Li Jing, Wang Dejian, Qi Guoqiang, Li Zheming, Huang Jian, Zhu Zhu, Shen Chen, Lin Bo, Dong Kexiong, Zhao Baolong, Shu Qiang, Yin Jianwei, Yu Gang
Department of Data and Information, The Children's Hospital Zhejiang University School of Medicine, Hangzhou, China.
Department of Research, Sino-Finland Joint AI Laboratory for Child Health of Zhejiang Province, Hangzhou, China.
Ann Transl Med. 2022 Aug;10(15):836. doi: 10.21037/atm-22-3671.
Multicenter clinical research faces many challenges, including how to quantitatively evaluate the data contribution of each research center. However, few data pricing model meets the requirements to the scenario. Thus, a suitable mechanism to measure the data value for clinical research is required.
Extensive documents were acquired and analyzed, including a rare disease list from the National Health Commission, data structures of the electronic medical records (EMR) system, diagnosis-related groups (DRGs) regulations from the Health Commission of Zhejiang Province, and the Clinical Service Price List of Zhejiang Province. Nine senior experts were invited as consultants from hospital and enterprises with professional field of clinical research, data governance, and health economics. After brainstorming and expert evaluation, seven data attributes were identified as the main factors affecting the value of medical data. Different weights were assigned for each attribute based on its influence on data value. Each attribute was quantized to an index based on proposed algorithms. The data value models for chronic diseases and other diseases were distinguished given the different sensitivity of data timeliness. A simulation system using blockchain and federated learning techniques was constructed to verify the data pricing model in the scenario of clinical research.
A comprehensive clinical data pricing model is proposed and the simulation of three research centers with 50 million real clinical data entries was conducted to verify its effectiveness. It demonstrates that the proposed model can compute medical data value quantitatively.
Quantitative evaluation of the value of medical data for multicenter clinical research based on the proposed data pricing model works well in simulation. This model will be improved by real-world applications in the near future.
多中心临床研究面临诸多挑战，包括如何定量评估每个研究中心的数据贡献。然而，很少有数据定价模型能满足该场景的要求。因此，需要一种合适的机制来衡量临床研究数据的价值。
收集并分析了大量文档，包括国家卫生健康委员会的罕见病清单、电子病历（EMR）系统的数据结构、浙江省卫生健康委员会的诊断相关分组（DRG）规定以及浙江省临床服务价格清单。邀请了9位来自医院和企业的资深专家作为顾问，他们的专业领域涵盖临床研究、数据治理和卫生经济学。经过头脑风暴和专家评估，确定了7个数据属性作为影响医疗数据价值的主要因素。根据每个属性对数据价值的影响为其赋予不同权重。基于所提出的算法，将每个属性量化为一个指标。考虑到数据时效性的不同敏感性，区分了慢性病和其他疾病的数据价值模型。构建了一个使用区块链和联邦学习技术的模拟系统，以在临床研究场景中验证数据定价模型。
提出了一个全面的临床数据定价模型，并对三个拥有5000万条真实临床数据条目的研究中心进行了模拟，以验证其有效性。结果表明，所提出的模型能够定量计算医疗数据价值。
基于所提出的数据定价模型对多中心临床研究医疗数据价值进行定量评估在模拟中效果良好。该模型将在不久的将来通过实际应用得到改进。
