PDF下载 ( 801 KB)
代谢相关脂肪性肝病的智能诊疗与数字健康综合管理
DOI: 10.12449/JCH260422
利益冲突声明：本文不存在任何利益冲突。
作者贡献声明：蒋晔玮负责设计论文框架，起草论文，修改论文；徐蕴怡、苟明阳、乔王宇负责实施研究过程，起草论文；何钰茹负责数据收集，绘制图表；周婧琪负责拟定写作思路，指导撰写文章并最后定稿。
Intelligent diagnosis and treatment and comprehensive digital health management of metabolic dysfunction-associated fatty liver disease
-
摘要: 代谢相关脂肪性肝病（MAFLD）已成为全球范围内最常见的慢性肝病之一，构成严峻的公共卫生挑战。在此背景下，融合人工智能技术，特别是机器学习的智能诊疗和数字健康干预，能够突破传统方法局限，高效筛选关键基因、生物标志物、生化代谢等多维度数据，实现MAFLD风险预测、亚型识别、疗效评估等革命性突破。本文系统综述了机器学习模型在驱动MAFLD临床诊断革新与精准风险预测中的突破性应用；全面比较并分析了国内外MAFLD数字健康实践案例，深入剖析其在研究对象、干预方式及管理团队等方面的优势与局限。研究表明，数字健康与MAFLD长期管理的深度整合，正成为推动疾病管理模式向智能化、个体化、精准化转型的核心动力，但也存在诸多伦理技术问题亟待解决。Abstract: Metabolic dysfunction-associated fatty liver disease （MAFLD） has become one of the most prevalent chronic liver diseases worldwide， posing a serious challenge to public health. In this context， the integration of artificial intelligence （AI）， especially intelligent diagnosis and treatment and digital health interventions based on machine learning， can break through the limitations of traditional methods， realize efficient screening of multi-dimensional data such as key genes， biomarkers， and biochemical metabolites， and achieve revolutionary breakthroughs in risk prediction， subtype identification， and therapeutic effect assessment for MAFLD. This article systematically reviews the ground-breaking application of machine learning models in driving the innovation of clinical diagnosis and precise risk prediction of MAFLD， conducts a comprehensive comparative analysis of digital health practice cases of MAFLD in China and globally， and deeply analyzes their advantages and limitations in terms of research subjects， interventions， and management team. Studies have shown that the deep integration of digital health and long-term management of MAFLD is becoming the key engine driving the transformation of disease management modes towards an intelligent， individualized， and precise era， but there are various ethical and technical issues that need to be addressed urgently.
-
表 1 现有MAFLD数字健康研究的监测指标对比
Table 1. A comparison and collation of the monitoring indicators for current digital health research on MAFLD
指标类型 代表指标 优势 局限性 人体测量学 体重、BMI、腰围 简便、低成本 精度有限，标准化不足 身体成分分析 肌肉量、内脏脂肪［35，47，49］ 精准评估肥胖与少肌症 设备要求高，不易普及 临床评估 病史［35，39，41，49］、血压 识别心血管风险 回忆偏倚，瞬时因素干扰 血液生化 肝酶、代谢指标［40，42，46］、炎症
［44］、凝血［30，35，37］全面反映代谢与炎症状态 部分新型标志物（如PRO-
C3［44］、CK-18［35］）成本高，未经
临床验证影像学 MRI-PDFF［35，47-48］、超声［28］、瞬时弹
性成像［34，44］、CAP［26，34，47］、肝硬度
测量［42，45-47］MRI-PDFF是肝脂肪变性的无创
定量金标准；新兴技术可实现床
旁快速检测超声灵敏度有限，MRI成本高；
新兴技术的准确度难以保证组织学 肝活检［35］ 诊断精准 有创、成本高，且临床难以推广 风险评分 FLI［44，49，51］、FIB-4指数［35，37，45，47］、
APRI［44］多指标整合，无创评估 部分风险评分对晚期肝纤维化
识别性能不足行为与功能 体力活动、睡眠［35］、心理量表［34，43］、
心肺功能［35，48］、疼痛评估［41，47］贴近干预目标，主观与客观相结合 部分量表与评估缺乏统一标准 注：MAFLD，代谢相关脂肪性肝病；BMI，体重指数；PRO-C3，人Ⅲ型胶原前肽；CK-18，细胞角蛋白18；MRI-PDFF，磁共振质子密度脂肪分数；CAP，受控衰减参数；FLI，肝脂肪指数；APRI，天冬氨酸转氨酶与血小板比值指数。
下载: 导出CSV
-
[1] ZHOU JH, SUN DQ, TARGHER G, et al. Metabolic dysfunction-associated fatty liver disease increases risk of chronic kidney disease: A systematic review and meta-analysis[J]. eGastroenterology, 2023, 1( 1): e100005. DOI: 10.1136/egastro-2023-100005. [2] FAN JG, YANG R. Global prevalence trends and disease burden of non-alcoholic fatty liver disease[J]. Chin J Dig, 2023, 43( 4): 248- 252. DOI: 10.3760/cma.j.cn311367-20230202-00038.范建高, 杨荣. 全球非酒精性脂肪性肝病的流行趋势与疾病负担[J]. 中华消化杂志, 2023, 43( 4): 248- 252. DOI: 10.3760/cma.j.cn311367-20230202-00038. [3] ESLAM M, FAN JG, YU ML, et al. The Asian Pacific Association for the study of the liver clinical practice guidelines for the diagnosis and management of metabolic dysfunction-associated fatty liver disease[J]. Hepatol Int, 2025, 19( 2): 261- 301. DOI: 10.1007/s12072-024-10774-3. [4] YANG B, ZHANG R. Progress on the treatment of metabolic associated fatty liver disease[J/CD]. Chin J Liver Dis(Electronic Version), 2024, 16( 4): 25- 30. DOI: 10.3969/j.issn.1674-7380.2024.04.004.杨彬, 张瑞. 代谢相关脂肪性肝病治疗进展[J/CD]. 中国肝脏病杂志(电子版), 2024, 16( 4): 25- 30. DOI: 10.3969/j.issn.1674-7380.2024.04.004. [5] ZENG MH, SHI QY, XU L, et al. Establishment and validation of an adherence prediction system for lifestyle interventions in non-alcoholic fatty liver disease[J]. World J Gastroenterol, 2024, 30( 10): 1393- 1404. DOI: 10.3748/wjg.v30.i10.1393. [6] XIE TA, LIUFU LL, CHEN HJ, et al. Trends in the applications of artificial intelligence in fatty liver diseases[J]. Hepatol Int, 2025, 19( 5): 1109- 1120. DOI: 10.1007/s12072-025-10827-1. [7] XU XQ, LI J, FU YQ, et al. A plasma metabolome-derived model predicts severe liver outcomes of nonalcoholic fatty liver disease in the UK Biobank[J]. Diabetes Obes Metab, 2025, 27( 9): 4903- 4914. DOI: 10.1111/dom.16533. [8] MAMANDIPOOR B, WERNLY S, SEMMLER G, et al. Machine learning models predict liver steatosis but not liver fibrosis in a prospective cohort study[J]. Clin Res Hepatol Gastroenterol, 2023, 47( 7): 102181. DOI: 10.1016/j.clinre.2023.102181. [9] ZHANG YY, LI JE, ZENG HX, et al. Identification and validation of biomarkers in metabolic dysfunction-associated steatohepatitis using machine learning and bioinformatics[J]. Mol Genet Genomic Med, 2025, 13( 2): e70063. DOI: 10.1002/mgg3.70063. [10] WANG HN, CHENG W, HU P, et al. Integrative analysis identifies oxidative stress biomarkers in non-alcoholic fatty liver disease via machine learning and weighted gene co-expression network analysis[J]. Front Immunol, 2024, 15: 1335112. DOI: 10.3389/fimmu.2024.1335112. [11] QIN JT, CAO P, DING XX, et al. Machine learning identifies ferroptosis-related gene ANXA2 as potential diagnostic biomarkers for NAFLD[J]. Front Endocrinol, 2023, 14: 1303426. DOI: 10.3389/fendo.2023.1303426. [12] ABDURRACHIM D, LEK S, ONG CZL, et al. Utility of AI digital pathology as an aid for pathologists scoring fibrosis in MASH[J]. J Hepatol, 2025, 82( 5): 898- 908. DOI: 10.1016/j.jhep.2024.11.032. [13] JEON SK, JOO I, PARK J, et al. Automated hepatic steatosis assessment on dual-energy CT-derived virtual non-contrast images through fully-automated 3D organ segmentation[J]. Radiol Med, 2024, 129( 7): 967- 976. DOI: 10.1007/s11547-024-01833-8. [14] KWON H, KIM MG, OH S, et al. Application of quantitative ultrasonography and artificial intelligence for assessing severity of fatty liver: A pilot study[J]. Diagnostics(Basel), 2024, 14( 12): 1237. DOI: 10.3390/diagnostics14121237. [15] LIN HP, LEE HW, YIP TC, et al. Vibration-controlled transient elastography scores to predict liver-related events in steatotic liver disease[J]. JAMA, 2024, 331( 15): 1287- 1297. DOI: 10.1001/jama.2024.1447. [16] WANG XN, CHEN HH, WANG LQ, et al. Machine learning for predicting all-cause mortality of metabolic dysfunction-associated fatty liver disease: A longitudinal study based on NHANES[J]. BMC Gastroenterol, 2025, 25( 1): 376. DOI: 10.1186/s12876-025-03946-4. [17] YE JZ, ZHUANG XD, LI X, et al. Novel metabolic classification for extrahepatic complication of metabolic associated fatty liver disease: A data-driven cluster analysis with international validation[J]. Metabolism, 2022, 136: 155294. DOI: 10.1016/j.metabol.2022.155294. [18] VERMA N, VOJJALA N, MISHRA S, et al. Machine learning can guide suitability of consultation and patient referral through telemedicine for hepatobiliary diseases[J]. J Gastroenterol Hepatol, 2023, 38( 6): 999- 1007. DOI: 10.1111/jgh.16194. [19] ZAMANIAN H, SHALBAF A, ZALI MR, et al. Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review(2005-2023)[J]. Comput Methods Programs Biomed, 2024, 244: 107932. DOI: 10.1016/j.cmpb.2023.107932. [20] World Health Organization. Global strategy on digital health 2020- 2025[R/OL].( 2021-08-18)[ 2025-09-25]. Geneva: World Health Organization, 2021. https://www.who.int/publications/i/item/9789240020924. https://www.who.int/publications/i/item/9789240020924 [21] CHEN XH, HUANG J, HUANG Q, et al. Application of network support intervention in patients with nonalcoholic fatty liver disease[J]. Nurs Pract Res, 2014, 11( 7): 56- 57. DOI: 10.3969/j.issn.1672-9676.2014.07.028.陈小华, 黄健, 黄群, 等. 网络支持干预在非酒精性脂肪肝患者中的应用[J]. 护理实践与研究, 2014, 11( 7): 56- 57. DOI: 10.3969/j.issn.1672-9676.2014.07.028. [22] KWON OY, CHOI JY, JANG Y. The effectiveness of eHealth interventions on lifestyle modification in patients with nonalcoholic fatty liver disease: Systematic review and meta-analysis[J]. J Med Internet Res, 2023, 25: e37487. DOI: 10.2196/37487. [23] ZAFAR Y, SOHAIL MU, SAAD M, et al. eHealth interventions and patients with metabolic dysfunction-associated steatotic liver disease: A systematic review and meta-analysis[J]. BMJ Open Gastroenterol, 2025, 12( 1): e001670. DOI: 10.1136/bmjgast-2024-001670. [24] SAOKAEW S, KANCHANASURAKIT S, KOSITAMONGKOL C, et al. Effects of telemedicine on obese patients with non-alcoholic fatty liver disease: A systematic review and meta-analysis[J]. Front Med, 2021, 8: 723790. DOI: 10.3389/fmed.2021.723790. [25] SUN C, FAN JG. Effects of mobile health applications on lifestyle intervention for patients with nonalcoholic fatty liver disease[J]. Chin J Health Manage, 2023, 17( 10): 796- 800. DOI: 10.3760/cma.j.cn115624-20230615-00374.孙超, 范建高. 移动医疗应用程序干预非酒精性脂肪性肝病患者生活方式的效果[J]. 中华健康管理学杂志, 2023, 17( 10): 796- 800. DOI: 10.3760/cma.j.cn115624-20230615-00374. [26] LI J, HE TS, WANG P, et al. Application of PDCA health education management model on WeChat platform in patients with fatty liver[J]. J Qilu Nurs, 2018, 24( 4): 108- 110. DOI: 10.3969/j.issn.1006-7256.2018.04.049.李静, 何婷珊, 王鹏, 等. 微信平台PDCA健康教育管理模式在脂肪肝患者中的应用[J]. 齐鲁护理杂志, 2018, 24( 4): 108- 110. DOI: 10.3969/j.issn.1006-7256.2018.04.049. [27] WANG XJ, CHEN JC, JIAO LM, et al. Effect of internet-based health management intervention among college students with nonalcoholic fatty liver disease[J]. Chin J Public Health, 2017, 33( 6): 988- 990. DOI: 10.11847/zgggws2017-33-06-32.王雪娇, 陈基成, 焦凌梅, 等. 非酒精性脂肪肝大学生“互联网+”健康管理干预效果分析[J]. 中国公共卫生, 2017, 33( 6): 988- 990. DOI: 10.11847/zgggws2017-33-06-32. [28] DONG FY, ZHANG Y, HUANG YQ, et al. Long-term lifestyle interventions in middle-aged and elderly men with nonalcoholic fatty liver disease: A randomized controlled trial[J]. Sci Rep, 2016, 6: 36783. DOI: 10.1038/srep36783. [29] FARD SJ, GHODSBIN F, KAVIANI MJ, et al. The effect of follow up(telenursing) on liver enzymes in patients with nonalcoholic fatty liver disease: A randomized controlled clinical trial[J]. Int J Community Based Nurs Midwifery, 2016, 4( 3): 239- 246. [30] GHODSBIN F, JAVANMARDIFARD S, JAVAD KAVIANI M, et al. Effect of tele-nursing in the improving of the ultrasound findings in patients with nonalcoholic fatty liver diseases: A randomized clinical trial study[J]. Invest Educ Enferm, 2018, 36( 3). DOI: 10.17533/udea.iee.v36n3e09. [31] AXLEY P, KODALI S, KUO YF, et al. Text messaging approach improves weight loss in patients with nonalcoholic fatty liver disease: A randomized study[J]. Liver Int, 2018, 38( 5): 924- 931. DOI: 10.1111/liv.13622. [32] MAZZOTTI A, CALETTI MT, BRODOSI L, et al. An Internet-based approach for lifestyle changes in patients with NAFLD: Two-year effects on weight loss and surrogate markers[J]. J Hepatol, 2018, 69( 5): 1155- 1163. DOI: 10.1016/j.jhep.2018.07.013. [33] HALLSWORTH K, MCPHERSON S, ANSTEE QM, et al. Digital intervention with lifestyle coach support to target dietary and physical activity behaviors of adults with nonalcoholic fatty liver disease: Systematic development process of VITALISE using intervention mapping[J]. J Med Internet Res, 2021, 23( 1): e20491. DOI: 10.2196/20491. [34] TINCOPA MA, LYDEN A, WONG J, et al. Impact of a pilot structured mobile technology based lifestyle intervention for patients with nonalcoholic fatty liver disease[J]. Dig Dis Sci, 2022, 67( 2): 481- 491. DOI: 10.1007/s10620-021-06922-6. [35] STINE JG, SCHREIBMAN I, NAVABI S, et al. Nonalcoholic steatohepatitis Fitness Intervention in Thrombosis(NASHFit): Study protocol for a randomized controlled trial of a supervised aerobic exercise program to reduce elevated clotting risk in patients with NASH[J]. Contemp Clin Trials Commun, 2020, 18: 100560. DOI: 10.1016/j.conctc.2020.100560. [36] LIM SL, JOHAL J, ONG KW, et al. Lifestyle intervention enabled by mobile technology on weight loss in patients with nonalcoholic fatty liver disease: Randomized controlled trial[J]. JMIR Mhealth Uhealth, 2020, 8( 4): e14802. DOI: 10.2196/14802. [37] STINE JG, RIVAS G, HUMMER B, et al. Mobile health lifestyle intervention program leads to clinically significant loss of body weight in patients with NASH[J]. Hepatol Commun, 2023, 7( 4): e0052. DOI: 10.1097/HC9.0000000000000052. [38] CHO E, KIM S, KIM S, et al. The effect of mobile lifestyle intervention combined with high-protein meal replacement on liver function in patients with metabolic dysfunction-associated steatotic liver disease: A pilot randomized controlled trial[J]. Nutrients, 2024, 16( 14): 2254. DOI: 10.3390/nu16142254. [39] FREER CL, GEORGE ES, TAN SY, et al. Delivery of a telehealth supported home exercise program with dietary advice to increase plant-based protein intake in people with non-alcoholic fatty liver disease: A 12-week randomised controlled feasibility trial[J]. Br J Nutr, 2024, 131( 10): 1709- 1719. DOI: 10.1017/S0007114524000242. [40] FREER CL, GEORGE ES, TAN SY, et al. Acceptability and perceptions of a 12-week telehealth exercise programme with dietary advice to increase plant-based protein in people with non-alcoholic fatty liver disease: A programme evaluation using mixed methods[J]. BMJ Open, 2025, 15( 3): e086604. DOI: 10.1136/bmjopen-2024-086604. [41] KWON OY, LEE MK, LEE HW, et al. Mobile app-based lifestyle coaching intervention for patients with nonalcoholic fatty liver disease: Randomized controlled trial[J]. J Med Internet Res, 2024, 26: e49839. DOI: 10.2196/49839. [42] KAEWDECH A, ASSAWASUWANNAKIT S, CHURUANGSUK C, et al. Effect of smartphone-assisted lifestyle intervention in MASLD patients: A randomized controlled trial[J]. Sci Rep, 2024, 14: 13961. DOI: 10.1038/s41598-024-64988-4. [43] PFIRRMANN D, HUBER Y, SCHATTENBERG JM, et al. Web-based exercise as an effective complementary treatment for patients with nonalcoholic fatty liver disease: Intervention study[J]. J Med Internet Res, 2019, 21( 1): e11250. DOI: 10.2196/11250. [44] HUBER Y, PFIRRMANN D, GEBHARDT I, et al. Improvement of non-invasive markers of NAFLD from an individualised, web-based exercise program[J]. Aliment Pharmacol Ther, 2019, 50( 8): 930- 939. DOI: 10.1111/apt.15427. [45] AVERY L, SMITH H, MCPHERSON S, et al. Feasibility and acceptability of an evidence-informed digital intervention to support self-management in people with non-alcoholic fatty liver disease: Protocol for a non-randomised feasibility study(VITALISE)[J]. Pilot Feasibility Stud, 2023, 9( 1): 62. DOI: 10.1186/s40814-023-01286-2. [46] AVERY L, SMITH H, LIVINGSTON R, et al. Feasibility of a digital lifestyle intervention(VITALISE) to support weight loss in patients with MASLD in routine secondary care[J]. BMJ Open Gastroenterol, 2025, 12( 1): e001771. DOI: 10.1136/bmjgast-2025-001771. [47] BJÖRNSDOTTIR S, ULFSDOTTIR H, GUDMUNDSSON EF, et al. User engagement, acceptability, and clinical markers in a digital health program for nonalcoholic fatty liver disease: Prospective, single-arm feasibility study[J]. JMIR Cardio, 2024, 8: e52576. DOI: 10.2196/52576. [48] MOTZ V, FAUST A, DAHMUS J, et al. Utilization of a directly supervised telehealth-based exercise training program in patients with nonalcoholic steatohepatitis: Feasibility study[J]. JMIR Form Res, 2021, 5( 8): e30239. DOI: 10.2196/30239. [49] SONI J, PATHAK N, GHARIA M, et al. Effectiveness of RESET care program: A real-world-evidence on managing non-alcoholic fatty liver disease through digital health interventions[J]. World J Hepatol, 2025, 17( 1): 101630. DOI: 10.4254/wjh.v17.i1.101630. [50] ZHOU R, GU YP, ZHANG BB, et al. Digital therapeutics: Emerging new therapy for nonalcoholic fatty liver disease[J]. Clin Transl Gastroenterol, 2023, 14( 4): e00575. DOI: 10.14309/ctg.0000000000000575. [51] VILAR-GOMEZ E, ATHINARAYANAN SJ, ADAMS RN, et al. Post hoc analyses of surrogate markers of non-alcoholic fatty liver disease(NAFLD) and liver fibrosis in patients with type 2 diabetes in a digitally supported continuous care intervention: An open-label, non-randomised controlled study[J]. BMJ Open, 2019, 9( 2): e023597. DOI: 10.1136/bmjopen-2018-023597. [52] MO LF, LI Z, GAN HL, et al. Patient privacy and data security in medical artificial intelligence from a global perspective: Focus and strategies[J]. Acad J Nav Med Univ, 2025, 46( 8): 989- 999. DOI: 10.16781/j.CN31-2187/R.20250363.莫琳芳, 李喆, 甘辉亮, 等. 全球视野下医疗人工智能中患者隐私和数据安全: 焦点与策略[J]. 海军军医大学学报, 2025, 46( 8): 989- 999. DOI: 10.16781/j.CN31-2187/R.20250363. -
本文二维码
表(1)
计量
- 文章访问数: 756
- HTML全文浏览量: 150
- PDF下载量: 113
- 被引次数: 0
