基于机器学习的南京地区献血者精准招募方法的建立和应用*

doi:10.3969/j.issn.1671-2587.2024.04.018

临床输血与检验 ›› 2024, Vol. 26 ›› Issue (4): 535-543.DOI: 10.3969/j.issn.1671-2587.2024.04.018

基于机器学习的南京地区献血者精准招募方法的建立和应用^*

陈娟¹, 赵作彦^2,3, 田金玥^2,3, 张子涵^3,4, 周春¹, 蔡丽娜¹, 马宇驰¹, 周青杨¹, 薛晖^2,3, 梁文飚¹

¹江苏省血液中心;
²东南大学计算机科学与工程学院;
³新一代人工智能技术与交叉应用教育部重点实验室（东南大学）;
⁴东南大学软件学院; 江苏南京 210042

收稿日期:2024-07-02 出版日期:2024-08-20 发布日期:2024-09-23
通讯作者: 薛晖,主要从事机器学习、模式识别与计算机视觉方面研究,（E-mail）hxue@seu.edu.cn。梁文飚,主要从事血液安全方面研究,（E-mail）wenbiaoliang@hotmail.com。
作者简介:陈娟,主要从事献血者招募方面研究,（E-mail）695678835@qq.com。赵作彦,主要从事模式识别与计算机视觉方面研究,（E-mail）zuoyanzhao@seu.edu.cn;田金玥,主要从事模式识别与机器学习方面研究,（E-mail）jinyuetian@seu.edu.cn;张子涵,主要从事模式识别与计算机视觉方面研究,（E-mail）zzhdylan@seu.edu.cn;周春,主要从事网络及数据管理方面研究,（E-mail）21755316@qq.com。
基金资助:
*本课题受江苏省重点研发计划（社会发展）面上（No.BE2022811）项目资助

Machine Learning-based Development and Application of a Precise Blood Donor Recruitment Strategy in Nanjing

CHEN Juan¹, ZHAO Zuoyan^2,3, TIAN Jinyue^2,3, ZHANG Zihan^3,4, ZHOU Chun¹, CAI Lina¹, MA Yuchi¹, ZHOU Qingyang¹, XUE Hui^2,3, LIANG Wenbiao¹

¹Jiangsu Blood Center, Nanjing 210042;
²School of Computer Science and Engineering, Southeast University, Nanjing, 210096;
³Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education;
⁴College of Software Engineering, Southeast University, Nanjing, 210096

Received:2024-07-02 Online:2024-08-20 Published:2024-09-23

摘要/Abstract

摘要： 目的通过基于机器学习的方法,建立南京地区献血者精准招募模型并开展应用,以提高献血招募的效率和质量,招募更多的献血者,确保血液供应的安全性和充足性。方法对江苏省血液中心2017—2022年的献血和短信招募数据进行回顾性研究,利用极端梯度提升、支持向量机、K近邻算法、逻辑回归、决策树、随机森林、多层感知机等模型,并使用合成少数类过采样技术、下采样等多种采样技术,结合代价敏感方法（MFE、MSFE损失函数）进行训练,通过网格搜索选择性能较佳的机器学习模型。结果研究发现,机器学习模型对高意愿献血者招募成功率提升57.79%,机器学习模型可减少40.05%的短信发送数量,每条短信招募效率较常规方法平均提升12.26%,减少了短信发送数量,提高了每条短信的招募效率。结论机器学习算法可以对献血者进行精准识别,提高招募效率,减少不必要的短信发送,降低招募成本,为确保血液供应的安全性和充足性提供了有效的手段。

关键词: 献血者招募, 短信招募, 机器学习, 人工智能

Abstract: Objectives To establish and apply a precise blood donor recruitment model based on machine learning in Nanjing, thus enhancing the efficiency and quality of blood donation recruitment, incresing the number of blood donors, and ensuring the safety and sufficiency of blood supply. Methods This study retrospectively investigated blood donation and SMS recruitment data from Jiangsu Blood Center from 2017 to 2022. Various machine learning models, including eXtreme Gradient Boosting, Support Vector Machine, K-Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, and multi-layer perceptron models were used. These models were trained via techniques such as synthetic minority oversampling, under-sampling and cost-sensitive methods (mean false error and mean squared false error).The grid search method was used to select the machine learning models with better performance. Results The implemented machine learning model demonstrated a 57.79% improvement in the success rate of recruiting high willingness blood donors. Additionally, it reduced the number of SMS sending by 40.05%, and increased the recruitment efficiency of each SMS by an average of 12.26% compared with the conventional method. Conclusion Machine learning algorithms could accurately identify potential blood donors, thereby improving recruitment efficiency, reducing unnecessary SMS messages, decreasing recruitment costs, and providing an effective means to ensure the safety and adequacy of blood supply.

Key words: Blood donor recruitment, SMS recruitment, Machine Learning, Artificial Intelligence

中图分类号:

R457

陈娟, 赵作彦, 田金玥, 张子涵, 周春, 蔡丽娜, 马宇驰, 周青杨, 薛晖, 梁文飚. 基于机器学习的南京地区献血者精准招募方法的建立和应用^*[J]. 临床输血与检验, 2024, 26(4): 535-543.

CHEN Juan, ZHAO Zuoyan, TIAN Jinyue, ZHANG Zihan, ZHOU Chun, CAI Lina, MA Yuchi, ZHOU Qingyang, XUE Hui, LIANG Wenbiao. Machine Learning-based Development and Application of a Precise Blood Donor Recruitment Strategy in Nanjing[J]. JOURNAL OF CLINICAL TRANSFUSION AND LABORATORY MEDICINE, 2024, 26(4): 535-543.

参考文献

[1] 世界卫生组织. 血液安全与可得性[EB/OL].(2023-06-02). https://www.who.int/zh/news-room/fact-sheets/detail/blood-safety-and-availability.
[2] 中国新闻网. “献血点亮生命之光”主题活动在深圳启动[EB/OL].(2024-06-13). https://www.chinanews.com.cn/sh/2024/06-13/10233033.shtml.
[3] WU H Y,LI Z G,SUN X K,et al.Predicting willingness to donate blood based on machine learning:two blood donor recruitments during COVID-19 outbreaks[J]. Sci Rep, 2022,12(1):19165.
[4] CHEN T Q,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM,2016:785-794.
[5] CORTES C,VAPNIK V.Support-vector networks[J]. Mach Learn,1995,20(3):273-297.
[6] BREIMAN L.Random forests[J]. Mach Learn, 2001,45(1):5-32.
[7] ROSENBLATT F.The perceptron:a probabilistic model for information storage and organization in the brain[J]. Psychol Rev,1958,65(6):386-408.
[8] CHAWLA N V,BOWYER K W,HALL L O,et al.SMOTE:synthetic minority over-sampling technique[J]. Jair,2002,16:321-357.
[9] WANG S J,LIU W,WU J,et al.Training deep neural networks on imbalanced data sets[C]//2016 International Joint Conference on Neural Networks (IJCNN). July 24-29,2016,Vancouver,BC,Canada. IEEE,2016:4368-4374.
[10] HANAPI WHWM, SARKAN H, SJARIF N N A, et al. A prediction model for blood donation using multiple logistic regression[J]. Open International Journal of Informatics, 2019, 7(Special Issue 2): 147-157.
[11] SALAZAR-CONCHA C,RAMÍREZ-CORREA P. Predicting the intention to donate blood among blood donors using a decision tree algorithm[J]. Symmetry, 2021,13(8):1460.
[12] MARADE C, PRADEEP A, MOHANTY D, et al.Forecasting blood donor response using predictive modeling approach[J]. International Journal of Computer Science and Mobile Computing, 2019,8(4): 73-77.
[13] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J]. Neural Comput,1997,9(8):1735-1780.
[14] DING X Y,ZHANG X,LI X F,et al.A hybrid neural network based model for blood donation forecasting[J]. J Biomed Inform,2023,146:104488.
[15] FREUND Y,SCHAPIRE R E.A decision-theoretic generalization of on-line learning and an application to boosting[J]. J Comput Syst Sci,1997,55(1):119-139.
[16] EL-RASHIDY N,EL-GHAMRY A,ELSAYED N E.Machine learning for blood donors classification model using ensemble learning[M]//Lecture Notes in Networks and Systems. Singapore:Springer Nature Singapore,2023:173-181.
[17] SELVARAJ P,SARIN A,SERAPHIM B I.Blood donation prediction system using machine learning techniques[C]//2022 International Conference on Computer Communication and Informatics (ICCCI). January 25-27,2022,Coimbatore,India. IEEE,2022:1-4.
[18] SELVARAJ P,SARIN A,SERAPHIM B I.Forecasting system for donation of blood using SVM model[J]. Int J Res Appl Sci Eng Technol,2022,10(5):136-140.
[19] HANDOJO A,PURBOWO A N,KARAENG G B,et al.Predicting potential blood donors who can attend blood donation activities using a support vector machine[C]//2022 5th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). December 8-9,2022,Yogyakarta,Indonesia. IEEE,2022:351-355.
[20] 马宇驰. 一种基于深度学习的献血者精准招募方法[J]. 计算机应用文摘,2024(9):92-95.
[21] 医新苑. 项目展示|基于献血者用户画像的精准招募系统[EB/OL].(2024-05-17). https://mp.weixin.qq.com/s?__biz=MzAxMjExMjM4MQ==&mid=2651769382&idx=3&sn=af0960b6c27e7e37cba6d332d8cc5d04&chksm=804cb2b4b73b3ba2cf7ef300523903b851bcb7c6830a32103e14008051abff9b9dab02878e57#rd.
[22] LIU H,ZHOU Y,LIU B,et al.Incremental learning with neural networks for computer vision:a survey[J]. Artif Intell Rev,2023,56(5):4557-4589.

基于机器学习的南京地区献血者精准招募方法的建立和应用^*

Machine Learning-based Development and Application of a Precise Blood Donor Recruitment Strategy in Nanjing

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

关于本刊

作者中心

在线期刊

访问统计

联系我们

[1]	赵兴丹, 翁艾罕. 极低出生体重儿输血及输血量的影响因素及其预测模型构建[J]. 临床输血与检验, 2023, 25(6): 758-766.
[2]	范可欣, 朱鹏汇, 王云, 王勇军, 张宁洁. 基于机器学习算法建立胎母输血综合征预测模型^*[J]. 临床输血与检验, 2022, 24(4): 427-432.
[3]	王克成, 王小芹, 严峰, 张良. 标准话术在献血者沟通中的应用^*[J]. 临床输血与检验, 2021, 23(5): 655-658.