The world today is in an era of evidence-based medicine based on massive real-world data. In 2022, Chen Saijuan, a member of the National Committee of the Chinese People's Political Consultative Conference (CPPCC), suggested at the two sessions that priority be given to focusing on diseases that seriously affect the health of the population, establish a national database platform for major disease specialties, develop standards for speciality data sets; improve the quality of major disease speciality data with the joint participation of multidisciplinary personnel; explore mechanisms for sharing major disease speciality data and improve relevant policy support.

The standardized dataset to improve prostate cancer research

Recently, under the organization of the Chinese Society of Clinical Oncology Prostate Cancer Expert Committee (CSCO-PC), the Prostate Cancer Standard Data Set (2022 Edition), edited by Prof. Dingwei Ye, reviewed by academician Xu Zhang, and co-authored by the Department of Urology of the Cancer Hospital of Fudan University, CSCO-PC, and the Medical Data Department of DHC, was officially published. The dataset aggregates the collective wisdom of prostate cancer experts from the Chinese Society of Clinical Oncology, prostate cancer medical experts from many well-known hospitals, and clinical data experts from DHC. The research will vigorously promote the formation of treatment norms for prostate cancer in China, allowing researchers to better conduct real-world research with the support of a massive standardized dataset, and advancing clinical and scientific investigation to be more refined and in-depth.

Prostate cancer is a common malignant tumor among middle-aged and elderly male patients. With the deepening of population aging and changes in dietary combination and lifestyle habits, the incidence of prostate cancer is increasing annually as it becomes one of the major malignant tumors endangering the health of middle-aged and elderly men in China.

Also, as incidence rates increase, the volume of prostate cancer medical data is growing exponentially. Information systems from different hospitals and vendors have significant differences in data structure and standards, which affect the full interaction, integration, sharing, and application of data.

Therefore, for the disease characteristics of different specialties, it is especially important to establish standardized and unified standard basic data sets and standard core data sets to break the data barriers. It is favorable to form long-term, continuous, dynamic, multi-source and large-scale data accumulation of special diseases and enhance the transformation of rich clinical case resources into valuable medical research resources.

Data Value Released Uniform Data Standard Promotes Formation of Uniform Diagnostic and Treatment Standards

The China Prostate Cancer Standard Data Set (2022 Edition) refers to the Chinese Society of Clinical Oncology (CSCO) Prostate Cancer Treatment Guidelines 2021 Edition, NCCN Clinical Practice Guidelines: Prostate Cancer (2021.V2), and EAU Prostate Cancer Guidelines (2021). It also establishes a unified and standardized data meta-standard in the field of real-world prostate cancer research based on the health information industry standards of the People's Republic of China, such as the Health Information Data Metadata Catalogue, the Health Information Data Meta-value Domain Codes and the Basic Data Set for Electronic Medical Records, as well as the Chinese Population-based Tumor Registry Data Set Standards (TCHIA18-2021) and the International Classification of Diseases ICD10/ICD9 and other domestic and international information standards. The standardized data element standard was established, incorporating 12 data modules and 461 data elements, including general information, diagnosis, examination, treatment, evaluation, and medical costs. The core purpose is to guide the construction of a national prostate cancer-specific data platform at all levels, to support the unification of treatment standards with data unification, and to enable patients across the country to enjoy homogeneous medical services in close proximity to each other.

As the treatment of prostate cancer enters the era of precision therapy, a growing number of real-world research projects will be conducted in the future, which will need to be supported by specialized big data. The release of the Prostate Cancer Standard Dataset (2022 Edition) will certainly have an essential impact on the management and application of medical big data in the field of prostate cancer.

DHC is prepared to cooperate with experts and users from all walks of life to form more standards for major disease specific data sets that affect the health of all people, and to explore mechanisms for sharing major disease specific data, making data, a new type of production factor, burst forth with great social and economic value.