人工智能在自身免疫性肝病诊疗中的应用

摘要/Abstract

摘要： 自身免疫性肝病是一组病因复杂、诊断困难且治疗挑战大的慢性肝病,传统方法存在诸多局限。近年来,人工智能技术(尤其是机器学习和深度学习)在自身免疫性肝病的诊疗中展现出巨大潜力。这些技术能够整合处理影像学图片、病理切片、临床和实验室指标等多维度信息,在疾病诊断、生物标志物发现、疾病预测、治疗等方面发挥重要作用。本文综述了人工智能在自身免疫性肝病诊疗中的最新研究进展,同时分析了当前技术应用面临的主要问题,并对未来发展方向提出展望。

关键词: 人工智能, 自身免疫性肝病, 机器学习, 深度学习

凌铭霞, 韦影影, 郑广妃, 何宛蓉. 人工智能在自身免疫性肝病诊疗中的应用[J]. 肝脏, 2026, 31(7): 1044-1048.

/ 推荐

参考文献

[1] Heo N Y, Kim H. Epidemiology and updated management for autoimmune liver disease[J]. Clin Mol Hepatol, 2023, 29: 194-196.
[2] Carbone M, Neuberger J M. Autoimmune liver disease, autoimmunity and liver transplantation[J]. J Hepatol, 2014, 60: 210-223.
[3] Janiesch C, Zschech P, Heinrich K. Machine learning and deep learning[J]. Electron Markets, 2021, 31: 685-695.
[4] Liu W, Liu X, Peng M, et al. Artificial intelligence for hepatitis evaluation[J]. World J Gastroenterol, 2021, 27: 5715-5726.
[5] Calderaro J, Seraphin T P, Luedde T, et al. Artificial intelligence for the prevention and clinical management of hepatocellular carcinoma[J]. J Hepatol, 2022, 76: 1348-1361.
[6] Pellat A, Barat M, Coriat R, et al. Artificial intelligence: a review of current applications in hepatocellular carcinoma imaging[J]. Diagn Interv Imaging, 2023, 104: 24-36.
[7] Li Y, Wang X, Zhang J, et al. Applications of artificial intelligence (AI) in researches on non-alcoholic fatty liver disease (NAFLD): a systematic review[J]. Rev Endocr Metab Disord, 2022, 23: 387-400.
[8] Ragab H, Westhaeusser F, Ernst A, et al. DeePSC: a deep learning model for automated diagnosis of primary sclerosing cholangitis at two-dimensional MR cholangiopancreatography[J]. Radiol Artif Intell, 2023, 5: 220160.
[9] Ringe K I, Vo Chieu V D, Wacker F, et al. Fully automated detection of primary sclerosing cholangitis (PSC)-compatible bile duct changes based on 3D magnetic resonance cholangiopancreatography using machine learning[J]. Eur Radiol, 2021, 31: 2482-2489.
[10] Singh Y, Eaton J E, Venkatesh S K, et al. Deep learning analysis of magnetic resonance imaging accurately detects early-stage perihilar cholangiocarcinoma in patients with primary sclerosing cholangitis[J]. Hepatology, 2025, in press.
[11] Ercan C, Kordy K, Knuuttila A, et al. A deep-learning-based model for assessment of autoimmune hepatitis from histology: AI (H)[J]. Virchows Arch, 2024, 485: 1095-1105.
[12] Sjoblom N, Boyd S, Manninen A, et al. Chronic cholestasis detection by a novel tool: automated analysis of cytokeratin 7-stained liver specimens[J]. Diagn Pathol, 2021, 16: 41.
[13] Lu M, Bowlus C L, Lindor K, et al. Validity of an automated algorithm to identify cirrhosis using electronic health records in patients with primary biliary cholangitis[J]. Clin Epidemiol, 2020, 12: 1261-1267.
[14] 杨雪, 徐斌, 刘燕敏, 等. 原发性胆汁性胆管炎患者无创肝硬化诊断敏感指标的筛选[J]. 中国临床新医学, 2021, 14: 762-766.
[15] Alghamdi M A, Bhirud S G, Alam A M. Physician′s decision process for disease diagnosis of overlapping syndrome in liver disease using soft computing model[J]. Int J Soft Comput Eng, 2015, 4: 28-33.
[16] Wang K, Li Y, Pan J, et al. Noninvasive diagnosis of AIH/PBC overlap syndrome based on prediction models[J]. Open Med, 2022, 17: 1550-1558.
[17] Gerussi A, Saldanha O L, Cazzaniga G, et al. Deep learning helps discriminate between autoimmune hepatitis and primary biliary cholangitis[J]. JHEP Rep, 2025, 7: 101198.
[18] Wang Y, Lin X, Sun Y, et al. Development and validation of a novel model to discriminate idiosyncratic drug-induced liver injury and autoimmune hepatitis[J]. Liver Int, 2025, 45: 16239.
[19] Singh A, Pandey B. A KLD-LSSVM based computational method applied for feature ranking and classification of primary biliary cirrhosis stages[J]. Int J Comput Biol Drug Des, 2017, 10: 24-38.
[20] Guadalupi G, Contini C, Iavarone F, et al. Combined salivary proteome profiling and machine learning analysis provides insight into molecular signature for autoimmune liver diseases classification[J]. Int J Mol Sci, 2023, 24: 12207.
[21] Olianas A, Guadalupi G, Cabras T, et al. Top-down proteomics detection of potential salivary biomarkers for autoimmune liver diseases classification[J]. Int J Mol Sci, 2023, 24: 959.
[22] Snir T, Greenman R, Aricha R, et al. Machine learning identifies key proteins in primary sclerosing cholangitis progression and links high CCL24 to cirrhosis[J]. Int J Mol Sci, 2024, 25: 25116042.
[23] Lankisch T O, Metzger J, Negm A A, et al. Bile proteomic profiles differentiate cholangiocarcinoma from primary sclerosing cholangitis and choledocholithiasis[J]. Hepatology, 2011, 53: 875-884.
[24] Yu Y, Yao Q, Chen D, et al. Serum metabonomics reveal the effectiveness of human placental mesenchymal stem cell therapy for primary sclerosing cholangitis[J]. Stem Cell Res Ther, 2024, 15: 346.
[25] Iwasawa K, Suda W, Tsunoda T, et al. Dysbiosis of the salivary microbiota in pediatric-onset primary sclerosing cholangitis and its potential as a biomarker[J]. Sci Rep, 2018, 8: 5480.
[26] Shi H, Wang Q, Xu B, et al. Research on gut microbiota characteristics of PBC patients at different ALBI grades based on machine learning[J]. Front Microbiol, 2024, 15: 1495170.
[27] Liu Q, Huang B, Zhou Y, et al. Gut microbiome pattern impacts treatment response in primary biliary cholangitis[J]. Med, 2025, 6: 100504.
[28] Khendek L, Castro-Rojas C, Nelson C, et al. Quantitative fibrosis identifies biliary tract involvement and is associated with outcomes in pediatric autoimmune liver disease[J]. Hepatol Commun, 2025, 9: 0594.
[29] Hu J, Wu Y, Zhang D, et al. Regulatory T cells-related gene in primary sclerosing cholangitis: evidence from Mendelian randomization and transcriptome data[J]. Genes Immunity, 2024, 25: 492-513.
[30] Wacker E M, Uellendahl-Werth F, Bej S, et al. Whole blood RNA sequencing identifies transcriptional differences between primary sclerosing cholangitis and ulcerative colitis[J]. JHEP Rep, 2024, 6: 100988.
[31] 邓垂文. T细胞免疫检查点CD226/TIGIT在原发性胆汁性胆管炎发病机制中的作用研究[D]. 北京: 中国医学科学院北京协和医学院, 2021.
[32] 王一. 基于健康体检自身免疫性肝病高危人群早期筛查方案的建立和验证及家族遗传易感性研究[D]. 天津: 天津医科大学, 2019.
[33] da Silva B C, Kronbauer A H, Chebli J M F, et al. Predictive modeling for colectomy risk in patients with ulcerative colitis and primary sclerosing cholangitis: a brazilian multicentric study utilizing machine learning[J]. J Crohns Colitis, 2025, 19: 1155.
[34] Gerussi A, Verda D, Cappadona C, et al. LLM-PBC: logic learning machine-based explainable rules accurately stratify the genetic risk of primary biliary cholangitis[J]. J Pers Med, 2022, 12: 1587.
[35] 陈旭. 基于CT的影像组学预测自身免疫性肝病患者肝纤维化的初步研究[D]. 天津: 天津医科大学, 2021.
[36] Wei Q, Li W, He S, et al. An exploratory machine learning model for predicting advanced liver fibrosis in autoimmune hepatitis patients: a preliminary study[J]. Ann Hepatol, 2025, 30: 101754.
[37] Hu C, Iyer R K, Juran B D, et al. Predicting cholangiocarcinoma in primary sclerosing cholangitis: using artificial intelligence, clinical and laboratory data[J]. BMC Gastroenterol, 2023, 23: 129.
[38] Singh Y, Jons W A, Eaton J E, et al. Algebraic topology-based machine learning using MRI predicts outcomes in primary sclerosing cholangitis[J]. Eur Radiol Exp, 2022, 6: 58.
[39] Singh Y, Faghani S, Eaton J E, et al. Deep learning-based prediction of hepatic decompensation in patients with primary sclerosing cholangitis with computed tomography[J]. Mayo Clin Proc Digit Health, 2024, 2: 470-476.
[40] Singh Y, Eaton J E, Venkatesh S K, et al. Computed tomography-based radiomics and body composition model for predicting hepatic decompensation[J]. Oncotarget, 2024, 15: 809-813.
[41] Eaton J E, Vesterhus M, Mccauley B M, et al. Primary sclerosing cholangitis risk estimate tool (PREsTo) predicts outcomes of the disease: a derivation and validation study using machine learning[J]. Hepatology, 2020, 71: 214-224.
[42] Mousa O Y, Juran B D, Mccauley B M, et al. Bile acid profiles in primary sclerosing cholangitis and their ability to predict hepatic decompensation[J]. Hepatology, 2021, 74: 281-295.
[43] Zhao X, Naghibzadeh M, Sun Y, et al. Machine learning prediction model of waitlist outcomes in patients with primary sclerosing cholangitis[J]. Transplant Direct, 2025, 11: e1774.
[44] Sjöblom N, Boyd S, Manninen A, et al. Automated image analysis of keratin 7 staining can predict disease outcome in primary sclerosing cholangitis[J]. Hepatol Res, 2023, 53: 322-333.
[45] Fu X Y, Song Y Q, Lin J Y, et al. Developing a prognostic model for primary biliary cholangitis based on a random survival forest model[J]. Int J Med Sci, 2024, 21: 61-69.
[46] Gerussi A, Verda D, Bernasconi D P, et al. Machine learning in primary biliary cholangitis: a novel approach for risk stratification[J]. Liver Int, 2022, 42: 615-627.
[47] Ferreira D, Neto C, Lopes J, et al. Predicting the survival of primary biliary cholangitis patients[J]. Appl Sci, 2022, 12: 8043.
[48] de Vries E M, Wang J, Williamson K D, et al. A novel prognostic model for transplant-free survival in primary sclerosing cholangitis[J]. Gut, 2018, 67: 1864-1869.
[49] Kimura N, Takahashi K, Setsu T, et al. Machine learning prediction model for treatment responders in patients with primary biliary cholangitis[J]. JGH Open, 2023, 7: 431-438.
[50] Kimura N, Takahashi K, Setsu T, et al. Development and validation of machine learning model for predicting treatment responders in patients with primary biliary cholangitis[J]. Hepatol Res, 2024, 54: 67-77.
[51] 王凯玲. 原发性胆汁性胆管炎熊去氧胆酸应答不佳的预测模型研究[D]. 长沙: 中南大学, 2022.
[52] Shahini E, Pasculli G, Mastropietro A, et al. Network proximity-based drug repurposing strategy for early and late stages of primary biliary cholangitis[J]. Biomedicines, 2022, 10: 1694.
[53] Hu C, Saboo K V, Ali A H, et al. REMEDI: REinforcement learning-driven adaptive MEtabolism modeling of primary sclerosing cholangitis DIsease progression[C]//Machine learning for Health Symposium (ML4H) 2023. Procecdings of Machine Learning Research, 2023, 225: 157-189.