Prediction method of liver transplantation complications based on transfer component analysis and support vector machine

doi:10.11772/j.issn.1001-9081.2021060886

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (12): 3608-3613.DOI: 10.11772/j.issn.1001-9081.2021060886

• The 18th China Conference on Machine Learning • Previous Articles

Prediction method of liver transplantation complications based on transfer component analysis and support vector machine

Hongliang CAO¹^,², Ying ZHANG¹^,²(), Bin WU¹, Fanyu LI¹, Xubo NA¹

^1.School of Control and Computer Engineering，North China Electric Power University，Beijing 102206，China
^2.Beijing Key Laboratory of Traf?c Data Analysis and Mining （Beijing Jiaotong University），Beijing 100044，China

Received:2021-05-12 Revised:2021-06-14 Accepted:2021-06-23 Online:2021-12-28 Published:2021-12-10
Contact: Ying ZHANG
About author:CAO Hongliang， born in 2000. His research interests include machine learning， artificial intelligence.
WU Bin， born in 1996， M. S. candidate. His research interests include deep learning， spatio-temporal big data.
LI Fanyu， born in 1998， M. S. candidate. Her research interests include reinforcement learning， path planning.
NA Xubo， born in 1994， M. S. candidate. His research interests include urban computing， spatio-temporal big data.
Supported by:
the Surface Program of National Natural Science Foundation of China(52078212)

基于迁移成分分析和支持向量机的肝移植并发症预测方法

曹鸿亮¹^,², 张莹¹^,²(), 武斌¹, 李繁菀¹, 那绪博¹

^1.华北电力大学控制与计算机工程学院，北京 102206
^2.交通数据分析与挖掘北京市重点实验室（北京交通大学），北京 100044

通讯作者: 张莹
作者简介:曹鸿亮（2000—），男，江苏淮安人，主要研究方向：机器学习、人工智能
武斌（1996—），男，河北邯郸人，硕士研究生，主要研究方向：深度学习、时空大数据
李繁菀（1998—），女，湖南株洲人，硕士研究生，主要研究方向：强化学习、路径规划
那绪博（1994—），男，辽宁沈阳人，硕士研究生，主要研究方向：城市计算、时空大数据。
基金资助:
国家自然基金面上项目(52078212)

Abstract

Abstract:

Many machine learning algorithms can cope well with prediction and classification， but these methods suffer from poor prediction accuracy and F1 score when they are used on medical datasets with small samples and large feature spaces. To improve the accuracy and F1 score of liver transplantation complication prediction， a prediction and classification method of liver transplantation complications based on Transfer Component Analysis （TCA） and Support Vector Machine （SVM） was proposed. In this method， TCA was used for mapping and dimension reduction of the feature space， and the source domain and the target domain were mapped to the same reproducing kernel Hilbert space， thereby achieving the adaptivity of edge distribution. The SVM was trained in the source domain after transferring， and the complications were predicted in the target domain after training. In the liver transplantation complication prediction experiments for complication Ⅰ， complication Ⅱ， complication Ⅲa， complication Ⅲb， and complication Ⅳ， compared with the traditional machine learning and Heterogeneous Domain Adaptation （HDA）， the accuracy of the proposed method was improved by 7.8% to 42.8%， and the F1 score reached 85.0% to 99.0%， while the traditional machine learning and HDA had high accuracy but low recall due to the imbalance of positive and negative samples. Experimental results show that TCA combined with SVM can effectively improve the accuracy and F1 score of liver transplantation complication prediction.

Key words: transfer learning, Transfer Component Analysis (TCA), Support Vector Machine (SVM), liver transplantation, prediction of complications

摘要：

已有很多机器学习算法能够很好地应对预测分类问题，但这些方法在用于小样本、大特征空间的医疗数据集时存在着预测准确率和F1值不高的问题。为改善肝移植并发症预测的准确率和F1值，提出一种基于迁移成分分析（TCA）和支持向量机（SVM）的肝移植并发症预测分类方法。该方法采用TCA进行特征空间的映射和降维，将源领域和目标领域映射到同一再生核希尔伯特空间，从而实现边缘分布自适应；迁移完成之后在源领域上训练SVM，训练完成后在目标领域上实现并发症的预测分析。在肝移植并发症预测实验中，针对并发症Ⅰ、并发症Ⅱ、并发症Ⅲa、并发症Ⅲb、并发症Ⅳ进行预测，与传统机器学习和渐进式对齐异构域适应（HDA）相比，所提方法的准确率提升了7.8%~42.8%，F1值达到85.0%~99.0%，而传统机器学习和HDA由于正负样本不均衡出现了精确率很高而召回率很低的情况。实验结果表明TCA结合SVM能够有效提高肝移植并发症预测的准确率和F1值。

关键词: 迁移学习, 迁移成分分析, 支持向量机, 肝移植, 并发症预测

CLC Number:

TP18

Hongliang CAO, Ying ZHANG, Bin WU, Fanyu LI, Xubo NA. Prediction method of liver transplantation complications based on transfer component analysis and support vector machine[J]. Journal of Computer Applications, 2021, 41(12): 3608-3613.

曹鸿亮, 张莹, 武斌, 李繁菀, 那绪博. 基于迁移成分分析和支持向量机的肝移植并发症预测方法[J]. 《计算机应用》唯一官方网站, 2021, 41(12): 3608-3613.

符号	说明	符号	说明
$X s ∈ R d s × n s$	源领域原始数据	$X ∈ R m × n$	$X s, X t$
$X t ∈ R d t × n t$	目标领域原始数据	$B ∈ R m × k$	共享字典编码
$M ∈ R n × n$	MMD矩阵	$S ∈ R k × n$	$S s, S t$

数据集	样本数	正例数
术后并发症I	425	301
术后并发症Ⅱ	425	99
术后并发症Ⅲa	425	42
术后并发症Ⅲb	425	33
术后并发症Ⅳ	425	283
V级（死亡）	425	40

术前特征	特征数	术中特征	特征数	术后特征	特征数
血常规	10	术中情况	46	输血情况	34
生化	10	血气	110	出院前后转归	4
血气	11			血常规	90
凝血	7			生化	90
				血气	44
				凝血	63

1	PRODANOVA K， UZUNOVA Y. Prediction of graft dysfunction in pediatric liver transplantation by logistic regression［C］// Proceedings of the 2020 International Conference on Mathematics and Computers in Science and Engineering. Piscataway： IEEE， 2020：260-263. 10.1109/macise49704.2020.00054
2	余忠山，江艺，蔡秋程，等. 肝移植后的并发症［J］. 中国组织工程研究， 2013， 17（18）：3275-3282. 10.3969/j.issn.2095-4344.2013.18.007
	YU Z S， JIANG Y， CAI Q C， et al. Complications after liver transplantation［J］. Chinese Journal of Tissue Engineering Research， 2013， 17（18）：3275-3282. 10.3969/j.issn.2095-4344.2013.18.007
3	陈规划，何晓顺，叶小鸣，等. 临床原位肝移植术后并发症分析［J］. 肝胆外科杂志， 1995（3）：157-159. 10.3321/j.issn:0529-5815.2008.12.009
	CHEN G H， HE X S， YE X M， et al. Analysis of complications after clinical orthotopic liver transplantation［J］. Journal of Hepatobiliary Surgery， 1995（3）：157-159. 10.3321/j.issn:0529-5815.2008.12.009
4	《中国组织工程研究与临床康复》杂志社学术部. 中国肝移植的历史记录［J］. 中国组织工程研究与临床康复， 2011， 15（18）：3365-3366. 10.1142/9789814374415_0001
	Academic department of magazine Chinese Journal of Tissue Engineering Research. History records of liver transplantation in China［J］. Chinese Journal of Tissue Engineering Research， 2011， 15（18）：3365-3366. 10.1142/9789814374415_0001
5	LIU C L， SOONG R S， LEE W C， et al. Predicting shortterm survival after liver transplantation using machine learning［J］. Scientific Reports， 2020， 10： No.5654. 10.1038/s41598-020-62387-z
6	KANTIDAKIS G， PUTTER H， LANCIA C， et al. Survival prediction models since liver transplantation - comparisons between cox models and machine learning techniques［J］. BMC Medical Research Methodology， 2020， 20： No.277. 10.1186/s12874-020-01153-1
7	史斌，王建立. 人工智能对肝癌患者预后预测的研究进展［J］. 解放军医学院学报， 2020， 41（9）：922-925， 953. 10.3969/j.issn.2095-5227.2020.09.017
	SHI B， WANG J L. Research advances in artificial intelligence in predicting prognosis of patients with hepatocellular carcinoma［J］. Academic Journal of Chinese PLA Medical School， 2020， 41（9）：922-925， 953. 10.3969/j.issn.2095-5227.2020.09.017
8	胡满满，陈旭，孙毓忠，等. 基于动态采样和迁移学习的疾病预测模型［J］. 计算机学报， 2019， 42（10）：23392354. 10.11897/SP.J.1016.2019.02339
	HU M M， CHEN X， SUN Y Z， et al. A disease prediction model based on dynamic sampling and transfer learning［J］. Chinese Journal of Computers， 2019， 42（10）：2339-2354. 10.11897/SP.J.1016.2019.02339
9	臧绍飞. 基于特征迁移与模型迁移的分类器设计［D］. 徐州：中国矿业大学， 2017：133.
	ZANG S F. Classifier design based on feature transfer and model transfer［D］. Xuzhou： China University of Mining and Technology， 2017：133.
10	PAN S J， YANG Q. A survey on transfer learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2010， 22（10）：1345-1359. 10.1109/tkde.2009.191
11	于重重，田蕊，谭励，等. 非平衡样本分类的集成迁移学习算法［J］. 电子学报， 2012， 40（7）：1358-1363. 10.3969/j.issn.0372-2112.2012.07.012
	YU C C， TIAN R， TAN L， et al. Integrated transfer learning algorithmic for unbalanced samples classification［J］. Acta Electronica Sinica， 2012， 40（7）：1358-1363. 10.3969/j.issn.0372-2112.2012.07.012
12	PAN S J， TSANG I W， KWOK J T， et al. Domain adaptation via transfer component analysis［J］. IEEE Transactions on Neural Networks， 2011， 22（2）：199-210. 10.1109/tnn.2010.2091281
13	PAN J H， HU X G， LI P P， et al. Domain adaptation via multi-layer transfer learning［J］. Neurocomputing， 2016， 190：10-24. 10.1016/j.neucom.2015.12.097
14	龙明盛. 迁移学习问题与方法研究［D］. 北京：清华大学， 2014：134.
	LONG M S. Transfer learning： problems and methods［D］. Beijing： Tsinghua University， 2014：134.
15	LONG M S， WANG J M， DING G G， et al. Transfer feature learning with joint distribution adaptation［C］// Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2013：2200-2207. 10.1109/iccv.2013.274
16	LI J J， LU K， HUANG Z， et al. Heterogeneous domain adaptation through progressive alignment［J］. IEEE Transactions on Neural Networks and Learning Systems， 2019， 30（5）：1381-1391. 10.1109/tnnls.2018.2868854
17	HEARST M A， DUMAIS S T， OSUNA E， et al. Support vector machines［J］. IEEE Intelligent Systems and Their Applications， 1998， 13（4）：18-28. 10.1109/5254.708428
18	奉国和. SVM分类核函数及参数选择比较［J］. 计算机工程与应用， 2011， 47（3）：123-124， 128. 10.3778/j.issn.1002-8331.2011.03.037
	FENG G H. Parameter optimizing for Support Vector Machines classification［J］. Computer Engineering and Applications， 2011， 47（3）：123-124， 128. 10.3778/j.issn.1002-8331.2011.03.037

[1]	CHEN Zhengtao, HUANG Can, YANG Bo, ZHAO Li, LIAO Yong. Yak face recognition algorithm of parallel convolutional neural network based on transfer learning [J]. Journal of Computer Applications, 2021, 41(5): 1332-1336.
[2]	JIA Heming, JIANG Zichao, LI Yao, SUN Kangjian. Simultaneous feature selection optimization based on improved spotted hyena optimizer algorithm [J]. Journal of Computer Applications, 2021, 41(5): 1290-1298.
[3]	WANG Jinkai, JIA Xu. Vein recognition algorithm based on Siamese nonnegative matrix factorization with transferability [J]. Journal of Computer Applications, 2021, 41(3): 898-903.
[4]	YUAN Qianqian, DENG Hongmin, WANG Xiaohang. Citrus disease and insect pest area segmentation based on superpixel fast fuzzy C-means clustering and support vector machine [J]. Journal of Computer Applications, 2021, 41(2): 563-570.
[5]	Xiancong CHEN, Weike PAN, Zhong MING. Staged variational autoencoder for heterogeneous one-class collaborative filtering [J]. Journal of Computer Applications, 2021, 41(12): 3499-3507.
[6]	Xiaolong LIU, Shitong WANG. Open set fuzzy domain adaptation algorithm via progressive separation [J]. Journal of Computer Applications, 2021, 41(11): 3127-3131.
[7]	Jianfang CAO, Minmin YAN, Yiming JIA, Xiaodong TIAN. Application of Inception-v3 model integrated with transfer learning in dynasty identification of ancient murals [J]. Journal of Computer Applications, 2021, 41(11): 3219-3227.
[8]	Jin ZHAO, Wen’ai SONG, Jun TAI, Jijiang YANG, Qing WANG, Xiaodan LI, Yi LEI, Yue QIU. Review of computer-aided face diagnosis for obstructive sleep apnea in children [J]. Journal of Computer Applications, 2021, 41(11): 3394-3401.
[9]	Kai LI, Jie LI. Structure-fuzzy multi-class support vector machine algorithm based on pinball loss [J]. Journal of Computer Applications, 2021, 41(11): 3104-3112.
[10]	TONG Lin, GUAN Zheng. Fuzzy granulation prediction of traffic flow based on improved whale optimization support vector machine [J]. Journal of Computer Applications, 2021, 41(10): 2919-2927.
[11]	HUANG Xueyu, XU Haote, TAO Jianwen. Multi-source adaptation classification framework with feature selection [J]. Journal of Computer Applications, 2020, 40(9): 2499-2506.
[12]	ZHANG Chenxi, TANG Shu, TANG Ke. Strategies of parameter fault detection for rocket engines based on transfer learning [J]. Journal of Computer Applications, 2020, 40(9): 2774-2780.
[13]	BAI Ruyi, GUO Xiaoying, JIA Chunhua. Sentiment prediction of small sample abstract painting image based on feature fusion [J]. Journal of Computer Applications, 2020, 40(8): 2207-2213.
[14]	MA Jinlin, WEI Meng, MA Ziping. Pulmonary nodule segmentation method based on deep transfer learning [J]. Journal of Computer Applications, 2020, 40(7): 2117-2125.
[15]	ZHANG Jianming, SHI Yuanhao, XU Zhengyi, WEI Jianming. Adaptive UWB/PDR fusion positioning algorithm based on error prediction [J]. Journal of Computer Applications, 2020, 40(6): 1755-1762.

Prediction method of liver transplantation complications based on transfer component analysis and support vector machine

基于迁移成分分析和支持向量机的肝移植并发症预测方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 18

Related Articles 15

Recommended Articles

Metrics