因果机器学习在医疗决策中的应用研究综述

doi:10.11896/jsjkx.240800160

摘要/Abstract

摘要： 归纳了因果机器学习的核心概念和基本原理,以及其在医疗领域的应用研究进展,为医学研究人员、医生和决策者提供重要的参考。介绍了因果学习的基本概念、主要因果模型以及因果机器学习模型,系统梳理了因果机器学习在医疗决策中的应用进展及面临的挑战。因果机器学习相关技术能够有效应用于医疗诊断、治疗、预测等过程中,增强对病症的把控和识别能力,从而帮助医生和决策者更好地理解和预测治疗效果,为患者提供更加有效的医疗方案。因此,因果机器学习在医疗决策中具有广阔的应用前景,但当下仍然面临着数据质量、模型可解释性等方面的挑战。未来的研究应关注如何克服现有挑战,提供更加精确和个性化的医疗决策支持,更大程度地维护患者的健康。

关键词: 因果机器学习, 医疗决策, 医疗应用

Abstract: This paper summarises the core concepts and fundamentals of causal machine learning,as well as the research progress of its application in healthcare,providing an important reference for medical researchers,doctors and policy makers.It introduces the basic concepts of causal learning,the main causal models,and causal machine learning models,systematically sorts out the progress and challenges of the application of causal machine learning in medical decision-making.This paper points out that causal machine learning-related technologies can be effectively applied to the process of medical diagnosis,treatment,and prediction to enhance the ability to control and identify the disease,thus helping doctors and decision makers better understand and predict the treatment effect,and provide more effective medical solutions for patients.Therefore,causal machine learning has a broad application prospect in medical decision-making,but it still faces challenges in data quality and model interpretability at the moment.Future research should focus on how to overcome the existing challenges,provide more precise and personalised medical decision support to maintain patients’ health to a greater extent.

Key words: Causal machine learning, Medical decision-making, Medical application

中图分类号:

TP391

周婵魏, 郑希, 刘江, 陈芋文. 因果机器学习在医疗决策中的应用研究综述[J]. 计算机科学, 2025, 52(11A): 240800160-8. https://doi.org/10.11896/jsjkx.240800160

ZHOU Chan, WEI Zhengxi, LIU Jiang, CHEN Yuwen. Research Progress on Application of Causal Machine Learning in Medical Decision-making[J]. Computer Science, 2025, 52(11A): 240800160-8. https://doi.org/10.11896/jsjkx.240800160

参考文献

[1]CUI L,HOU Y F,ZHANG H.On medical decision support sys-tem[J].Journal of Medical Informatics,2003(1):28-30,40.
[2]PEARL J.Causal inference in statistics:An overview[J].Statistics Surveys.2009,3:96-146.
[3]PEARL J.Causal inference[C]//Proceedings of the 2008th International Conference on Causality:Objectives and Assessment.JMLR.org,2008.
[4]NEUBERG L G.Causality:models,reasoning,and inference,by Judea Pearl,Cambridge University Press,2000[J].Econometric Theory,2003,19(4):675-685.
[5]LEWIS D.Causation[J].Journal of Philosophy,1973,70(17):556-567.
[6]WOODWARD J.Making Things Happen:A Theory of CausalExplanation[M].Oxford University Press,2004.
[7]DANKS D.Singular Causation[M]//The Oxford Handbook of Causal Reasoning,Waldmann M R,Oxford University Press,2017:201-216.
[8]GLYMOUR C,DANKS D,GLYMOUR B,et al.Actual causa-tion:a stone soup essay[J].Synthese,2010,175(2):169-192.
[9]RICHENS J G,LEE C M,JOHRI S.Improving the accuracy of medical diagnosis with causal machine learning[J].Nature Communications.2020,11:3923.
[10]PEARL J.Causal diagrams for empirical research[J].Biometrika,1995,82(4):669-688.
[11]REINHOLD J C,CARASS A,PRINCE J L.A Structural Causal Model for MR Images of Multiple Sclerosis[J].arXiv:2103.03158,2021.
[12]RUBIN D B.Bayesian Inference for Causal Effects:The Role of Randomization[J].The Annals of Statistics.1978,6(1):34-58,25.
[13]NOGUEIRA A R,PUGNANA A,RUGGIERI S,et al.Methods and tools for causal discovery and causal inference[J].WIREs Data Mining and Knowledge Discovery,2022,12(2):e1449.
[14]YAO L,CHU Z,LI S,et al.A Survey on Causal Inference[J].ACM Transactions on Knowledge Discovery form Data,2021,15(5):1-46.
[15]FEHR J,PICCININNI M,KURTH T,et al.Assessing thetransportability of clinical prediction models for cognitive impairment using causal models[J].BMC Medical Research Me-thodology.2023,23(1):187.
[16]PAVLOVIĆ M,AL HAJJ G S,KANDURI C,et al.Improving generalization of machine learning-identified biomarkers using causal modelling with examples from immune receptor diagnostics[J].Nature Machine Intelligence,2024,6(1):15-24.
[17]RICHENS J G,LEE C M,JOHRI S.Improving the accuracy of medical diagnosis with causal machine learning[J].Nature Communications,2020,11(1):3923.
[18]SCHÖLKOPF B.Causality for Machine Learning[M]//Probabilistic and Causal Inference:The Works of Judea Pearl.Association for Computing Machinery,2022:765-804.
[19]KIM B,KHANNA R,KOYEJO O.Examples are not enough,learn to criticize! criticism for interpretability[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems.Curran Associates Inc.,2016.
[20]DOSHI-VELEZ F,KIM B.Towards A Rigorous Science of Interpretable Machine Learning[J].arXiv:1702.08608,2017.
[21]GILPIN L,BAU D,YUAN B Z,et al.Explaining Explanations:An Overview of Interpretability of Machine Learning[C]//2018 IEEE 5th International Conference on Data Science and Advanced Analytics(DSAA).2018.
[22]KIM C,BASTANI O.Learning Interpretable Models with Cau-sal Guarantees[J].arXiv:1901.08576,2019.
[23]KRZYWINSKI M,ALTMAN N.Classification and regressiontrees[J].Nature Methods,2017,14(8):757-758.
[24]TIBSHIRANI R.Regression Shrinkage and Selection Via the Lasso[J].Journal of the Royal Statistical Society:Series B(Methodological),2018,58(1):267-288.
[25]USTUN B,RUDIN C.Supersparse linear integer models for optimized medical scoring systems[J].Machine Learning,2016,102(3):349-391.
[26]CARUANA R,LOU Y,GEHRKE J,et al.Intelligible Models for HealthCare:Predicting Pneumonia Risk and Hospital 30-day Readmission[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mi-ning.Association for Computing Machinery,2015.
[27]ANGELINO E,LARUS-STONE N,ALABI D,et al.Learning Certifiably Optimal Rule Lists[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Disco-very and Data Mining.Association for Computing Machinery,2017.
[28]ELLIS K,SOLAR-LEZAMA A,TENENBAUM J B.Unsupervised learning by program synthesis[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems.MIT,2015.
[29]VERMA A,MURALI V,SINGH R,et al.Programmatically Interpretable Reinforcement Learning[J].arXiv:1804.02477,2018.
[30]VALKOV L,CHAUDHARI D,SRIVASTAVA A,et al.HOUDINI:Lifelong Learning as Program Synthesis[C]//Neural Information Processing Systems.2018.
[31]ELLIS K,RITCHIE D,SOLAR-LEZAMA A,et al.Learning to infer graphics programs from hand-drawn images[C]//Procee-dings of the 32nd International Conference on Neural Information Processing Systems.Curran Associates Inc.,2018.
[32]LI Y,MA S,LE T,et al.Causal Decision Trees[J].IEEETransactions on Knowledge and Data Engineering,2017,29(2):257-271.
[33]LI J,WU B,SUN X,et al.Causal Hidden Markov Model for Time Series Disease Forecasting[C]//2021 IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition(CVPR).2021:12100-12109.
[34]GERSTENBERG T,GOODMAN N D,LAGNADO D A,et al.A counterfactual simulation model of causal judgments for physical events[J].Psychological Review,2021,128(5):935-975.
[35]JACKSON C.Random forest classification of multiple sclerosis clinical courses[J].Frontiers in Neurology, 2017,8:1-10.
[36]FLAUZINO T,SIMÃO A N C,DE CARVALHO JENNINGS PEREIRA W L,et al.Disability in multiple sclerosis is associa-ted with age and inflammatory,metabolic and oxidative/nitrosative stress biomarkers:results of multivariate and machine lear-ning procedures[J].Metabolic Brain Disease,2019,34:1401-1413.
[37] BICA I,ALAA A,LAMBERT C,et al.From Real-World Patient Data to Individualized Treatment Effects Using Machine Learning:Current and Future Methods to Address Underlying Challenges[J].Clinical Pharmacology & Therapeutics,2020,109(1):87-100.
[38]WILKINSON J,ARNOLD K F,MURRAY E J,et al.Time to reality check the promises of machine learning-powered precision medicine[J].The Lancet Digital health,2020,2(12):e677-e680.
[39]GRUBER S,LAAN M V D.tmle:An R Package for Targeted Maximum Likelihood Estimation[J].Journal of Statistical Software,2012,51(13):1-35.
[40]AUSTIN P C,STUART E A.Moving towards best practicewhen using inverse probability of treatment weighting(IPTW) using the propensity score to estimate causal treatment effects in observational studies[J].Statistics in Medicine,2015,34:3661-3679.
[41]CHIPMAN H A,GEORGE E I,MCCULLOCH R E.BART:Bayesian Additive Regression Trees[J].The Annals of Applied Statistics,2008,4:266-298.
[42]HILL J L.Bayesian Nonparametric Modeling for Causal Infe-rence[J].Journal of Computational and Graphical Statistics,2011,20:217-240.
[43]WAGER S,ATHEY S.Estimation and Inference of Heterogeneous Treatment Effects using Random Forests[J].Journal of the American Statistical Association,2015,113:1228-1242.
[44]ROSENBAUM P R,RUBIN D B.The central role of the propensity score in observational studies for causal effects[J].Biometrika,1983,70:41-55.
[45]DEHEJIA R H,WAHBA S.Propensity Score-Matching Me-thods for Nonexperimental Causal Studies[J].The Review of Economics and Statistics,2002,84(1):151-161.
[46]HO D,IMAI K,KING G,et al.MatchIt:Nonparametric Preprocessing for Parametric Causal Inference[J].Journal of Statistical Software,2011,42(8):1-28.
[47]OPRESCU M,SYRGKANIS V,BATTOCCHI K,et al.Econ-ML:A Machine Learning Library for Estimating Heterogeneous Treatment Effects[EB/OL].https://mirunaoprescu.com/assets/publications/2019_econml/EconML_Workshop_Poster.pdf.
[48]DUDÍK M,LANGFORD J,LI L.Doubly Robust Policy Evaluation and Learning[C]//International Conference on Machine Learning.2011.
[49]DUDÍK M,ERHAN D,LANGFORD J,et al.Doubly RobustPolicy Evaluation and Optimization[J].arXiv:1503.02834,2015.
[50]TIAN J.Identifying Dynamic Sequential Plans[C]//Conference on Uncertainty in Artificial Intelligence.2008.
[51]DUONG T D,LI Q,XU G.Stochastic intervention for causal inference via reinforcement learning[J].Neurocomputing,2022,482:40-49.
[52]SHEN X,MA S,VEMURI P,et al.Challenges and Opportunities with Causal Discovery Algorithms:Application to Alzheimer’s Pathophysiology[J].Scientific Reports,2020,10(1):2975.
[53]ZHANG F,BARANOVA A,ZHOU C,et al.Causal influences of neuroticism on mental health and cardiovascular disease[J].Human Genetics,2021,140(9):1267-1281.
[54]HARTMANN M,FENTON N,DOBSON R.Current reviewand next steps for artificial intelligence in multiple sclerosis risk research[J].Computers in Biology and Medicine,2021,132:104337.
[55]TOPUZ K,ZENGUL F D,DAGˇ A,et al.Predicting graft survi-val among kidney transplant recipients:A Bayesian decision support model[J].Decision Support Systems,2018,106:97-109.
[56]DAHABREH I J,BIBBINS-DOMINGO K.Causal InferenceAbout the Effects of Interventions From Observational Studies in Medical Journals[J].JAMA,2024,331(21):1845-1853.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed