摘要:

我國(guó)器官捐獻(xiàn)與移植事業(yè)發(fā)展迅速，已躍居成為世界第二捐獻(xiàn)與移植大國(guó)，但是器官移植數(shù)量和質(zhì)量仍有待進(jìn)一步提高，以滿(mǎn)足廣大等待移植受者需求。人工智能（AI）支持多源臨床大數(shù)據(jù)的整合、分析與應(yīng)用，能夠輔助拓展可用供器官、提升移植物質(zhì)量，為緩解移植器官供需失衡提供新的技術(shù)基礎(chǔ)。為規(guī)范AI在我國(guó)器官捐獻(xiàn)與移植全流程的輔助應(yīng)用，現(xiàn)組織多學(xué)科專(zhuān)家制定《中國(guó)器官移植AI輔助臨床決策專(zhuān)家共識(shí)》，通過(guò)構(gòu)建統(tǒng)一的數(shù)據(jù)與模型要求，形成覆蓋供者評(píng)估維護(hù)及器官匹配、器官保存與轉(zhuǎn)運(yùn)、器官移植手術(shù)和術(shù)后受者管理等全流程器官捐獻(xiàn)與移植臨床場(chǎng)景的技術(shù)框架，并規(guī)范倫理法規(guī)約束與責(zé)任主體邊界，以進(jìn)一步提升AI輔助器官捐獻(xiàn)與移植工作的規(guī)范化、安全化水平，促進(jìn)我國(guó)器官捐獻(xiàn)與移植事業(yè)的高質(zhì)量發(fā)展。

Abstract:

Organ donation and transplantation in China have developed rapidly, ranking second in the world in terms of both donation and transplantation volume. However, both the quantity and quality of organ transplants remain to be further improved to satisfy the demands of the vast number of recipients awaiting transplantation. Artificial intelligence (AI) facilitates the integration, analysis, and application of multi-source clinical big data. It is capable of assisting in expanding the pool of available donor organs and enhancing graft quality, thereby providing a novel technological foundation for alleviating the imbalance between the supply and demand of transplant organs. To standardize the auxiliary application of AI throughout the entire process of organ donation and transplantation in China, a team of multidisciplinary experts were convened to formulate the Chinese Expert Consensus on AI-Assisted Clinical Decision-Making in Organ Transplantation. By establishing unified requirements for data and models, this consensus forms a technical framework covering clinical scenarios across the entire workflow of organ donation and transplantation, including donor assessment and maintenance, organ matching, organ preservation and transport, transplant surgery, and post-transplant recipient management. Furthermore, it clarifies ethical and regulatory constraints as well as the boundaries of responsibility subjects. The aim is to further enhance the standardization and safety of AI-assisted organ donation and transplantation, ultimately promoting the high-quality development of this field in China.

圖  1   AI輔助全流程器官捐獻(xiàn)與移植服務(wù)技術(shù)體系

Figure  1.   AI-assisted full-process organ donation and transplantation service technology system

[1] 國(guó)家衛(wèi)生健康委員會(huì). 2022年國(guó)家醫(yī)療服務(wù)與質(zhì)量安全報(bào)告[M]. 北京: 科學(xué)技術(shù)文獻(xiàn)出版社, 2023. [2]

ANDERSON D J, LOCKE J E. Progress towards solving the donor organ shortage[J]. Nat Rev Nephrol, 2023, 19(2): 83-84. DOI: 10.1038/s41581-022-00664-y.

[3]

LOUPY A, PREKA E, CHEN X, et al. Reshaping transplantation with AI, emerging technologies and xenotransplantation[J]. Nat Med, 2025, 31(7): 2161-2173. DOI: 10.1038/s41591-025-03801-9.

[4]

SPANN A, STRAUSS A T, DAVIS S E, et al. The role of artificial intelligence in chronic liver diseases and liver transplantation[J]. Gastroenterology, 2025, 169(3): 456-470. DOI: 10.1053/j.gastro.2025.05.012.

[5] 中華人民共和國(guó)國(guó)務(wù)院. 人體器官捐獻(xiàn)和移植條例[EB/OL]. (2023-12-14) [2025-10-27]. https://www.gov.cn/zhengce/content/202312/content_6920195.htm. [6] 國(guó)家衛(wèi)生健康委. 人體器官移植技術(shù)臨床應(yīng)用管理規(guī)定[EB/OL]. (2024-04-19) [2025-10-27]. https://zwfw.nhc.gov.cn/kzx/zcfg/yljgrtqgyzzyzgddsp_240/202408/t20240815_2832.html xxgkhide=1. [7]

HOSSEINZADEH E, AFKANPOUR M, MOMENI M, et al. Data quality assessment in healthcare, dimensions, methods and tools: a systematic review[J]. BMC Med Inform Decis Mak, 2025, 25(1): 296. DOI: 10.1186/s12911-025-03136-y.

[8]

RICHESSON R L, KRISCHER J. Data standards in clinical research: gaps, overlaps, challenges and future directions[J]. J Am Med Inform Assoc, 2007, 14(6): 687-696. DOI: 10.1197/jamia.M2470.

[9]

YU M, KING K L, ALI HUSAIN S, et al. Discrepant outcomes between national kidney transplant data registries in the United States[J]. J Am Soc Nephrol, 2023, 34(11): 1863-1874. DOI: 10.1681/ASN.0000000000000194.

[10]

FARRIS A B, MOGHE I, WU S, et al. Banff Digital Pathology Working Group: going digital in transplant pathology[J]. Am J Transplant, 2020, 20(9): 2392-2399. DOI: 10.1111/ajt.15850.

[11]

PERAKSLIS E D, KNECHTLE S J, MCCOURT B, et al. Doing it right: caring for and protecting patient information for US organ donors and transplant recipients[J]. Patterns, 2023, 4(4): 100734. DOI: 10.1016/j.patter.2023.100734.

[12] 國(guó)家藥品監(jiān)督管理局. 人工智能醫(yī)療器械 質(zhì)量要求和評(píng)價(jià) 第2部分: 數(shù)據(jù)集通用要求: YY/T 1833.2—2022[S]. 北京: 中國(guó)標(biāo)準(zhǔn)出版社, 2022. [13] 國(guó)家衛(wèi)生健康委辦公廳, 國(guó)家發(fā)展改革委辦公廳, 工業(yè)和信息化部辦公廳, 等. 關(guān)于促進(jìn)和規(guī)范“人工智能+醫(yī)療衛(wèi)生”應(yīng)用發(fā)展的實(shí)施意見(jiàn)[EB/OL]. (2025-10-20)[2025-10-27]. https://www.gov.cn/zhengce/zhengceku/202511/content_7047018.htm [14]

BHAT M, RABINDRANATH M, CHARA B S, et al. Artificial intelligence, machine learning, and deep learning in liver transplantation[J]. J Hepatol, 2023, 78(6): 1216-1233. DOI: 10.1016/j.jhep.2023.01.006.

[15]

BENEVENTO E, ALOINI D, VAN DER AALST W M P. How can interactive process discovery address data quality issues in real business settings? evidence from a case study in healthcare[J]. J Biomed Inform, 2022, 130: 104083. DOI: 10.1016/j.jbi.2022.104083.

[16] 國(guó)家藥品監(jiān)督管理局醫(yī)療器械技術(shù)審評(píng)中心. 人工智能醫(yī)療器械注冊(cè)審查指導(dǎo)原則[EB/OL]. (2022-03-10)[2025-10-27]. https://www.cncsdr.org/ggtz/ggzz/202203/t20220311_304188.html. [17] 中國(guó)醫(yī)療器械行業(yè)協(xié)會(huì). 深度學(xué)習(xí)輔助決策醫(yī)療器械軟件審評(píng)要點(diǎn)[EB/OL]. (2019-07-01)[2025-11-16]. https://www.mdcpp.com/doc/materialDownload/深度學(xué)習(xí)輔助決策醫(yī)療器械軟件審評(píng)要點(diǎn).pdf. [18] 國(guó)家藥品監(jiān)督管理局. 人工智能醫(yī)療器械質(zhì)量要求和評(píng)價(jià)第3部分: 數(shù)據(jù)標(biāo)注通用要求: YY/T 1833.3—2022[S]. 北京: 中國(guó)標(biāo)準(zhǔn)出版社, 2022. [19] 于蘭亦, 翟曉梅. 人工智能在臨床實(shí)踐中的創(chuàng)新應(yīng)用和倫理挑戰(zhàn)[J]. 數(shù)字醫(yī)學(xué)與健康, 2024, 2(2): 108-112. DOI: 10.3760/cma.j.cn101909-20231127-00073.

YU L Y, ZHAI X M. Innovative applications and ethical challenges of artificial intelligence in clinical practice[J]. Digit Med Health, 2024, 2(2): 108-112. DOI: 10.3760/cma.j.cn101909-20231127-00073.

[20]

EL-SAPPAGH S, ALONSO J M, RIAZUL ISLAM S M, et al. A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease[J]. Sci Rep, 2021, 11(1): 2660. DOI: 10.1038/s41598-021-82098-3.

[21]

LAMY J B, SEKAR B, GUEZENNEC G, et al. Explainable artificial intelligence for breast cancer: a visual case-based reasoning approach[J]. Artif Intell Med, 2019, 94: 42-53. DOI: 10.1016/j.artmed.2019.01.001.

[22]

LIU Y, YU W, DILLON T. Regulatory responses and approval status of artificial intelligence medical devices with a focus on China[J]. NPJ Digit Med, 2024, 7(1): 255. DOI: 10.1038/s41746-024-01254-x.

[23]

KELLY C J, KARTHIKESALINGAM A, SULEYMAN M, et al. Key challenges for delivering clinical impact with artificial intelligence[J]. BMC Med, 2019, 17(1): 195. DOI: 10.1186/s12916-019-1426-2.

[24]

SHEN T, LI Y, CAO Y, et al. Rapid deployment of large language model DeepSeek in Chinese hospitals demands a regulatory response[J]. Nat Med, 2025, 31(10): 3233-3238. DOI: 10.1038/s41591-025-03836-y.

[25]

ROSCHEWITZ M, MEHTA R, JONES C, et al. Automatic dataset shift identification to support safe deployment of medical imaging AI[C]//Medical Image Computing and Computer Assisted Intervention – MICCAI 2025. Cham: Springer, 2026: 67-76. DOI: 10.1007/978-3-032-04981-0_7.

[26]

BEDI S, LIU Y, ORR-EWING L, et al. Testing and evaluation of health care applications of large language models: a systematic review[J]. JAMA, 2025, 333(4): 319-328. DOI: 10.1001/jama.2024.21700.

[27]

PAL A, UMAPATHI L K, SANKARASUBBU M. Med-HALT: medical domain hallucination test for large language models[C]//Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL). Singapore. Stroudsburg, PA, USA: ACL, 2023: 314-334. DOI: 10.18653/v1/2023.conll-1.21.

[28]

NG K K Y, MATSUBA I, ZHANG P C. RAG in health care: a novel framework for improving communication and decision-making by addressing LLM limitations[J]. Nejm Ai, 2025, 2(1): 1-12. DOI: 10.1056/aira2400380.

[29] 國(guó)家衛(wèi)生健康委辦公廳, 國(guó)家中醫(yī)藥局綜合司, 國(guó)家疾控局綜合司. 衛(wèi)生健康行業(yè)人工智能應(yīng)用場(chǎng)景參考指引[EB/OL]. (2024-11-14) [2025-10-27]. https://www.nhc.gov.cn/guihuaxxs/c100133/202411/3dee425b8dc34f739d63483c4e5c334c.shtml. [30]

MONTGOMERY A E, RANA A. Current state of artificial intelligence in liver transplantation[J]. Transplant Rep, 2025, 10(2): 100173. DOI: 10.1016/j.tpr.2025.100173.

[31]

SCHATTENBERG J M, CHALASANI N, ALKHOURI N. Artificial intelligence applications in hepatology[J]. Clin Gastroenterol Hepatol, 2023, 21(8): 2015-2025. DOI: 10.1016/j.cgh.2023.04.007.

[32]

TSCHUOR C, FERRARESE A, KUEMMERLI C, et al. Allocation of liver grafts worldwide–is there a best system?[J]. J Hepatol, 2019, 71(4): 707-718. DOI: 10.1016/j.jhep.2019.05.025.

[33]

JEONG J G, CHOI S, KIM Y J, et al. Deep 3D attention CLSTM U-Net based automated liver segmentation and volumetry for the liver transplantation in abdominal CT volumes[J]. Sci Rep, 2022, 12: 6370. DOI: 10.1038/s41598-022-09978-0.

[34]

SHAVER C M, REESE P P, GRIESEMER A, et al. Scientific advances in the assessment, modification, and generation of transplantable organs for patients with end-stage organ diseases[J]. Lancet, 2025, 406(10501): 376-388. DOI: 10.1016/S0140-6736(25)00239-9.

[35]

BERRY P, KOTHA S. The fundamental importance of exploring the risks alongside the benefits of artificial intelligence[J]. J Hepatol, 2024, 80(5): e223-e225. DOI: 10.1016/j.jhep.2023.06.020.

[36]

SCHWANTES I R, AXELROD D A. Technology-enabled care and artificial intelligence in kidney transplantation[J]. Curr Transplant Rep, 2021, 8(3): 235-240. DOI: 10.1007/s40472-021-00336-z.

[37]

SENANAYAKE S, WHITE N, GRAVES N, et al. Machine learning in predicting graft failure following kidney transplantation: a systematic review of published predictive models[J]. Int J Med Inform, 2019, 130: 103957. DOI: 10.1016/j.ijmedinf.2019.103957.

[38]

NAKAYAMA T, SASAKI K. Advanced viability assessment in machine perfusion: what lies ahead?[J]. EBioMedicine, 2024, 108: 105351. DOI: 10.1016/j.ebiom.2024.105351.

[39]

WANG S, YANG M, LIU Y, et al. Aortic pressure control based on deep reinforcement learning for ex vivo heart perfusion[J]. Appl Sci, 2024, 14(19): 8735. DOI: 10.3390/app14198735.

[40]

SAGE A T, DONAHOE L L, SHAMANDY A A, et al. A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization[J]. Nat Commun, 2023, 14(1): 4810. DOI: 10.1038/s41467-023-40468-7.

[41]

DUMBILL R, KNIGHT S, HUNTER J, et al. Prolonged normothermic perfusion of the kidney prior to transplantation: a historically controlled, phase 1 cohort study[J]. Nat Commun, 2025, 16(1): 4584. DOI: 10.1038/s41467-025-59829-5.

[42]

MANTECCHINI L, PAGANELLI F, MORABITO V, et al. Transportation of organs by air: safety, quality, and sustainability criteria[J]. Transplant Proc, 2016, 48(2): 304-308. DOI: 10.1016/j.transproceed.2015.12.050.

[43]

TALMALE G, SHRAWANKAR U. Dynamic clustered hierarchical real time task assignment & resource management for IoT based smart human organ transplantation system[C]//2017 Conference on Emerging Devices and Smart Systems (ICEDSS). Mallasamudram, India. IEEE, 2017: 103-109. DOI: 10.1109/ICEDSS.2017.8073667.

[44]

CAO Y, WANG Y, LIU H, et al. Artificial intelligence revolutionizing anesthesia management: advances and prospects in intelligent anesthesia technology[J]. Front Med, 2025, 12: 1571725. DOI: 10.3389/fmed.2025.1571725.

[45]

CESARETTI M, BRUSTIA R, GOUMARD C, et al. Use of artificial intelligence as an innovative method for liver graft macrosteatosis assessment[J]. Liver Transpl, 2020, 26(10): 1224-1232. DOI: 10.1002/lt.25801.

[46]

OH N, LIM M, KIM B, et al. AI-assisted intraoperative navigation for safe right liver mobilization in pure laparoscopic donor hepatectomy: an experimental multi-institutional validation study[J]. Sci Rep, 2025, 15(1): 27935. DOI: 10.1038/s41598-025-11627-1.

[47]

CHEN X, XU H, QI Q, et al. AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels[J]. Front Oncol, 2022, 12: 1021084. DOI: 10.3389/fonc.2022.1021084.

[48]

BELLINI V, GUZZON M, BIGLIARDI B, et al. Artificial intelligence: a new tool in operating room management. role of machine learning models in operating room optimization[J]. J Med Syst, 2019, 44(1): 20. DOI: 10.1007/s10916-019-1512-1.

[49]

SLAGTER J S, OUTMANI L, TRAN K T C K, et al. Robot-assisted kidney transplantation as a minimally invasive approach for kidney transplant recipients: a systematic review and meta-analyses[J]. Int J Surg, 2022, 99: 106264. DOI: 10.1016/j.ijsu.2022.106264.

[50]

KHALIEL F H, HAQ M I, ALSULBUD A K, et al. “First-in-human” totally robotic orthotopic heart transplant[J]. J Heart Lung Transplant, 2025, 44(6): 1000-1003. DOI: 10.1016/j.healun.2025.02.1685.

[51]

SONE K, TANIMOTO S, TOYOHARA Y, et al. Evolution of a surgical system using deep learning in minimally invasive surgery (Review)[J]. Biomed Rep, 2023, 19(1): 45. DOI: 10.3892/br.2023.1628.

[52]

YILMAZ R, BAKHAIDAR M, ALSAYEGH A, et al. 828 real-time artificial intelligence instruction in comparison to human expert instruction in surgical technical skills teaching–a randomized controlled trial[J]. Br J Surg, 2023, 110(Supplement_7): znad258.077. DOI: 10.1093/bjs/znad258.077.

[53]

LUONGO F, HAKIM R, NGUYEN J H, et al. Deep learning-based computer vision to recognize and classify suturing gestures in robot-assisted surgery[J]. Surgery, 2021, 169(5): 1240-1244. DOI: 10.1016/j.surg.2020.08.016.

[54]

KIYASSEH D, MA R, HAQUE T F, et al. A vision transformer for decoding surgeon activity from surgical videos[J]. Nat Biomed Eng, 2023, 7(6): 780-796. DOI: 10.1038/s41551-023-01010-8.

[55]

BAE S, MASSIE A B, CAFFO B S, et al. Machine learning to predict transplant outcomes: helpful or hype? a national cohort study[J]. Transpl Int, 2020, 33(11): 1472-1480. DOI: 10.1111/tri.13695.

[56]

MALDONADO A Q, WEST-THIELKE P, JOYAL K, et al. Advances in personalized medicine and noninvasive diagnostics in solid organ transplantation[J]. Pharmacotherapy, 2021, 41(1): 132-143. DOI: 10.1002/phar.2484.

[57]

SCARDONI A, BALZARINI F, SIGNORELLI C, et al. Artificial intelligence-based tools to control healthcare associated infections: a systematic review of the literature[J]. J Infect Public Health, 2020, 13(8): 1061-1077. DOI: 10.1016/j.jiph.2020.06.006.

[58]

GRSKOVIC M, HILLER D J, EUBANK L A, et al. Validation of a clinical-grade assay to measure donor-derived cell-free DNA in solid organ transplant recipients[J]. J Mol Diagn, 2016, 18(6): 890-902. DOI: 10.1016/j.jmoldx.2016.07.003.

[59]

O’CONNELL P J, ZHANG W, MENON M C, et al. Biopsy transcriptome expression profiling to identify kidney transplants at risk of chronic injury: a multicentre, prospective study[J]. Lancet, 2016, 388(10048): 983-993. DOI: 10.1016/S0140-6736(16)30826-1.

[60]

WOILLARD J B, LABRIFFE M, DEBORD J, et al. Tacrolimus exposure prediction using machine learning[J]. Clin Pharmacol Ther, 2021, 110(2): 361-369. DOI: 10.1002/cpt.2123.

[61]

LIPKOVA J, CHEN T Y, LU M Y, et al. Deep learning-enabled assessment of cardiac allograft rejection from endomyocardial biopsies[J]. Nat Med, 2022, 28(3): 575-582. DOI: 10.1038/s41591-022-01709-2.

[62]

RAYNAUD M, AUBERT O, DIVARD G, et al. Dynamic prediction of renal survival among deeply phenotyped kidney transplant recipients using artificial intelligence: an observational, international, multicohort study[J]. Lancet Digit Health, 2021, 3(12): e795-e805. DOI: 10.1016/S2589-7500(21)00209-0.

[63]

LOUPY A, COUTANCE G, BONNET G, et al. Identification and characterization of trajectories of cardiac allograft vasculopathy after heart transplantation: a population-based study[J]. Circulation, 2020, 141(24): 1954-1967. DOI: 10.1161/CIRCULATIONAHA.119.044924.

[64]

OLAWADE D B, MARINZE S, QURESHI N, et al. The impact of artificial intelligence and machine learning in organ retrieval and transplantation: a comprehensive review[J]. Curr Res Transl Med, 2025, 73(2): 103493. DOI: 10.1016/j.retram.2025.103493.

[65]

VIVEK K, PAPALOIS V. AI and machine learning in transplantation[J]. Transplantology, 2025, 6(3): 23. DOI: 10.3390/transplantology6030023.

[66]

DE CANNIèRE H, CORRADI F, SMEETS C J P, et al. Wearable monitoring and interpretable machine learning can objectively track progression in patients during cardiac rehabilitation[J]. Sensors, 2020, 20(12): 3601. DOI: 10.3390/s20123601.

[67]

HASSAN M K, EL DESOUKY A I, ELGHAMRAWY S M, et al. A Hybrid real-time remote monitoring framework with NB-WOA algorithm for patients with chronic diseases[J]. Future Gener Comput Syst, 2019, 93: 77-95. DOI: 10.1016/j.future.2018.10.021.

[68]

ENDO Y, SASAKI K, MOAZZAM Z, et al. Quality of ChatGPT responses to questions related to liver transplantation[J]. J Gastrointest Surg, 2023, 27(8): 1716-1719. DOI: 10.1007/s11605-023-05714-9.

[69]

SINGLA R, LODHI S, KIBRET T, et al. Accuracy, clarity, and comprehensiveness of ChatGPT outputs for commonly asked questions about living kidney donation[J]. Clin Transplant, 2025, 39(9): e70303. DOI: 10.1111/ctr.70303.

[70] 國(guó)家衛(wèi)生健康委辦公廳, 國(guó)家中醫(yī)藥局綜合司, 國(guó)家疾控局綜合司. 關(guān)于進(jìn)一步加強(qiáng)醫(yī)療機(jī)構(gòu)電子病歷信息使用管理的通知[EB/OL]. (2025-06-23) [2025-10-27]. https://www.nhc.gov.cn/yzygj/c100068/202506/c68abee7c54b4651a774cd533761780b.shtml. [71]

Penn LPS Online. The importance of ethical considerations in research and clinical trials [EB/OL]. (2024-7-30) [2025-10-15]. https://lpsonline.sas.upenn.edu/features/importance-ethical-considerations-research-and-clinical-trials.

[72]

EGUIA H, SáNCHEZ-BOCANEGRA C L, VINCIARELLI F, et al. Clinical decision support and natural language processing in medicine: systematic literature review[J]. J Med Internet Res, 2024, 26: e55315. DOI: 10.2196/55315.

[73]

U. S. Department of Energy. Generative Artificial Intelligence Reference Guide (Version 2) [EB/OL]. (2024-06-14) [2025-10-15]. https://www.energy.gov/sites/default/files/2024-06/Generative%20AI%20Reference%20Guide%20v2%206-14-24.pdf.

相關(guān)知識(shí)

香港維爾利健康科技集團(tuán)發(fā)布AI臨床輔助決策引擎V
頂尖專(zhuān)家齊聚武漢，共話(huà)器官移植新進(jìn)展
智能臨床輔助決策支持系統(tǒng)
專(zhuān)家論壇｜楊揚(yáng)：人工智能在肝移植中的應(yīng)用
國(guó)家衛(wèi)生健康委關(guān)于印發(fā)人體器官移植技術(shù)臨床應(yīng)用管理規(guī)定的通知
AI輔助病理學(xué)家工具連接臨床研究與臨床護(hù)理
克隆器官移植后的功能恢復(fù)策略
AI臨床助手ACA
【專(zhuān)家共識(shí)】卒中后失語(yǔ)臨床管理專(zhuān)家共識(shí)（2022）
2024年AI輔助醫(yī)療決策

網(wǎng)址: 中國(guó)器官移植AI輔助臨床決策專(zhuān)家共識(shí) http://m.gysdgmq.cn/newsview1931654.html