,1.727,all P<0.05).The cumulative survival rate of patients with high expression of circRNA MBOAT2(23.40%vs 46.94%)and circRNA ACTN4(24.00%vs 47.83%)was lower than that of patients with low expression(χ2=5.809,5.946,all P<0.05).Conclusion The serum levels of circRNA MBOAT2 and circRNA ACTN4 increase with the progression of the disease,and the combination of the two has certain value in diagnosing the occurrence of cholangiocarcinoma.