Page 101 - 2022-24-中国全科医学
P. 101
·3042· http://www.chinagp.net E-mail:zgqkyx@chinagp.net.cn
(3):273-282. DOI:10.1111/j.1467-9868.2011.00771.x. under test[J]. Neurocomputing,2003,55(1/2):169-186.
[25]SAFAVIAN S R,LANDGREBE D. A survey of decision tree DOI:10.1016/S0925-2312(03)00431-4.
classifier methodology[J]. IEEE Trans Syst Man Cybern,1991, [38]KRIEGESKORTE N,GOLAN T. Neural network models and deep
21(3):660-674. DOI:10.1109/21.97458. learning[J]. Curr Biol,2019,29(7):R231-236. DOI:
[26]BREIMAN L. Bagging predictors[J]. Mach Learn,1996,24(2): 10.1016/j.cub.2019.02.034.
123-140. DOI:10.1007/bf00058655. [39]LEK S,PARK Y S. Multilayer Perceptron [M]. Oxford:
[27]BREIMAN L. Random forests [J]. Machine Learning,2001,45:5-32. Academic Press,2008:2455-2462. DOI:10.1016/B978-
DOI:10.1023/A:1010933404324. 008045405-4.00162-2.
[28]TANG F,ISHWARAN H. Random forest missing data [40]RUMELHART D E,HINTON G E,WILLIAMS R J. Learning
algorithms[J]. Stat Anal Data Min ASA Data Sci J,2017,10(6): representations by back-propagating errors[J]. Nature,1986,
363-377. DOI:10.1002/sam.11348. 323(6088):533-536. DOI:10.1038/323533a0.
[29]肖美丽,晏春丽,付冰,等 . 随机森林算法在产后抑郁风险预 [41]FATIMA I,ABBASI B,KHAN S,et al. Prediction of postpartum
测中的应用[J]. 中南大学学报:医学版,2020,45(10): depression using machine learning techniques from social media
1215-1222. DOI:10.11817/j.issn.1672-7347.2020.190655. text [J]. Expert Systems,2019,36(4):e12409. DOI:
XIAO M L,YAN C L,FU B,et al. Risk prediction for postpartum
10.1111/exsy.12409.
depression based on random forest[J]. Journal of Central South
[42]SHIN D,LEE K J,ADELUWA T,et al. Machine learning-based
University (Medical Science),2020,45(10):1215-1222.
predictive modeling of postpartum depression[J]. J Clin Med,
DOI:10.11817/j.issn.1672-7347.2020.190655.
2020,9(9):E2899. DOI:10.3390/jcm9092899.
[30]CHEN T Q,GUESTRIN C. XGBoost:a scalable tree boosting
[43]ANDERSSON S,BATHULA D R,ILIADIS S I,et al. Predicting
system[C]//KDD '16:Proceedings of the 22nd ACM SIGKDD
women with depressive symptoms postpartum with machine
International Conference on Knowledge Discovery and Data Mining.
learning methods[J]. Sci Rep,2021,11(1):7877. DOI:
2016:785-794. DOI:10.1145/2939672.2939785.
10.1038/s41598-021-86368-y.
[31]HOCHMAN E,FELDMAN B,WEIZMAN A,et al. Development
[44]HARRELL F E. Regression Modeling Strategies:With Applications
and validation of a machine learning-based postpartum depression
to LinearModels,Logistic and Ordinal Regression,and Survival
prediction model:a nationwide cohort study[J]. Depress
Analysis[M]. 2nd ed. New York:Springer,2019:63-102.
Anxiety,2021,38(4):400-411. DOI:10.1002/da.23123.
DOI:10.1007/978-3-319-19425-7.
[32]WEBB G.I. Naïve Bayes[M/OL]//Sammut C. Webb G.
[45]PODGORELEC V,KOKOL P,STIGLIC B,et al. Decision
Encyclopedia of Machine Learning and Data Mining. Boston:
trees:an overview and their use in medicine [J]. J Med Syst,
Springer,2016:1-2.[2022-01-15]. https://link.springer.
2002,26(5):445-463. DOI:10.1023/A:1016409317640.
com/referenceworkentry/10.1007/978-1-4899-7502-7_581-
[46]YU R J,ABDEL-ATY M. Utilizing support vector machine in real-
1#howtocite.
time crash risk evaluation[J]. Accid Anal Prev,2013,51:
[33]JIMÉNEZ-SERRANO S,TORTAJADA S,GARCÍA-GÓMEZ J M.
252-259. DOI:10.1016/j.aap.2012.11.027.
A mobile health application to predict postpartum depression based
[47]RILEY R D,ENSOR J,SNELL K I E,et al. Calculating the
on machine learning[J]. Telemed J E Health,2015,21(7):
sample size required for developing a clinical prediction model[J].
567-574. DOI:10.1089/tmj.2014.0113.
BMJ,2020,368:m441. DOI:10.1136/bmj.m441.
[34]BERGER J O. Statistical decision theory and Bayesian analysis [M].
[48]STEYERBERG E W,HARRELL F E Jr,BORSBOOM G J,et al.
New York:Springer Science & Business Media,2013:218-247.
Internal validation of predictive models:efficiency of some procedures
DOI:10.1007/978-1-4757-4286-2.
for logistic regression analysis[J]. J Clin Epidemiol,2001,54(8):
[35]HEARST M A,DUMAIS S T,OSUNA E,et al. Support vector
774-781. DOI:10.1016/s0895-4356(01)00341-9.
machines [J]. IEEE Intelligent Systems,1998,13(4):18-
[49]JUSTICE A C,COVINSKY K E,BERLIN J A. Assessing the
28. DOI:10.1109/5254.708428.
generalizability of prognostic information[J]. Ann Intern Med,
[36]ZHANG W N,LIU H,SILENZIO V M B,et al. Machine learning
models for the prediction of postpartum depression:application 1999,130(6):515-524. DOI:10.7326/0003-4819-130-6-
and comparison based on a cohort study[J]. JMIR Med Inform, 199903160-00016.
2020,8(4):e15516. DOI:10.2196/15516. (收稿日期:2022-02-05;修回日期:2022-05-15)
[37]MEYER D,LEISCH F,HORNIK K. The support vector machine (本文编辑:宋春梅)