需求预测视角下的医疗数据价值

doi:10.16381/j.cnki.issn1003-207x.2022.0562

Abstract

Abstract:

The rapid development of digital technology has advanced global digitalization. As a vital resource for driving economic growth， the value assessment of data has not yet formed a unified paradigm. With the expansion of data scale， the data quality disparity and data distortion urgently need to be addressed. The valuation of data is considered beneficial for evaluating data quality， filtering out distorted data， and promoting data trade， making its importance self-evident. In this paper， an online medical platform is used as the context， and the Shapley value method is employed to evaluate the value of data in doctor-patient matching. The efficiency of data value on the platform is intended to be improved through the data valuation results. First， the demand of doctors for the next year is predicted through the historical characteristics of doctors and the XGBoost model. Second， an operational profit function of hospitals based on the prediction results is constructed according to the online service mode of the medical platform， forming a value chain of data， model， and benefit. Finally， the Shapley value is used to assess data value， the effectiveness of the value assessment method is validated， and the characteristics of high-value data on the platform are analyzed. It is found that data value can be captured according to the task by the Shapley value. Cost reduction and efficiency increase of the model can be realized by filtering data based on the Shapley value， then enhancing the efficiency of application of data. Additionally， false data on the platform can be find， improving data quality. Therefore， appropriate valuation of data is seen as beneficial for better business understanding of the platform and enhancement of the efficiency of data.

Key words: data valuation, online medical platform, Shapley value

CLC Number:

F272.3

Yue Zhao,Yanzhi Wang,Jie Song,Xuan He. Research on Data Value Based on Demand Forecast of Online Medical Platform[J]. Chinese Journal of Management Science, 2024, 32(7): 28-36.

Figures/Tables 13

符号	意义
$t$	$t ∈ 1,2, …$ 为平台进行预测-决策的时间点
$i$	$i ? ∈ 1,2, …, n$ 代表平台的医生
$D i t$	医生i在第t期的实际需求患者数
$D ? i t$	平台预测医生i在第t期的需求患者数
$Δ D i t$	平台预测的需求误差
$S i t$	平台预测医生i在第t期的需求时长
$w i$	医生工作单位时间的薪资
$τ$	医生服务一位患者的平均时长
$α$	临时服务每位患者的调度费
$X t$	截止到第t期平台收集的历史数据
$r i$	医生i服务一位患者的平台收益分成
$R i t$	第i位医生在第t期为平台带来的收益
$R i t *$	第i位医生在第t期为平台带来的最大收益
$R t$	平台在第t期的总收益
$V$	沙普利价值计算使用的效用函数

References 39

1	郭薇，薛澜.互联网医疗的现实定位与未来发展［J］.探索，2016（6）：142-148.
	Guo W， Xue L. The realistic positioning and future development of internet healthcare［J］. Probe，2016（6）：142-148.
2	陈惠芳，徐卫国. 价值共创视角下互联网医疗服务模式研究［J］. 现代管理科学， 2016（3）： 30-32.
	Chen H F， Xu W G. Research on internet medical service model from the perspective of value co-creation［J］. Modern Management Science， 2016（3）： 30-32.
3	Sillence E， Briggs P， Harris P， et al. A framework for understanding trust factors in web-based health advice［J］. International Journal of Human-Computer Studies， 2006， 64（8）： 697-713.
4	Slotin J. What do we know about the value of data［EB/OL］.（2018-05-03）［2018-05-03］..
5	EC， IMF， OECD， and WB UN. Systems of national accounts 2008［M］.New York： United Nations，2009.
6	Akred J， Samani A. Your data is worth more than you think［EB/OL］.（2018-12-17）［2018-12-17］..
7	Li W， Nirei M， Yamana K. Value of data： There’s no such thing as a free lunch in the digital economy［R］. Working Papers， Bureau of Economic Analysis， 2018.
8	Mawer C.Valuing data is hard［EB/OL］. （2015-11-10）［2015-11-10］..
9	Elia G， Polimeno G， Solazzo G， et al. A multi-dimension framework for value creation through big data［J］. Industrial Marketing Management， 2020， 90： 617-632.
10	许宪春，张美慧.中国数字经济规模测算研究——基于国际比较的视角［J］.中国工业经济，2020（5）： 23-41.
	Xu X C， Zhang M H. Research on the scale measurement of China’s digital economy： Based on the perspective of international comparison［J］. China Industrial Economics， 2020（5）： 23-41.
11	Pratt J W， Raiffa H， Schlaifer R. Introduction to statistical decision theory［M］. Cambridge， Massachusetts： MIT Press， 1995.
12	Anscombe F J. Probability and statistics for business decisions： An introduction to managerial economics under uncertainty［J］. Publications of the American Statistical Association， 1959， 54（288）：813-814.
13	Raiffa H， Schlaifer R. Applied statistical decision theory［M］. USA：Wiley， 1961.
14	Wilson E C F. A practical guide to value of information analysis［J］. Pharmacoeconomics， 2015，33（2）： 105-121.
15	Claxton K. The irrelevance of inference： A decision-making approach to the stochastic evaluation of health care technologies［J］. Journal of Health Economics， 1999， 18（3）： 341-364.
16	Eckermann S， Willan A R. Expected value of information and decision making in HTA［J］. Health Economics， 2007， 16（2）： 195-209.
17	Willan A R. Statistical analysis of cost-effectiveness data［J］. Expert Review of Pharmacoeconomics & Outcomes Research， 2006， 6（3）：337-346.
18	Koh P W， Liang P. Understanding black-box predictions via influence functions［C］//Proceedings of the 34th International Conference on Machine Learning-Volume 70， Sydney， Australia， August 06-11 ， ML Research Press， 2017： 1885-1894.
19	Shapley L S. A value for n-person games［M/OL］. Princeton： Princeton University Press， 1953：307-318. .
20	Gul F. Bargaining foundations of Shapley value［J］. Econometrica： Journal of the Econometric Society， 1989，57（1）：81-95.
21	Ghorbani A， Zou J. Data shapley： Equitable valuation of data for machine learning［C］//Proceedings of International Conference on Machine Learning.PMLR，Long Beach， California， USA， June 9-15 ， ML Research Press， 2019： 2242-2251.
22	Jia R X， Wu F， Sun X H， et al. Scalability vs. utility： Do we have to sacrifice one for the other in data importance quantification？［C］//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition， Nashville， TN， USA， June 20-25， IEEE， 2021： 8239-8247.
23	Yoon J， Arik S， Pfister T. Data valuation using reinforcement learning［C］//Proceedings of International Conference on Machine Learning. PMLR，Virtual， July 13-18 ， ML Research Press， 2020： 10842-10851.
24	Ghorbani A， Kim M， Zou J. A distributional framework for data valuation［C］//Proceesdings of International Conference on Machine Learning. PMLR，Virtual， July 13-18 ， ML Research Press， 2020： 3535-3544.
25	Jia R， Dao D， Wang B， et al. Towards efficient data valuation based on the shapley value［C］//Proceedings of The 22nd International Conference on Artificial Intelligence and Statistics. PMLR， Naha， Okinawa， Japan， April 16-18 ， ML Research Press， 2019： 1167-1176.
26	Kwon Y， Rivas M A， Zou J. Efficient computation and analysis of distributional shapley values［C］//Proceedings of International Conference on Artificial Intelligence and Statistics.PMLR， Virtual， April 13-15 ， ML Research Press， 2021： 793-801.
27	Wei S， Tong Y， Zhou Z， et al. Efficient and fair data valuation for horizontal federated learning［J］. Federated Learning： Privacy and Incentive， 2020： 139-152.
28	Shim D， Mai Z， Jeong J， et al. Online class-incremental continual learning with adversarial shapley value［C］//Proceedings of the AAAI Conference on Artificial Intelligence，Virtual， Februar y2-9， Research PressML， 2021， 35（11）： 9630-9638.
29	Agarwal A， Dahleh M， Sarkar T. A marketplace for data： An algorithmic solution［C］//Proceedings of the 2019 ACM Conference on Economics and Computation， Phoenix， AZ， USA， June 24-28，Association for Computing Machinery， 2019： 701-726.
30	Quinlan J R. Induction of decision trees［J］. Machine learning， 1986（1）： 81-106.
31	Zhu X Q， Wu X D. Class noise vs. attribute noise： A quantitative study［J］.The Artificial Intelligence Review， 2004， 22（3）： 177-210.
32	Wu X D. Knowledge acquisition from databases［M］. Norwood， NJ， USA： Ablex Publishing Corp， 1996.
33	Friedman J， Hastie T， Tibshirani R. Additive logistic regression： A statistical view of boosting （with discussion and a rejoinder by the authors）［J］. The Annals of statistics， 2000， 28（2）： 337-407.
34	Freund Y. An adaptive version of the boost by majority algorithm［C］//Proceedings of the Twelfth Annual Conference on Computational learning theory， Santa Cruz， California， USA， Jul y7-9， Association for Computing Machinery， 1999： 102-113.
35	Sun J， Zhao F， Wang C， et al. Identifying and correcting mislabeled training instances［C］//Proceedings of Future Generation Communication and Networking （FGCN 2007）， Jeju Island， Korea， December 6-8， IEEE， 2007， 1： 244-250.
36	Jeatrakul P， Wong K W， Fung C C. Data cleaning for classification using misclassification analysis［J］. Journal of Advanced Computational Intelligence and Intelligent Informatics， 2010， 14（3）： 297-302.
37	Manwani N， Sastry P S. Noise tolerance under risk minimization［J］. IEEE Transactions on Cybernetics， 2013， 43（3）： 1146-1151.
38	Gaba A， Winkler R L. Implications of errors in survey data： A Bayesian model［J］. Management Science， 1992， 38（7）： 913-925.
39	Kozachenko L F， Leonenko N N. Sample estimate of the entropy of a random vector［J］. Problemy Peredachi Informatsii， 1987， 23（2）： 9-16.

变量名称	变量类型	变量介绍
性别	定性变量	医生性别
医院级别	定性变量	所在医院级别
文章数	定量变量	医生在平台上传的有关疾病治疗的文章数量
诊后患者报到数	定量变量	为患者在线上问诊结束后，转到线下进一步问诊的患者数量
患者投票	定量变量	患者根据自己在问诊过程中服务的满意程度，对医生进行网上投票数量
感谢信	定量变量	患者根据自己在问诊过程中服务的满意程度，为医生写的感谢信数量
心意礼物	定量变量	患者根据自己在问诊过程中服务的满意程度，为医生赠送的虚拟礼物数量
一般等待时长	定量变量	医生对于患者问诊需求的响应速度
综合推荐热度	定量变量	平台通过医生的背景信息、患者投票和患者报道综合计算的推荐热度
总单量	定量变量	根据订单详细信息统计，2019-2020年每位医生平台总订单量。模型的预测目标。

SV分位数	心意礼物	感谢信	综合推荐热度	诊后患者报到	文章数	总单量
0%～20%	-0.036	-0.066	-0.052	-0.037	0.067	34.66
20%～40%	-0.040	-0.041	-0.057	-0.046	-0.022	26.03
40%～60%	-0.058	-0.041	-0.049	-0.059	-0.019	25.62
60%～80%	0.093	0.052	0.024	0.084	-0.014	37.13
80%～100%	0.040	0.095	0.134	0.058	-0.011	48.52

[1]	Weizhen Rao,Xiaohe Miao,lu Liu. Research on Collaborative Distribution Model Considering Distribution Capability Constraints of Enterprises and Its Influence on Cost Allocation [J]. Chinese Journal of Management Science, 2024, 32(7): 106-116.
[2]	Er-fang SHAN. The Cooperative Game Approach for River Flooding Risk [J]. Chinese Journal of Management Science, 2023, 31(9): 45-51.
[3]	NI Xuan-ming, QIU Yu-ning, ZHAO Hui-min. The Mechanism and Solution of Equity Gap in Private Equity Market [J]. Chinese Journal of Management Science, 2023, 31(7): 91-102.
[4]	NAN Jiang-xia, WANG Pan-pan, LI Deng-feng. A Solution Method for Shapley-based Equilibrium Strategies of Biform Games [J]. Chinese Journal of Management Science, 2021, 29(5): 202-210.
[5]	LIU Pei-de, TENG Fei. Multiple Attribute Group Decision-Making Method Based on Evidential Reasoning and Generalized Shapley for Extended Probabilistic Linguistic Term Set [J]. Chinese Journal of Management Science, 2020, 28(11): 206-218.
[6]	WU Jun, XU Di. Value Sharing of Business Model Innovation Based on Shapley Value [J]. Chinese Journal of Management Science, 2019, 27(6): 191-205.
[7]	WANG Da-ao, JIAN Li-rong, WANG Hui, LIU Si-feng. Study on Profit Allocation of Industrial Cluster Based on Restricted Cooperative Game [J]. Chinese Journal of Management Science, 2019, 27(4): 171-178.
[8]	YE Yin-fang, LI Deng-feng, YU Gao-feng. Joint Replenishment Interval-Valued EOQ Model and Cost Allocation Approach Based on Variable-weighted Shapely Value [J]. Chinese Journal of Management Science, 2019, 27(10): 90-99.
[9]	ZHANG Shen, MENG Qing-chun, AN Guo-zheng. Coordinated Pricing in the Dual Channel Supply Chain with the Commission Rate of the E-commerce Platform [J]. Chinese Journal of Management Science, 2019, 27(10): 44-55.
[10]	LIU Wen-li, WANG Ying-ming, LV Shu-long. Ranking Decision Making Units Based on Cross-efficiency and Cooperative Game [J]. Chinese Journal of Management Science, 2018, 26(4): 163-170.
[11]	ZHANG De-bin, XU Juan, Paul D. Mitchell, LI Chong-guang. Stability Research for Cooperation Between Farmers and Dealers in China: An Analysis of Marketing Risks Sharing [J]. Chinese Journal of Management Science, 2017, 25(7): 93-101.
[12]	ZHANG Yu, JIAN Li-rong, LIU Si-feng, ZHAO Huan-huan, LIU Yong. Interests Coordination Mechanism of University-Industry Network Cooperation Based on Optimized Shapley Value——A Case Study in Industrial Technology Innovation Strategy Alliance [J]. Chinese Journal of Management Science, 2016, 24(9): 36-44.
[13]	SUN Xiao-lei, YAO Xiao-yang, YANG Yu-ying, WU Deng-sheng, LI Jian-ping. Multi-scale Feature Extraction and Identification of Country Risk Dynamics:Cases of OPEC Countries [J]. Chinese Journal of Management Science, 2015, 23(4): 1-10.
[14]	WANG Jun, WANG Mei-rong, QU Ran-lin. Research on the Equitable Apportionment of Marine Salvage Reward Based on Collaborative Rescue at Sea [J]. Chinese Journal of Management Science, 2014, 22(9): 74-81.
[15]	ZHAO Xiao-li, QI Jian-xun. Distribution of Cooperation Benefits under Different Supply Chains——The Case of Coal and Eletric Power Enterprises [J]. Chinese Journal of Management Science, 2007, 15(4): 70-76.

Research on Data Value Based on Demand Forecast of Online Medical Platform

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 39

Related Articles 15

Metrics

Comments

Recommended 0