Artificial intelligence (AI) processes complex data through machine learning algorithms, accelerates drug carrier development, predicts pharmacokinetic parameters, improves design efficiency and accuracy, and exhibts broad application prospects in drug delivery systems. Compared to traditional drug delivery systems which are time-consuming and laborious to design, AI empowerment greatly improves their practical application efficiency. This article reviews the application progress of AI in drug delivery systems. Firstly, the focus was on exploring AI enabled drug carrier design. Subsequently, the construction of AI models in drug formulation and release optimization was summarized, and the latest achievements in AI prediction of pharmacokinetics were analyzed. Finally, a summary and outlook were provided for the challenges faced by AI enabled drug delivery systems and future research directions.
胶束是具有纳米尺寸的聚合物颗粒,通过其增强渗透与滞留效应(enhanced permeability and retention, EPR)促进其在人体组织中的被动靶向[33].Kehrein等[34]先通过全原子分子动力学模拟,研究了基于聚2-噁唑啉和聚2-噁嗪的两亲性三嵌段共聚物胶束对姜黄素的超高负载特性,并通过ML方法对小模型系统中的单体进行聚类分析,进一步揭示了不同胶束区域的聚合物-药物相互作用差异.随后Kehrein课题组继续利用ML开发了预测聚合物胶束药物负载量的模型,整合了大量实验数据并建立了预测工具POxload[35].该工具通过多种描述符成功预测了药物负载效率和容量,准确率高达0.8,并通过虚拟筛选发现了新的潜在药物候选(图9).
JAINK K. An overview of drug delivery systems[J]. Methods in Molecular Biology, 2020, 2059: 1-54.
[2]
AALTONENP, KURVINENE. Introduction to the concepts: the past, present, and future of AI[M]//AALTONEN P, KURVINEN E. Contemporary issues in industry 5.0. Cham: Palgrave Macmillan, 2025: 3-28.
[3]
PANGG S, SHENC H, CAOL B, et al. Deep learning for anomaly detection: a review[J]. ACM Computing Surveys, 2022, 54(2): 1-38.
[4]
LÓPEZ-MONROYA P, GARCÍA-SALINASJ S. Neural networks and deep learning[M]//TORRES-GARCÍA A A, REYES-GARCÍA C A, VILLASEÑOR-PINEDA L, et al. Biosignal processing and classification using computational learning and intelligence: principles, algorithms and applications. Pittsburgh: Academic Press, 2022.
[5]
SEROVN, VINOGRADOVV. Artificial intelligence to bring nanomedicine to life[J/OL]. Advanced Drug Delivery Reviews, 2022, 184[2025-07-15]
[6]
HO D, WANGP, KEE T. Artificial intelligence in nanomedicine[J]. Nanoscale Horizons, 2019, 4(2): 365-377.
[7]
ZHAOF, WANGJ T, ZHANGY, et al. In vivo fate of targeted drug delivery carriers[J]. International Journal of Nanomedicine, 2024, 19: 6895-6929.
[8]
XIANGJ, ZHAOR, WANGB, et al. Advanced nano-carriers for anti-tumor drug loading[J/OL]. Frontiers in Oncology, 2021, 11[2025-07-15]
[9]
SAGDICK, EŞI, SITTIM, et al. Smart materials: rational design in biosystems via artificial intelligence[J]. Trends in Biotechnology, 2022, 40(8): 987-1003.
[10]
SUNL M, LIUH M, YEY Q, et al. Smart nanoparticles for cancer therapy[J/OL]. Signal Transduction and Targeted Therapy, 2023, 8[2025-07-15].
ZHANGM Q, GONGM C, CHENZ K, et al. Research progress of artificial intelligence and molecular simulation in drug design[J]. Herald of Medicine, 2024, 43(1): 78-84. (Ch).
[13]
VERMONDENT, KLUMPERMANB. The past, present and future of hydrogels[J]. European Polymer Journal, 2015, 72: 341-343.
[14]
NEGUTI, BITAB. Exploring the potential of artificial intelligence for hydrogel development:a short review[J/OL]. Gels, 2023, 9(11) [2025-07-15].
[15]
OWH C, HO D, LOHX J, et al. Towards machine learning for hydrogel drug delivery systems[J]. Trends in Biotechnology, 2023, 41(4): 476-479.
[16]
LIZ H, SONGP R, LIG F, et al. AI energized hydrogel design, optimization and application in biomedicine[J/OL]. Materials Today Bio, 2024, 25[2025-07-15].
[17]
WANGL R, ZHOUM Y, XUT L, et al. Multifunctional hydrogel as wound dressing for intelligent wound monitoring[J/OL]. Chemical Engineering Journal, 2022, 433[2025-07-15].
[18]
SHOKROLLAHIY, DONGP F, GAMAGEP T, et al. Finite element-based machine learning model for predicting the mechanical properties of composite hydrogels[J/OL]. Applied Sciences, 2022, 12(21)[2025-07-15].
[19]
HALD ALBERTSENC, KULKARNIJ A, WITZIGMANND, et al. The role of lipid components in lipid nanoparticles for vaccines and gene therapy[J/OL]. Advanced Drug Delivery Reviews, 2022, 188[2025-07-15].
[20]
EUGSTERR, ORSIM, BUTTITTAG, et al. Leveraging machine learning to streamline the development of liposomal drug delivery systems[J]. Journal of Controlled Release, 2024, 376: 1025-1038.
[21]
ROUCOH, DIAZ-RODRIGUEZP, RAMA-MOLINOSS, et al. Delimiting the knowledge space and the design space of nanostructured lipid carriers through artificial intelligence tools[J]. International Journal of Pharmaceutics, 2018, 553(1-2): 522-530.
[22]
KUMARIK, SINGHH R, SAMPATHM K. Enhanced amoxicillin delivery via artificial intelligence (AI)-based optimized lipid nanoparticles for Helicobacter pylori [J]. Biologia, 2025, 80(1): 133-148.
[23]
SURIYAAMPORNP, PAMORNPATHOMKULB, WONGPRAYOONP, et al. The artificial intelligence and design of experiment assisted in the development of progesterone-loaded solid-lipid nanoparticles for transdermal drug delivery[J]. Pharmacia, 2024, 71: 1-12.
[24]
WANGW, CHENK P, JIANGT, et al. Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery[J/OL]. Nature Communications, 2024, 15[2025-07-15].
[25]
GHOLAPA D, UDDINM J, FAIYAZUDDINM, et al. Advances in artificial intelligence for drug delivery and development: a comprehensive review[J/OL]. Computers in Biology and Medicine, 2024, 178[2025-07-15].
[26]
FATHIF, EBRAHIMIS N, PRIORJ A V, et al. Formulation of nano/micro-carriers loaded with an enriched extract of coffee silverskin: physicochemical properties, in vitro release mechanism and in silico molecular modeling[J/OL]. Pharmaceutics, 2022, 14(1) [2025-07-15].
[27]
AMASYAG, OZTURKC, AKSUB, et al. QbD based formulation optimization of semi-solid lipid nanoparticles as nano-cosmeceuticals[J/OL]. Journal of Drug Delivery Science and Technology, 2021, 66[2025-07-15].
[28]
DORSEYP J, LAUC L, CHANGT C, et al. Review of machine learning for lipid nanoparticle formulation and process development[J]. Journal of Pharmaceutical Sciences, 2024, 113(12): 3413-3433.
[29]
DASK P, CHANDRAJ. Nanoparticles and convergence of artificial intelligence for targeted drug delivery for cancer therapy: current progress and challenges[J/OL]. Frontiers in Medical Technology, 2022, 4[2025-07-15].
[30]
KNOXS T, WUK E, ISLAMN, et al. Self-driving laboratory platform for many-objective self-optimisation of polymer nanoparticle synthesis with cloud-integrated machine learning and orthogonal online analytics[J]. Polymer Chemistry, 2025, 16(12): 1355-1364.
[31]
DAMIATIS A, ROSSID, JOENSSONH N, et al. Artificial intelligence application for rapid fabrication of size-tunable PLGA microparticles in microfluidics[J/OL]. Scientific Reports, 2020, 10[2025-07-15].
[32]
DAMIATIS A, DAMIATIS. Microfluidic synthesis of indomethacin-loaded PLGA microparticles optimized by machine learning[J/OL]. Frontiers in Molecular Biosciences, 2021, 8[2025-07-15].
[33]
HATHOUTR M, MAHMOUDO A, ALID S, et al. Modeling drugs-PLGA nanoparticles interactions using Gaussian processes: Pharmaceutics informatics approach[J]. Journal of Cluster Science, 2022, 33(5): 2031-2036.
[34]
ZHENGY T, OZ Y, GUY M, et al. Rational design of polymeric micelles for targeted therapeutic delivery[J/OL]. Nano Today, 2024, 55[2025-07-15].
[35]
KEHREINJ, GÜRSÖZE, DAVIESM, et al. Unravel the tangle: Atomistic insight into ultrahigh curcumin-loaded polymer micelles[J/OL]. Small, 2023, 19(44) [2025-07-15].
[36]
KEHREINJ, BUNKERA, LUXENHOFERR. POxload: Machine learning estimates drug loadings of polymeric micelles[J]. Molecular Pharmaceutics, 2024, 21(7): 3356-3374.
[37]
XUJ S, LIAOK L, JIANGH X, et al. Research progress of novel inorganic nanometre materials carriers in nanomedicine for cancer diagnosis and treatment[J]. Artificial Cells, Nanomedicine, and Biotechnology, 2018, 46(sup3): 492-502.
[38]
JYAKHWOS, SEROVN, DMITRENKOA, et al. Machine learning reinforced genetic algorithm for massive targeted discovery of selectively cytotoxic inorganic nanoparticles[J/OL]. Small, 2024, 20(6)[2025-07-15].
[39]
AMINAS J, GUOB. A review on the synthesis and functionalization of gold nanoparticles as a drug delivery vehicle[J]. International Journal of Nanomedicine, 2020, 15: 9823-9857.
[40]
HUANGH Q, LIUR H, YANGJ, et al. Gold nanoparticles: construction for drug delivery and application in cancer immunotherapy[J/OL]. Pharmaceutics, 2023, 15(7)[2025-07-15].
[41]
YANX L, SEDYKHA, WANGW Y, et al. In silico profiling nanoparticles: predictive nanomodeling using universal nanodescriptors and various machine learning approaches[J]. Nanoscale, 2019, 11(17): 8352-8362.
[42]
ALEXEREES M I, YOUSSEFD, ABDEL-HARITHM. Using biospeckle and LIBS techniques with artificial intelligence to monitor phthalocyanine-gold nanoconjugates as a new drug delivery mediator for in vivo PDT[J/OL]. Journal of Photochemistry and Photobiology A: Chemistry, 2023, 440[2025-07-15].
[43]
GUN, ZHANGZ H, LIY. Adaptive iron-based magnetic nanomaterials of high performance for biomedical applications[J]. Nano Research, 2022, 15(1): 1-17.
[44]
GOVINDANB, SABRIM A, HAI A, et al. A review of advanced multifunctional magnetic nanostructures for cancer diagnosis and therapy integrated into an artificial intelligence approach[J/OL]. Pharmaceutics, 2023, 15(3)[2025-07-15].
[45]
TOMITAKAA, VASHISTA, KOLISHETTIN, et al. Machine learning assisted-nanomedicine using magnetic nanoparticles for central nervous system diseases[J]. Nanoscale Advances, 2023, 5(17): 4354-4367.
[46]
HADJIANFARM, SEMNANID, VARSHOSAZJ, et al. 5FU-loaded PCL/chitosan/Fe(3)O(4) core-shell nanofibers structure: An approach to multi-mode anticancer system[J]. Advanced Pharmaceutical Bulletin, 2022, 12(3): 568-582.
[47]
ZAREH, AHMADIS, GHASEMIA, et al. Carbon nanotubes: Smart drug/gene delivery carriers[J]. International Journal of Nanomedicine, 2021, 16: 1681-1706.
[48]
JEONGW Y, CHOIH E, KIMK S. Graphene-based nanomaterials as drug delivery carriers[M]//HAN D W, HONG S W. Multifaceted Biomedical Applications of Graphene. Singapore: Springer Singapore, 2022: : 109-124.
[49]
MEHRIZADA. Prompt loading and prolonged release of metronidazole by calcium ferrite-carbon nanotubes carrier: optimization and modeling of the process by RSM and ANN[J/OL]. Diamond and Related Materials, 2023, 135 [2025-07-15].
[50]
EGOROVE, PIETERSC, KORACH-RECHTMANH, et al. Robotics, microfluidics, nanotechnology and AI in the synthesis and evaluation of liposomes and polymeric drug delivery systems[J]. Drug Delivery and Translational Research, 2021, 11(2): 345-352.
[51]
VILLASEÑOR-CAVAZOSF J, TORRES-
[52]
VALLADARESD, LOZANOO. Modeling and optimization of nanovector drug delivery systems: exploring the most efficient algorithms[J]. Journal of Nanoparticle Research, 2022, 24(6): 119.
[53]
ZHANGC Y, YUANY C, XIAQ, et al. Machine learning-driven prediction, preparation, and evaluation of functional nanomedicines via drug-drug self-assembly[J/OL]. Advanced Science, 2025, 12(9)[2025-07-15].
[54]
ELBADAWIM, MCCOUBREYL E, GAVINSF K H, et al. Harnessing artificial intelligence for the next generation of 3D printed medicines[J/OL]. Advanced Drug Delivery Reviews, 2021, 175[2025-07-15].
[55]
PUGLIESER, REGONDIS. Artificial intelligence-empowered 3D and 4D printing technologies toward smarter biomedical materials and approaches[J/OL]. Polymers, 2022, 14(14)[2025-07-15].
[56]
LIUG Q, DONGL L, LUK, et al. Preparation and in vivo pharmacokinetics of the Tongshu suppository[J/OL]. BioMed Research International, 2016, 2016(1)[2025-07-15].
[57]
BOLGERM B. Perspective on a chemistry classification system for AI-assisted formulation development[J]. Journal of Controlled Release, 2022, 352: 833-839.
[58]
NOORAIN, SRIVASTAVAV, PARVEENB, et al. Artificial intelligence in drug formulation and development: Applications and future prospects[J]. Current Drug Metabolism, 2023, 24(9): 622-634.
[59]
BANNIGANP, HICKMANR J, ASPURU-GUZIKA, et al. The dawn of a new pharmaceutical epoch: can AI and robotics reshape drug formulation?[J/OL]. Advanced Healthcare Materials, 2024, 13(29)[2025-07-15].
[60]
HORNICKT, MAOC, KOYNOVA, et al. In silico formulation optimization and particle engineering of pharmaceutical products using a generative artificial intelligence structure synthesis method[J/OL]. Nature Communications, 2024, 15[2025-07-15].
[61]
BANNIGANP, ALDEGHIM, BAOZ Q, et al. Machine learning directed drug formulation development[J/OL]. Advanced Drug Delivery Reviews, 2021, 175[2025-07-15].
[62]
WANGN N, DONGJ, OUYANGD F. AI-directed formulation strategy design initiates rational drug development[J]. Journal of Controlled Release, 2025, 378: 619-636.
[63]
DAWOUDM H S, MANNAAI S, ABDEL-DAIMA, et al. Integrating artificial intelligence with quality by design in the formulation of lecithin/chitosan nanoparticles of a poorly water-soluble drug[J/OL]. AAPS PharmSciTech, 2023, 24(6)[2025-07-15].
[64]
BAGDEA, DEVS, SRIRAML M K, et al. Biphasic burst and sustained transdermal delivery in vivo using an AI-optimized 3D-printed MN patch[J/OL]. International Journal of Pharmaceutics, 2023, 636[2025-07-15].
[65]
VIDHYAK S, SULTANAA, NAVEEN KUMARM, et al. Artificial intelligence’s impact on drug discovery and development from bench to bedside[J/OL]. Cureus, 2023, 15(10)[2025-07-15].
[66]
HANR, YANGY L, LIX S, et al. Predicting oral disintegrating tablet formulations by neural network techniques[J]. Asian Journal of Pharmaceutical Sciences, 2018, 13(4): 336-342.
[67]
BOZTEPEC, KÜNKÜLA, YÜCEERM. Application of artificial intelligence in modeling of the doxorubicin release behavior of pH and temperature responsive poly(NIPAAm-co-AAc)-PEG IPN hydrogel[J/OL]. Journal of Drug Delivery Science and Technology, 2020, 57[2025-07-15].
[68]
ZHANGS, WUD, ZHOUL P. Characterization of controlled release microspheres using FIB-SEM and image-based release prediction[J]. AAPS PharmSciTech, 2020, 21(5): 194.
[69]
WANGX Y, BURGESSD J. Drug release from in situ forming implants and advances in release testing[J/OL]. Advanced Drug Delivery Reviews, 2021, 178[2025-07-15].
[70]
YUANL, CHENQ R, RIVIEREJ E, et al. Pharmacokinetics and tumor delivery of nanoparticles[J/OL]. Journal of Drug Delivery Science and Technology, 2023, 83[2025-07-15].
[71]
IWATAH. Application of in silico technologies for drug target discovery and pharmacokinetic analysis[J]. Chemical & Pharmaceutical Bulletin, 2023, 71(6): 398-405.
[72]
OZBEKO, GENCD E, ULGENKO. Advances in physiologically based pharmacokinetic (PBPK) modeling of nanomaterials[J]. ACS Pharmacology & Translational Science, 2024, 7(8): 2251-2279.
[73]
VORAL K, GHOLAPA D, JETHAK, et al. Artificial intelligence in pharmaceutical technology and drug delivery design[J/OL]. Pharmaceutics, 2023, 15(7)[2025-07-15].
[74]
CHOUW C, CHENQ R, YUANL, et al. An artificial intelligence-assisted physiologically-based pharmacokinetic model to predict nanoparticle delivery to tumors in mice[J]. Journal of Controlled Release, 2023, 361: 53-63.
[75]
HOUYN, LE GRANDF. Personalized oncology with artificial intelligence: The case of temozolomide[J/OL]. Artificial Intelligence in Medicine, 2019, 99[2025-07-15].
[76]
DESTEREA, MARQUETP, LABRIFFEM, et al. A hybrid algorithm combining population pharmacokinetic and machine learning for isavuconazole exposure prediction[J]. Pharmaceutical Research, 2023, 40(4): 951-959.