人工智能在药物递送中的应用

Application of artificial intelligence in drug delivery

摘要

人工智能（artificial intelligence，AI）正驱动现代药物递送系统向智能化与精准化范式变革。为应对传统研发中周期长、成本高及靶向性不足等挑战，文章系统综述了AI技术在整个药物递送链条中的赋能作用。通过解析机器学习和深度学习等AI技术在多种剂型（包括传统剂型、缓释系统、微球/微囊、纳米载体及3D打印制剂）开发中的应用实例，阐明了AI模型在预测药物释放行为、优化配方设计、智能识别制剂缺陷以及实现个性化给药等方面的显著优势。文章指出，尽管面临数据质量、模型可解释性等挑战，AI无疑已成为推动药物递送迈向智能响应与精准医学时代的核心驱动力，在医药研发变革领域展现出巨大潜力。

Abstract

Artificial intelligence（AI）is driving the paradigm shift of modern drug delivery systems towards intelligence and precision. To address the challenges of long cycles，high costs，and insufficient targeting in traditional research and development，this article systematically reviews the empowering role of AI technology throughout the entire drug delivery chain. By analyzing application examples of AI technologies such as machine learning and deep learning in the development of various dosage forms（including traditional dosage forms，sustained-release systems，microspheres/microcapsules，nanocarriers，and 3D-printed formulations），the article elucidates the significant advantages of AI models in predicting drug release behavior，optimizing formulation design，intelligently identifying formulation defects，and achieving personalized drug delivery. The article points out that despite challenges such as data quality and model interpretability，AI has undoubtedly become the core driving force propelling drug delivery towards the era of intelligent response and precision medicine，demonstrating immense potential in the field of pharmaceutical research and development transformation.

关键词

人工智能 / 药物递送 / 机器学习 / 精准医疗 / 制剂优化

Key words

artificial intelligence / drug delivery / machine learning / precision medicine / formulation optimization

参考文献

[1] CHOI R Y, COYNER A S, KALPATHY—CRAMER J, et al. Introduction to machine learning, neural networks, and deep learning[J]. Transl Vis Sci Technol, 2020, 9(2):14.

[2] CHOUDHARY L, CHOUDHARY J S. Deep learning meets machine learning: a synergistic approach towards artificial intelligence[J]. J Sci Res Rep, 2024, 30(11):865-875.

[3] SHIN S H, OH S M, YOON PARK J H, et al. OptNCMiner: a deep learning approach for the discovery of natural compounds modulating disease—specific multi—targets[J]. BMC Bioinform, 2022, 23(1):218.

[4] ZHANG K, YANG X, WANG Y F, et al. Artificial intelligence in drug development[J]. Nat Med, 2025, 31(1):45-59.

[5] LIU F, NIU Y, ZHANG Q H, et al. A foundational architecture for AI agents in healthcare[J]. Cell Rep Med, 2025, 6(10):102374.

[6] DAS S, DEY R, NAYAK A K. Artificial intelligence in pharmacy[J]. Indian J Pharm Educ Res, 2021, 55(2):304-318.

[7] FARIZHANDI A A K, ALISHIRI M, LAU R. Machine learning approach for carrier surface design in carrier—based dry powder inhalation[J]. Comput Chem Eng, 2021, 151:107367.

[8] CHAUHAN S, O’CALLAGHAN S, WALL A, et al. Using peptidomics and machine learning to assess effects of drying processes on the peptide profile within a functional ingredient[J]. Processes, 2021, 9(3):425.

[9] KESKES S, HANINI S, HENTABLI M, et al. Artificial intelligence and mathematical modelling of the drying kinetics of pharmaceutical powders[J]. Kem Ind, 2020, 69(3/4):137-152.

[10] ZHAO J, TIAN G, QIU Y Y, et al. Rapid quantification of active pharmaceutical ingredient for sugar—free Yangwei granules in commercial production using FT—NIR spectroscopy based on machine learning techniques[J]. Spectrochim Acta Part A Mol Biomol Spectrosc, 2021, 245:118878.

[11] LANDIN M. Artificial intelligence tools for scaling up of high shear wet granulation process[J]. J Pharm Sci, 2017, 106(1):273-277.

[12] MA X Y, KITTIKUNAKORN N, SORMAN B, et al. Application of deep learning convolutional neural networks for internal tablet defect detection: high accuracy, throughput, and adaptability[J]. J Pharm Sci, 2020, 109(4):1547-1557.

[13] OBEID S, MADŽAREVIC M, KRKOBABIC M, et al. Predicting drug release from diazepam FDM printed tablets using deep learning approach: influence of process parameters and tablet surface/volume ratio[J]. Int J Pharm, 2021, 601:120507.

[14] WESTPHAL E, SEITZ H. A machine learning method for defect detection and visualization in selective laser sintering based on convolutional neural networks[J]. Addit Manuf, 2021, 41:101965.

[15] PETROVIC J, IBRIC S, BETZ G, et al. Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees[J]. Int J Pharm, 2012, 428(1/2):57-67.

[16] GALATA D L, KÖNYVES Z, NAGY B, et al. Real—time release testing of dissolution based on surrogate models developed by machine learning algorithms using NIR spectra, compression force and particle size distribution as input data[J]. Int J Pharm, 2021, 597:120338.

[17] SANKALIA M G, MASHRU R C, SANKALIA J M, et al. Papain entrapment in alginate beads for stability improvement and site—specific delivery: physicochemical characterization and factorial optimization using neural network modeling[J]. AAPS PharmSciTech, 2005, 6(2):31.

[18] LABOUTA H I, EL—KHORDAGUI L K, MOLOKHIA A M, et al. Multivariate modeling of encapsulation and release of an ionizable drug from polymer microspheres[J]. J Pharm Sci, 2009, 98(12):4603-4615.

[19] 张安阳, 范田园. 运用人工神经网络和响应曲面法体外优化阿司匹林海藻酸钙胃漂浮微球[J]. 北京大学学报（医学版）, 2010, 42(2):197-201.

[20] ZHANG A Y, FAN T Y. Optimization of calcium alginate floating microspheres loading aspirin by artificial neural networks and response surface methodology[J]. Journal of Peking University (Health Sciences), 2010, 42(2):197-201.

[21] MEDAREVIC D P, KLEINEBUDDE P, DJURIŠ J, et al. Combined application of mixture experimental design and artificial neural networks in the solid dispersion development[J]. Drug Dev Ind Pharm, 2016, 42(3):389-402.

[22] BARMPALEXIS P, KOUTSIDIS I, KARAVAS E, et al. Development of PVP/PEG mixtures as appropriate carriers for the preparation of drug solid dispersions by melt mixing technique and optimization of dissolution using artificial neural networks[J]. Eur J Pharm Biopharm, 2013, 85(3):1219-1231.

[23] GAO H L, WANG W, DONG J, et al. An integrated computational methodology with data—driven machine learning, molecular modeling and PBPK modeling to accelerate solid dispersion formulation design[J]. Eur J Pharm Biopharm, 2021, 158:336-346.

[24] HAN R, XIONG H, YE Z, et al. Predicting physical stability of solid dispersions by machine learning techniques[J]. J Control Release, 2019, 311/312:16-25.

[25] MEHTA C H, NARAYAN R, NAYAK U Y. Computational modeling for formulation design[J]. Drug Discov Today, 2019, 24(3):781-788.

[26] XU L, WANG H, XU Y, et al. Machine learning—assisted sensor array based on poly(amidoamine) (PAMAM) dendrimers for diagnosing Alzheimer’s disease[J]. ACS Sens, 2022, 7(5):1315-1322.

[27] HO D, WANG P, KEE T. Artificial intelligence in nanomedicine[J]. Nanoscale Horiz, 2019, 4(2):365-377.

[28] ASADI H, ROSTAMIZADEH K, SALARI D, et al. Preparation of biodegradable nanoparticles of tri—block PLA—PEG—PLA copolymer and determination of factors controlling the particle size using artificial neural network[J]. J Microencapsul, 2011, 28(5):406-416.

[29] LI Y Q, ABBASPOUR M R, GROOTENDORST P V, et al. Optimization of controlled release nanoparticle formulation of verapamil hydrochloride using artificial neural networks with genetic algorithm and response surface methodology[J]. Eur J Pharm Biopharm, 2015, 94:170-179.

[30] LUO M, FENG Y Z, WANG T W, et al. Micro/nanorobots at work in active drug delivery[J]. Adv Funct Mater, 2018, 28(25):1706100.

[31] NARAYANAN R R, DURGA N, NAGALAKSHMI S. Impact of artificial intelligence (AI) on drug discovery and product development[J]. Ind J Pharm Edu Res, 2022, 56(3S):S387-S397.

[32] HORTELAO A C, SIMÓ C, GUIX M, et al. Swarming behavior and in vivo monitoring of enzymatic nanomotors within the bladder[J]. Sci Robot, 2021, 6(52):eabd2823.

[33] VIDHYA K S, SULTANA A, NAVEEN KUMAR M, et al. Artificial intelligence’s impact on drug discovery and development from bench to bedside[J]. Cureus, 2023, 15(10):e47486.

[34] GHOLAP A D, UDDIN M J, FAIYAZUDDIN M, et al. Advances in artificial intelligence for drug delivery and development: a comprehensive review[J]. Comput Biol Med, 2024, 178:108702.

[35] NOORAIN, SRIVASTAVA V, PARVEEN B, et al. Artificial intelligence in drug formulation and development: applications and future prospects[J]. Curr Drug Metab, 2023, 24(9):622-634.

[36] VORA L K, GHOLAP A D, JETHA K, et al. Artificial intelligence in pharmaceutical technology and drug delivery design[J]. Pharmaceutics, 2023, 15(7):1916.

[37] KHAN M Z, YOUSUF R I, SHOAIB M H, et al. A hybrid framework of artificial intelligence—based neural network model (ANN) and central composite design (CCD) in quality by design formulation development of orodispersible moxifloxacin tablets: physicochemical evaluation, compaction analysis, and its in—silico PBPK modeling[J]. J Drug Deliv Sci Technol, 2023, 82:104323.

[38] NOSRATI H, NOSRATI M. Artificial intelligence in regenerative medicine: applications and implications[J]. Biomimetics, 2023, 8(5):442.

[39] YADAV S, SINGH A, SINGHAL R, et al. Revolutionizing drug discovery: the impact of artificial intelligence on advancements in pharmacology and the pharmaceutical industry[J]. Intell Pharm, 2024, 2(3):367-380.

[40] BUKHARI M M, ALKHAMEES B F, HUSSAIN S, et al. An improved artificial neural network model for effective diabetes prediction[J]. Complexity, 2021, 2021(1):5525271.

[41] HIRSCHBERG C, EDINGER M, HOLMFRED E, et al. Image—based artificial intelligence methods for product control of tablet coating quality[J]. Pharmaceutics, 2020, 12(9):877.

[42] DONG J, GAO H L, OUYANG D F. PharmSD: a novel AI—based computational platform for solid dispersion formulation design[J]. Int J Pharm, 2021, 604:120705.

[43] SUHAIL M, KHAN A, RAHIM M A, et al. Micro and nanorobot—based drug delivery: an overview[J]. J Drug Target, 2022, 30(4):349-358.

[44] YACOUB A S, AMMAR H O, IBRAHIM M, et al. Artificial intelligence—assisted development of in situ forming nanoparticles for arthritis therapy via intra—articular delivery[J]. Drug Deliv, 2022, 29(1):1423-1436.

[45] GELMAN R, HURVITZ N, NESSERAT R, et al. A second—generation artificial intelligence—based therapeutic regimen improves diuretic resistance in heart failure: results of a feasibility open—labeled clinical trial[J]. Biomed Pharmacother, 2023, 161:114334.

[46] HOUY N, LE GRAND F. Personalized oncology with artificial intelligence: the case of temozolomide[J]. Artif Intell Med, 2019, 99:101693.

[47] GROF Z, ŠTĚPANEK F. Artificial intelligence based design of 3D—printed tablets for personalised medicine[J]. Comput Chem Eng, 2021, 154:107492.

[48] AL—WDAN O A, SHARALLAH O A, ABDELWAHAB N A, et al. Insights into microfabrication and implementation of microfluidics in pharmaceutical drug delivery and analysis[J]. OpenNano, 2023, 12:100156.

[49] YONET—TANYERI N, AMER M, BALMERT S C, et al. Microfluidic systems for manufacturing of microparticle—based drug—delivery systems: design, construction, and operation[J]. ACS Biomater Sci Eng, 2022, 8(7):2864-2877.

[50] BANNIGAN P, ALDEGHI M, BAO Z Q, et al. Machine learning directed drug formulation development[J]. Adv Drug Deliv Rev, 2021, 175:113806.

[51] BLANCO—GONZALEZ A, CABEZON A, SECO—GONZALEZ A, et al. The role of AI in drug discovery: challenges, opportunities, and strategies[J]. Pharmaceuticals, 2023, 16(6):891.

[52] NORORI N, HU Q Y, AELLEN F M, et al. Addressing bias in big data and AI for health care: a call for open science[J]. Patterns, 2021, 2(10):100347.

[53] LAVECCHIA A. Advancing drug discovery with deep attention neural networks[J]. Drug Discov Today, 2024, 29(8):104067.

[54] JOHNSON K B, WEI W Q, WEERARATNE D, et al. Precision medicine, AI, and the future of personalized health care[J]. Clin Transl Sci, 2021, 14(1):86-93.

[55] STRUBLE T J, ALVAREZ J C, BROWN S P, et al. Current and future roles of artificial intelligence in medicinal chemistry synthesis[J]. J Med Chem, 2020, 63(16):8667-8682.

[56] STOKES J M, YANG K, SWANSON K, et al. A deep learning approach to antibiotic discovery[J]. Cell, 2020, 180(4):688-702.

基金资助

国家自然科学基金(82373105)

白求恩·医学科学研究基金(2023-YJ-119-J-039)