机器学习在临床药物治疗中的研究进展

doi:10.12114/j.issn.1007-9572.2021.01.309

摘要/Abstract

摘要： 随着真实世界研究、精准治疗等概念的提出和发展，科研工作者对医疗大数据处理的需求不断增大。机器学习技术因在处理海量、高维数据及开展预测研究等方面具有独特优势，故而近些年在医学领域的应用不断深入。除应用于疾病诊断、影像识别和风险预测外，越来越多的研究证明机器学习可被应用于临床药物治疗的决策支持相关研究中。本文就机器学习在临床药物治疗中的研究进展予以综述。

关键词: 机器学习, 临床药物治疗, 真实世界研究, 精准治疗, 综述

Abstract:

With the advancement and development of concepts such as real-world research and precision treatment, the demand of researchers for medical big data processing keeps increasing. Because machine learning technology has unique advantages in processing massive, high-dimensional data and conducting predictive research, it has been deeply applied in the medical field in recent years. In addition to the application in disease diagnosis, image recognition and risk prediction, more and more studies have proved that machine learning can be applied to the decision support related research of clinical drug treatment. This article reviews the research progress of machine learning in clinical drug therapy.

Key words: Machine learning, Clinical drug therapy, Real world research, Accurate treatment, Review

中图分类号:

R319

吴行伟,刘馨宇,龙恩武,等. 机器学习在临床药物治疗中的研究进展[J]. 中国全科医学, 2022, 25(02): 254-258. DOI: 10.12114/j.issn.1007-9572.2021.01.309.

WU Xingwei, LIU Xinyu, LONG Enwu, TONG Rongsheng.

Research Progress of Machine Learning in Clinical Drug Therapy [J]. Chinese General Practice, 2022, 25(02): 254-258.

参考文献 45

[1]	AFARI Z，LYND L D，FITZGERALD J M，et al. Economic and health effect of full adherence to controller therapy in adults with uncontrolled asthma：a simulation study[J]. J Allergy Clin Immunol，2014，134（4）：908-915.e3. DOI：10.1016/j.jaci.2014.04.009.
[2]	DAVIS K L，EDIN H M，ALLEN J K. Prevalence and cost of medication nonadherence in Parkinson&apos；s disease：evidence from administrative claims data[J]. Mov Disord，2010，25（4）：474-480. DOI：10.1002/mds.22999.
[3]	FORMICA D，SULTANA J，CUTRONEO P M，et al. The economic burden of preventable adverse drug reactions：a systematic review of observational studies[J]. Expert Opin Drug Saf，2018，17（7）：681-695. DOI：10.1080/14740338.2018.1491547.
[4]	PIRMOHAMED M，JAMES S，MEAKIN S，et al. Adverse drug reactions as cause of admission to hospital：prospective analysis of 18 820 patients[J]. BMJ，2004，329（7456）：15-19. DOI：10.1136/bmj.329.7456.15.
[5]	HANDELMAN G S，KOK H K，CHANDRA R V，et al. eDoctor：machine learning and the future of medicine[J]. J Intern Med，2018，284（6）：603-619. DOI：10.1111/joim.12822.
[6]	JARRETT D，STRIDE E，VALLIS K，et al. Applications and limitations of machine learning in radiation oncology[J]. Br J Radiol，2019，92（1100）：20190001. DOI：10.1259/bjr.20190001.
[7]	BZDOK D，KRZYWINSKI M，ALTMAN N. Machine learning：supervised methods[J]. Nat Methods，2018，15（1）：5-6. DOI：10.1038/nmeth.4551.
[8]	BI Q F，GOODMAN K E，KAMINSKY J，et al. What is machine learning? A primer for the epidemiologist[J]. Am J Epidemiol，2019，188（12）：2222-2239. DOI：10.1093/aje/kwz189.
[9]	ESTEVA A，ROBICQUET A，RAMSUNDAR B，et al. A guide to deep learning in healthcare[J]. Nat Med，2019，25（1）：24-29. DOI：10.1038/s41591-018-0316-z.
[10]	SUO Q L，MA F L，YUAN Y，et al. Deep patient similarity learning for personalized healthcare[J]. IEEE Trans Nanobioscience，2018，17（3）：219-227. DOI：10.1109/TNB.2018.2837622.
[11]	CHENG Y T，LIN Y F，CHIANG K H，et al. Mining sequential risk patterns from large-scale clinical databases for early assessment of chronic diseases：a case study on chronic obstructive pulmonary disease[J]. IEEE J Biomed Health Inform，2017，21（2）：303-311. DOI：10.1109/JBHI.2017.2657802.
[12]	WRIGHT A P，WRIGHT A T，MCCOY A B，et al. The use of sequential pattern mining to predict next prescribed medications[J]. J Biomed Inform，2015，53：73-80. DOI：10.1016/j.jbi.2014.09.003.
[13]	BEAM A L，KARTOUN U，PAI J K，et al. Predictive modeling of physician-patient dynamics that influence sleep medication prescriptions and clinical decision-making[J]. Sci Rep，2017，7：42282. DOI：10.1038/srep42282.
[14]	YELIN I，SNITSER O，NOVICH G，et al. Personal clinical history predicts antibiotic resistance of urinary tract infections[J]. Nat Med，2019，25（7）：1143-1152. DOI：10.1038/s41591-019-0503-6.
[15]	ROUGH K，DAI A M，ZHANG K，et al. Predicting inpatient medication orders from electronic health record data[J]. Clin Pharmacol Ther，2020，108（1）：145-154. DOI：10.1002/cpt.1826.
[16]	朱立强，王勇敢，李卫华，等. 采用机器学习方法建立Ⅰ类切口手术患者使用抗菌药物合理性的评价模型[J]. 中国药房，2019，30（9）：1260-1265. DOI：10.6039/j.issn.1001-0408.2019.09.22.
[17]	MA Z，WANG P，GAO Z，et al. Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose[J]. PLoS One，2018，13（10）：e0205872. DOI：10.1371/journal.pone.0205872.
[18]	ROCHE-LIMA A，ROMAN-SANTIAGO A，FELIU-MALDONADO R，et al. Machine learning algorithm for predicting warfarin dose in Caribbean hispanics using pharmacogenetic data[J]. Front Pharmacol，2019，10：1550. DOI：10.3389/fphar.2019.01550.
[19]	TAO Y Y，CHEN Y J，FU X Y，et al. Evolutionary ensemble learning algorithm to modeling of warfarin dose prediction for Chinese[J]. IEEE J Biomed Health Inform，2019，23（1）：395-406. DOI：10.1109/JBHI.2018.2812165.
[20]	SU L X，LIU C，LI D K，et al. Toward optimal heparin dosing by comparing multiple machine learning methods：retrospective study[J]. JMIR Med Inform，2020，8（6）：e17648. DOI：10.2196/17648.
[21]	LEVY A E，BISWAS M，WEBER R，et al. Applications of machine learning in decision analysis for dose management for dofetilide[J]. PLoS One，2019，14（12）：e0227324. DOI：10.1371/journal.pone.0227324.
[22]	NIKFARJAM A，GONZALEZ G H. Pattern mining for extraction of mentions of Adverse Drug Reactions from user comments[J]. AMIA Annu Symp Proc，2011，2011：1019-1026.
[23]	PATKI A，SARKER A，PIMPALKHUTE P，et al. Mining adverse drug reaction signals from social media：going beyond extraction[C]. BioLink-SIG，2014.
[24]	JAMAL S，GOYAL S，SHANKER A，et al. Predicting neurological Adverse Drug Reactions based on biological，chemical and phenotypic properties of drugs using machine learning models[J]. Sci Rep，2017，7（1）：1-12. DOI：10.1038/s41598-017-00908-z.
[25]	HAMMANN F，SCHÖNING V，DREWE J. Prediction of clinically relevant drug-induced liver injury from structure using machine learning[J]. J Appl Toxicol，2019，39（3）：412-419. DOI：10.1002/jat.3741.
[26]	FENG C L，CHEN H W，YUAN X Q，et al. Gene expression data based deep learning model for accurate prediction of drug-induced liver injury in advance[J]. J Chem Inf Model，2019，59（7）：3240-3250. DOI：10.1021/acs.jcim.9b00143.
[27]	LAI N H，SHEN W C，LEE C N，et al. Comparison of the predictive outcomes for anti-tuberculosis drug-induced hepatotoxicity by different machine learning techniques[J]. Comput Methods Programs Biomed，2020，188（2）：105307. DOI：10.1016/j.cmpb.2019.105307.
[28]	DAVAZDAHEMAMI B，DELEN D. A chronological pharmacovigilance network analytics approach for predicting adverse drug events[J]. J Am Med Inform Assoc，2018，25（10）：1311-1321. DOI：10.1093/jamia/ocy097.
[29]	CHEKROUD A M，ZOTTI R J，SHEHZAD Z，et al. Cross-trial prediction of treatment outcome in depression：a machine learning approach[J]. Lancet Psychiatry，2016，3（3）：243-250. DOI：10.1016/S2215-0366(15)00471-X.
[30]	ATHREYA A P，NEAVIN D，CARRILLO-ROA T，et al. Pharmacogenomics-driven prediction of antidepressant treatment outcomes：a machine-learning approach with multi-trial replication[J]. Clin Pharmacol Ther，2019，106（4）：855-865. DOI：10.1002/cpt.1482.
[31]	SAKELLAROPOULOS T，VOUGAS K，NARANG S，et al. A deep learning framework for predicting response to therapy in cancer[J]. Cell Rep，2019，29（11）：3367-3373.e4. DOI：10.1016/j.celrep.2019.11.017.
[32]	JIANG Y M，LIU W，LI T J，et al. Prognostic and predictive value of p21-activated kinase 6 associated support vector machine classifier in gastric cancer treated by 5-fluorouracil/oxaliplatin chemotherapy[J]. EBioMedicine，2017，22：78-88. DOI：10.1016/j.ebiom.2017.06.028.
[33]	MACESIC N，POLUBRIAGINOF F，TATONETTI N P. Machine learning：novel bioinformatics approaches for combating antimicrobial resistance[J]. Curr Opin Infect Dis，2017，30（6）：511-517. DOI：10.1097/QCO.0000000000000406.
[34]	DAVIS J J，BOISVERT S，BRETTIN T，et al. Antimicrobial resistance prediction in PATRIC and RAST[J]. Sci Rep，2016，6：27930. DOI：10.1038/srep27930.
[35]	CHOWDHURY A S，KHALEDIAN E，BROSCHAT S L. Capreomycin resistance prediction in two species of Mycobacterium using a stacked ensemble method[J]. J Appl Microbiol，2019，127（6）：1656-1664. DOI：10.1111/jam.14413.
[36]	MANCINI A，VITO L，MARCELLI E，et al. Machine learning models predicting multidrug resistant urinary tract infections using "DsaaS" [J]. BMC Bioinformatics，2020，21（）：347. DOI：10.1186/s12859-020-03566-7.
[37]	AN S，MALHOTRA K，DILLEY C，et al. Predicting drug-resistant epilepsy-A machine learning approach based on administrative claims data[J]. Epilepsy Behav，2018，89：118-125. DOI：10.1016/j.yebeh.2018.10.013.
[38]	DORMAN S N，BARANOVA K，KNOLL J H，et al. Genomic signatures for paclitaxel and gemcitabine resistance in breast cancer derived by machine learning[J]. Mol Oncol，2016，10（1）：85-100. DOI：10.1016/j.molonc.2015.07.006.
[39]	CHENG F X，ZHAO Z M. Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic，therapeutic，chemical，and genomic properties[J]. J Am Med Inform Assoc，2014，21（e2）：e278-286. DOI：10.1136/amiajnl-2013-002512.
[40]	KASTRIN A，FERK P，LESKOŠEK B. Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning[J]. PLoS One，2018，13（5）：e0196865. DOI：10.1371/journal.pone.0196865.
[41]	RYU J Y，KIM H U，LEE S Y. Deep learning improves prediction of drug-drug and drug-food interactions[J]. Proc Natl Acad Sci USA，2018，115（18）：E4304-4311. DOI：10.1073/pnas.1803294115.
[42]	TUCKER C S，BEHOORA I，NEMBHARD H B，et al. Machine learning classification of medication adherence in patients with movement disorders using non-wearable sensors[J]. Comput Biol Med，2015，66：120-134. DOI：10.1016/j.compbiomed.2015.08.012.
[43]	MOHEBBI A，ARADÓTTIR T B，JOHANSEN A R，et al. A deep learning approach to adherence detection for type 2 diabetics[J].Annu Int Conf IEEE Eng Med Biol Soc，2017，2017：2896-2899. DOI：10.1109/EMBC.2017.8037462.
[44]	LI Y，JASANI F，SU D，et al. Decoding nonadherence to hypertensive medication in New York City：a population segmentation approach[J]. J Prim Care Community Health，2019，10：2150132719829311. DOI：10.1177/2150132719829311.
[45]	WU X W，YANG H B，YUAN R，et al. Predictive models of medication non-adherence risks of patients with T2D based on multiple machine learning algorithms[J]. BMJ Open Diabetes Res Care，2020，8（1）：e001055. DOI：10.1136/bmjdrc-2019-001055.