In recent years, China has introduced a series of policies for drug innovation development and pharmaceutical management reforms. Notably, these policies include measures such as the verification of clinical trial data, generic drug consistency evaluation, and the market authorization holder system, all of which have significantly propelled the growth of the innovative pharmaceutical industry. According to statistics, in 2021, the number of registered clinical trials in China sur-passed 3000 for the first time, with a total of 3358 registrations, marking a remarkable growth rate of 29.1%.
1 However, despite this surge in clinical trial registrations, the development of innovative drug clinical trials in China lags behind other segments of the innovation chain, necessitating a deeper reform in the clinical trial domain to advance the design and implementation of the clinical research system. To fortify the pharmaceutical innovation ecosystem, accelerate the high-quality development of innovative drugs, and enhance China's international competitiveness in new drug research and development, it is imperative to address the critical issue of quality in drug clinical trials. The quality of clinical trials is paramount for ensuring the safety and rights of participants and obtaining reliable trial data.
2 Strengthening the application of quality management in the field of new drug development, establishing and maintaining a comprehensive and standardized clinical trial quality assessment system, and minimizing or avoiding risks in the clinical trial process are ongoing challenges for researchers. Recognizing the potential risks in clinical trials, regulatory authorities both domes-tically and internationally have introduced regulations on risk control. Western countries, such as the United States and Europe, took early steps in risk management, with both the FDA
3 and EMA
4 issuing guidelines in 2013 advising sponsors to focus on critical data and processes, employing a risk-based approach to monitor clinical trial quality. Since 2008, as innovative drug research and development have rapidly pro-gressed in China, regulatory authorities have actively explored risk management systems and models tailored to the Chinese context. The official implementation of the “Good Clinical Practice for Drug Clinical Trials” (GCP) on July 1, 2020,
5 introduced the concept of risk-based quality management. Despite the existence of relevant regulations, stakeholders in clinical trials have not fully integrated risk management into quality management. Consequently, optimizing the utilization of limited management resources to maximize clinical trial quality remains a significant challenges for medical institutions and research enterprises engaged in clinical trials in China.
6 (see Fig. 4)
Clinical trials involve multiple stakeholders, including sponsors, researchers, and clinical trial institutions, spanning various stages such as trial design, project initiation, drug and prescription management, financial oversight, biosample management, ethical review oversight, record keeping of raw data and case report forms, as well as the management of adverse events and serious adverse events.
7,8 Risks in clinical trials are diverse and pervasive, encompassing a wide range of categories. To ensure risk mitigation, it is essential to identify, assess, develop response measures, and monitor the implementation of risk management at each stage.
9 In this context, a comprehensive approach involves delving into data that may contribute to quality issues, dissecting key risk factors throughout the entire process of quality management, and developing tools for assessing clinical trial quality and risk. Combining this with AI technology allows for automatic extraction and identification of data and fields, recognition of predetermined risks, risk value assessment, and grade evaluation. This approach shifts the focus of clinical trial quality supervision upstream, preventing systematic and trend-related issues. Subsequently, embedding a comprehensive risk assessment tool into CTMS enhances and optimizes CTMS project management functions. Furthermore, the development of an integrated intelligent management model, utilizing AI algorithms for CTMS-HIS-EDC integration, breaks down information barriers. This integration facilitates the seamless exchange of clinical trial management data and subject diagnosis and treatment data. Establishing an informatics-based quality control management system for the entire clinical trial process achieves a closed-loop management of clinical trials, contributing to the high-quality development of new drug research and development in China.
In the current highly competitive global biopharmaceutical market, the need to assess the progress of research centers more efficiently using high-quality control methods and implement targeted monitoring has become an urgent requirement in the field of clinical investigation. Against the backdrop of the COVID-19 pandemic, the U. S. FDA released guidelines on conducting clinical trials of medical products during the pandemic, introducing the concept of remote monitoring for the first time. Concurrently, the U. S.-based Florence remote monitoring solution has been deployed in 25 countries, benefiting over 800 sponsors with over 10 million instances of remote monitoring practices. Over the past two years, China has successively introduced multiple regulations encouraging medical institutions and technology enterprises to develop and apply remote digital technologies in the conduct of clinical trials. The National Medical Products Administration, in its announcement titled “Guiding Principles for the Management of Drug Clinical Trials During the COVID-19 Pandemic (Trial)" (No. 13, 2020), highlighted the potential of combining centralized and remote monitoring using digital technologies in drug clinical trials during the pandemic, stating that “with the gradual maturity of remote monitoring and data management systems in electronic clinical trial systems, a combination of centralized and remote digital technologies can be employed to conduct drug clinical trials.”
10 Therefore, the imperative of utilizing digital means for remote monitoring is evident. By leveraging technologies such as big data and natural language processing, the development of applications for remote monitoring can revolutionize communication methods for sponsors, reducing the need for frequent visits to hospitals. Simultaneously, this approach alleviates the workload of researchers, enabling data to be collected more efficiently, ultimately enhancing collaborative efficiency and the quality of work.
11The recruitment of subjects for drug clinical trials is often a limiting factor in determining whether the trial can proceed as scheduled. Between 85% and 95% of trial delays are attributed to the inability to recruit eligible subjects according to plan, particularly in areas such as oncology, cardiovascular diseases, and infectious diseases.
12 With the advancement of precision medicine, patient recruitment criteria have become increasingly complex, encompassing not only common factors such as age, laboratory results, and diagnosis but also variables such as treatment regimens, efficacy, treatment intervals, genetic factors, and surgical history.
13 Traditional methods of reviewing medical records and searching for subjects within individual systems like HIS or LIS are highly inefficient and struggle to accurately pinpoint eligible subjects, potentially missing the window for them to participate in clinical trials. By employing big data and AI technologies to deeply analyze data, it is possible to identify patients who likely meet the inclusion criteria for clinical trials. This information can be automatically forwarded to project researchers for confirmation. This approach not only significantly improves the accuracy of patient identification, preventing subjects from missing the opportunity to participate in clinical trials, but also enhances the overall quality and efficiency of the clinical trial process. Moreover, it helps prevent the occurrence of professional subjects or instances of subjects participating in multiple trials within a short period, ensuring the authenticity and reliability of clinical trial data and safeguarding the safety and rights of the participants.
14Currently, both domestic and international software companies have successively introduced intelligent management systems for clinical trials, and there are also management systems developed independently by clinical research institutions. These systems may focus on specific stages of management or provide intelligent management for the entire process.
11,15 In our institution, during the implementation of the national Twelfth Five-Year Major Project “Constructing a Standardized International Drug Clinical Trial Research and Evaluation Technology Platform (Digestive System Diseases),” we initially conceived a CTMS.
16 After years of practical operation and improvement, our independently developed CTMS system has significantly enhanced functionality and operational practicability, covering project initiation, ethical review, contract review, project management, quality management, drug management, fund management, document management, CRC management, and human genetic management information. The CTMS system is integrated with the HIS to manage subject medication and standardize the writing of clinical trial prescriptions. This system has greatly improved the efficiency of the entire clinical trial process, increased researcher enthusiasm, and ensured the smooth progress of various aspects of clinical trial work. Our institution's independently developed CTMS system has not only obtained multiple software copyrights and patent certificates
17–20 but is also operational in 13 hospitals within the province. However, the challenge we face is how to leverage technologies such as big data and natural language processing, among others, to further enhance the CTMS system. The goal is to construct an integrated intelligent management and data platform for clinical trials—linking CTMS, HIS, and EDC —strengthening process supervision throughout the entire clinical trial, and reducing risks associated with clinical trials.
This project will be based on our institution's independently developed and maturely operational “CTMS”. By combining medical big data with AI digital technology, we aim to develop a digital intelligent platform for clinical trials and promote its application: (1) Intelligent Quality Control Module: For various types of clinical trials, we will collect and organize process data throughout the entire trial process. An intelligent quality control information module will be developed to monitor and control clinical trial risks. (2) Integration of CTMS, HIS, and EDC: We will enhance and optimize the functionalities of CTMS, HIS, and EDC. Breaking down information barriers, we will establish interconnectivity between clinical trial management data and subject diagnosis and treatment data. By embedding the intelligent quality control information module, we will develop an integrated intelligent management system based on artificial intelligence algorithms—CTMS-HIS-EDC. This system aims to achieve the goals outlined in the guidelines, including the development of a comprehensive CTMS, establishment of a fully informatics-driven management system for clinical trial initiation, drugs, prescriptions, and funding, and the creation of an independent clinical trial database and integrated intelligent system. (3)Quality Management System: Starting with a problem-oriented quality management system, we will develop a subject recruitment and screening system, as well as a remote monitoring subsystem. These components will strengthen the role of digital intelligent models in subject recruitment and remote monitoring. (4) Validation and Application Promotion: The clinical trial digital intelligent platform system will undergo standardized internal and external validation processes. Once validated, the system will be promoted for widespread application. In summary, this project aims to construct a clinical trial acceleration platform using AI and big data technologies. It will provide intelligent applications for subject recruitment, remote monitoring, and risk assessment for clinical trial institutions, researchers, and CRA. The ultimate goal is to enhance the overall quality of clinical trials. This platform will serve pharmaceutical companies and clinical trial institutions globally, attracting high-quality projects, and improving China's technological innovation capabilities and international competitiveness in drug development.
1 This section details the collection and organization of comprehensive process data across diverse clinical trials. Intelligent quality control information modules are subsequently developed to monitor and manage associated clinical trial risks.
Clinical trial processes are inherently intricate, characterized by their complexity, extended durations, and stringent data quality requirements. The escalating number of clinical trial projects exacerbates these complexities, introducing substantial risks amidst evolving regulatory and operational landscapes. To promptly identify and control these risks, this initiative aligns with the data verification points outlined by the NMPA, the requirements stipulated by the ICH-GCP, and insights garnered from the examination of quality issues uncovered in prior drug registration checks. Drawing upon a synthesis of literature reviews and a decade's worth of issues detected in clinical trial quality management inspections conducted by hospitals, the project comprehensively gathers, organizes, and analyzes data information related to trial protocol design, project initiation review, ethical review, contract review, compliance review of human genetic resources, investigational drug management, biological sample management, subject management, concomitant medication, adverse events, data collection, monitoring and inspection management, personnel management, document management, budget warnings, and safety events throughout the entire clinical trial process. Focusing on critical junctures and potential risk events associated with key data points in the clinical trial lifecycle, the project identifies indicators for monitoring the risks of regulatory drug clinical trials. Following the guidelines of the National Standardization Management Committee and the General Administration of Quality Supervision, Inspection, and Quarantine, as outlined in GB/T 27,921-2011 on risk management risk assessment technology, expert consultation forms are compiled based on the content of risk indicators. These forms are subject to extensive research and consultation with clinical trial regulatory authorities, industry experts, and practitioners in clinical trials from both within and outside the province. The initiative aims to clarify the comprehensive set of risk indicators throughout the entire clinical trial process, analyze and categorize them, and formulate a collection of key indicators for risk assessment. Employing both quantitative and qualitative analysis methods, each indicator is assessed based on criteria such as importance, sensitivity, and operability. Three risk levels—high, medium, and low—are assigned to the indicators. A consultation form is compiled and industry experts are consulted again to refine and optimize the risk assessment indicator levels and the framework of the system. Different hierarchical levels, risk values, and weight coefficients for risk indicators are preliminarily determined. This forms the basis for constructing a risk indicator evaluation system, creating a risk assessment scale, and developing a quality control information module using information technology and artificial intelligence. The risk assessment scale is developed by utilizing a combination of computer-based automatic risk identification, classification, and alerting to handle risks appropriately. This approach ensures precise control over the quality risks throughout the entire clinical trial process, thereby enhancing the implementation quality and management efficiency of clinical trial projects. This research section addresses two key objectives: first, analyzing and organizing potential risk events and risk indicators throughout the entire clinical trial process to form a risk assessment indicator set, and second, calculating the scores and levels of risk indicators based on their different classifications and weights. This involves determining a risk assessment scale and warning model, along with the development of an intelligent quality control information module. This project section lays the foundation for developing a comprehensive CTMS.
2. Enhance and optimize the functionalities of CTMS, HIS, and EDC. Overcome information barriers by establishing seamless connectivity, enabling the intercommunication of clinical trial management data and subject healthcare data. Embed intelligent quality control information modules and develop an integrated intelligent management system based on artificial intelligence algorithms for CTMS-HIS-EDC (see Fig. 1).
The majority of CTMS available on the market are relatively isolated office systems, unable to seamlessly integrate throughout the entire clinical trial process. Similarly, many domestic hospital Health Information Systems (HIS) are closed systems that lack interoperability with external systems and data. This results in the manual, time-consuming, and error-prone entry of clinical trial data into Electronic Data Capture Systems (EDC). The existence of information silos poses significant challenges to conducting clinical trials in the current landscape. This project aims to develop an integrated intelligent management system, CTMS-HIS-EDC, that spans the entire clinical trial process. According to the plan, the visit process, visit content, and key milestones will be pre-set in CTMS and seamlessly connected with HIS. Additionally, EDC will be integrated with HIS and CTMS to achieve automatic and intelligent data entry for clinical trial data. This integrated system will also ensure the separation of clinical trial expenses and medical insurance expenses, as illustrated in Fig. 2. Firstly, within the CTMS, enhancements and optimizations will be made to functions related to initiation review, ethical review, contract review, subject management, investigational drug management, budget management, personnel document management, project management, safety event reporting (AE/SAE/SUSAR), and quality management. Simultaneously, an intelligent quality control information module will be embedded to achieve intelligent online operation of clinical trials, intelligent quality control of clinical trial data, and automated data collection. Secondly, within the HIS, electronic medical data and paper data of trial subjects will be collected to establish a clinical trial database. This database will be interconnected with CTMS and EDC. CTMS will provide HIS with data related to the execution of clinical trial protocols, project operation, and management, while HIS will provide CTMS with medical data such as subject laboratory tests and medical records. The intelligent quality control information module will automatically compare and identify data from both systems using risk assessment scales and warning models. This automated process will help detect risks, such as missed subject laboratory tests, errors in AE records, omissions in concomitant medication, and multiple or missed doses of investigational drugs, thereby enhancing the quality of the trial. EDC systems, through interfaces and pre-configured collection rules, will automatically collect subject data from both CTMS and HIS, conducting intelligent comparisons and analyses to improve data entry accuracy. Finally, in accordance with the “Guidelines for Quality Management of Drug Clinical Trials” and ICH-GCP requirements, medical expenses related to trial subjects and clinical trials should be borne by the clinical trial project. However, due to the dual identity of trial subjects as both subjects and patients, and the fact that some subjects may have multiple diseases requiring treatment, the clinical trial medical expenses and medical insurance expenses for inpatient subjects are often intertwined. Current medical and insurance settlement systems cannot distinguish between these two types of expenses. As a result, patients often have to be admitted as self-pay when participating in clinical trials to avoid clinical trial expenses occupying medical insurance resources. This significantly impacts the right of trial subjects to enjoy normal medical and insurance reimbursement. Therefore, this project will leverage existing hospital medical business processes, using clinical trial research methods and information technology to establish clinical trial medical pathways within HIS. This will achieve the separation and independent settlement of regular expenses and clinical trial expenses. This approach is crucial for improving subject compliance, enhancing doctor–patient relationships, and alleviating the economic burden on both subjects and sponsors (see Fig. 3).
The primary technical challenges addressed in this study include: (1)Optimization and Enhancement of CTMS, HIS, and EDC Functions: The study aims to refine and optimize the functionalities of CTMS, HIS, and EDC systems. It seeks to address the issue of data heterogeneity from various sources by implementing standardized processing. The objective is to establish an independent comprehensive clinical trial database, breaking through information barriers and enabling seamless data interchange and automated collection. Integration of Clinical Trial Risk Management Tools and Intelligent Quality Control: The study incorporates established clinical trial risk management scales and risk warning models (via an intelligent quality control information module)alongside extensive data learning. This integration facilitates intelligent quality control over standardized datasets throughout a patient's entire lifecycle, enhancing overall data quality. Implementation of GCP Expense Isolation in HIS: Within the HIS, the study proposes the addition of a GCP labeling function to segregate GCP expenses from medical insurance expenses. This aims to ensure the separation of expenses related to GCP-compliant clinical trials from those covered by medical insurance. This project aligns with the overarching goals outlined in the guidelines, aiming to develop a comprehensive CTMS, establish an end-to-end information management system covering clinical trial initiation, drug management, prescription management, funding, adverse reactions, and quality management. The study seeks to overcome information barriers by establishing seamless connectivity between clinical trial management data and patient diagnostic and treatment data. It envisions the creation of an independent, comprehensive clinical trial database and an integrated intelligent system. Additionally, the study addresses the segregation of medical insurance expenses and clinical trial expenses for inpatient subjects, proposing methods and technologies for achieving this goal.
3. Taking a problem-oriented approach to quality management systems, we aim to develop a subject recruitment and screening system as well as a remote monitoring subsystem. Emphasizing a digitalized intelligent model, we seek to strengthen its role in subject recruitment and remote monitoring within the framework of a quality management system.
Regular on-site visits are the primary method of monitoring, typically conducted before the trial initiation, during its conduct, and after its completion, with on-site visits occurring approximately every 4–8 weeks. The scrutiny of source data is a crucial aspect of monitoring, where clinical monitors can only verify original data by physically visiting the site or by accessing authorized or temporary accounts. However, this approach suffers from inefficiencies, compliance issues in data utilization, and limitations imposed by temporal and spatial constraints such as the ongoing pandemic. These challenges may pose risks to the quality of clinical trial data. In the competitive landscape of innovative drug development in China, the speed of subject enrollment is a pivotal consideration for sponsors. Subject recruitment and enrollment rates are critical factors influencing the success or failure of a project. With the advancement of precision medicine, patient recruitment criteria have become increasingly complex, encompassing demographic information, diagnoses, past treatment regimens, surgeries, and other stringent screening conditions. The traditional methods of reviewing medical records and searching for subjects within individual systems like HIS and LIS are highly inefficient and struggle to precisely locate eligible subjects. This inefficiency poses a challenge in accurately identifying subjects who could participate in clinical trials and increases the likelihood of missing the optimal enrollment window.
Addressing the challenges posed by difficult subject recruitment, low enrollment efficiency, high sponsor monitoring costs, non-compliance in data utilization, and the inability to conduct on-site monitoring due to factors such as the pandemic and spatial constraints, this research segment proposes a comprehensive solution. This is achieved through the development of a CTMS-HIS-EDC integrated intelligent management and data platform. This study aims to leverage AI technologies such as big data and natural language processing to integrate, standardize, and structurally manage both existing and incremental electronic medical record (EMR) data within medical institutions. Through techniques like data anonymization, permission controls, and traceable operations, the research ensures data security and auditability, facilitating remote monitoring by clinical monitors. Simultaneously, utilizing AI-based big data mining techniques for intelligent patient screening, the study will identify potential subjects matching criteria, automatically pushing notifications to project researchers for confirmation. This approach significantly improves the accuracy of patient identification, preventing subjects from missing the opportunity to participate in clinical trials and thereby enhancing the quality and efficiency of trial enrollment. The key technical challenges addressed in this research include: (1) Establishment of Clinical Trial Data Platform with Data Anonymization: Implementing data anonymization techniques to establish a secure clinical trial data platform and develop the necessary security technologies for remote monitoring systems, ensuring both subject privacy protection and data security. (2) Utilization of AI for Protocol Parsing and Efficient Subject Identification: Leveraging AI technologies for the parsing and retrieval of protocol inclusion and exclusion criteria, enabling the efficient and accurate identification and notification of potential subjects, thereby expediting the conduct of clinical trials. This research segment aligns with the overall goal outlined in the guidelines to “establish an intelligent system integrating clinical trial management and research, an intelligent subject screening system, and a remote monitoring system for clinical monitors.”
4. Standardized validation and application promotion of the digital intelligent platform system for clinical trials
This section outlines the functional features of a clinical trial digital intelligent platform established based on medical big data and artificial intelligence technology. Internal and external validation of various system functions on the platform is conducted to ensure smooth processes, data security, and reliability, thus meeting the operational and regulatory needs of clinical trials. The Intelligent Subject Recruitment System and Remote Monitoring Subsystem, involving subject information security and privacy protection, are accessed by researchers and sponsor personnel through both internal and external networks to verify the reliability of permission control and data de-identification technology. Additionally, adhering to relevant industry validation standards, such as the China National Accreditation Service for Conformity Assessment (CNAS) or National Metrology Accreditation (CMA), external validation is carried out in terms of system security, including certification testing, permission management testing, file upload/download testing, and information leakage testing, to ensure the security and reliability of data. Simultaneously, through application layer development and leveraging AI technologies like big data and natural language processing, the clinical trial data management intelligent platform is extended. This involves standardizing and normalizing the data related to clinical trials from various brands of HIS, LIS, RIS, EMR systems, and other subsidiary systems in medical institutions within and outside the province. The data undergoes cleansing and processing, and through machine learning and deep mining, a versatile, accurate, highly intelligent, and widely applicable new clinical trial digital intelligent platform is developed. The platform will be deployed and promoted in clinical trial institutions within the province that have CTMS platforms and some clinical trial institutions outside the province. Through ongoing optimization and improvement of system functionality, the ultimate goal is to generate research results, consensus, and examples for global dissemination. This project segment aims to achieve the goal outlined in the guideline: “Implementing the application and technological promotion of an integrated, multifunctional clinical trial digital intelligent platform.”
This project is based on the independently developed and operationally mature CTMS within our institution. It aims to leverage the combination of medical big data and AI digital technology to develop and promote a clinical trial digital intelligent platform with the following key objectives:①To collect and organize comprehensive procedural data throughout the entire clinical trial process. To develop an intelligent quality control information module to monitor and mitigate clinical trial risks.②To enhance and optimize CTMS, HIS, and EDC functionality. To break down information barriers, and to enable interconnection between clinical trial management data and subject diagnostic and treatment data. To develop an integrated intelligent management system based on AI algorithms, embedding the intelligent quality control information module. To realize the goals outlined in guidelines, including developing a comprehensive CTMS, establishing an information management system for the entire process of clinical trials, breaking down information barriers, interconnecting clinical trial management data and subject diagnostic and treatment data, creating an independent comprehensive database and integrated intelligent system for clinical trials, and conducting research on methods and technologies for segregating inpatient subject medical insurance expenses from clinical trial expenses.③To develop subject recruitment and screening systems, as well as a remote monitoring subsystem, using a problem-oriented quality management system. To strengthen the role of digital intelligent models in subject recruitment and remote monitoring.④To conduct standardized internal and external validation of the clinical trial digital intelligent platform. To promote the application of the platform, creating a clinical trial acceleration platform using AI and big data technologies. The ultimate goal is to provide intelligent applications such as subject screening, remote monitoring, and risk assessment for clinical trial institutions, researchers, and CRA, with the aim of improving the overall quality of clinical trials. The platform will serve both domestic and international pharmaceutical companies and clinical trial institutions, attracting excellent projects to enhance China's pharmaceutical research and development innovation capabilities and international competitiveness.
This study features the following characteristics and innovations:
1. Establishment of a risk assessment scale and early warning model, and the development of an intelligent quality control information module for clinical trials. This addresses the challenges of inadequate risk identification capabilities and inconsistent risk assessment standards within clinical trial institutions.
We analyzed and organized potential risk events and risk indicators throughout the entire process of clinical trials. We conducted an in-depth analysis and classification of risk indicators, resulting in the formulation of a set of risk assessment indicators. We constructed a framework for the quality risk indicator system throughout the entire process of clinical trials. Based on the different levels and weights of risk indicators, we calculated the scores of risk indicators, determined the risk assessment scale, and developed a model for determining risk values. This enables the management of key processes and data in clinical trials at high, medium, and low-risk levels. We established corresponding risk management goals and developed an intelligent quality management module for risk warning.
2. Overcoming the information barriers between CTMS-HIS-EDC, we built a comprehensive clinical trial database to achieve automatic identification of clinical trial risks, intelligent quality control, automatic collection of EDC data, and isolation of medical insurance expenses. This promotes the improvement and efficiency of clinical trials.
The current limitations in clinical trial execution, such as information silos, complex processes, vast amounts of heterogeneous data, quality risks, and manual data entry, pose significant challenges to the evolving landscape of clinical trials and the internationalization of new drugs. Additionally, strict supervision of clinical trial expenses by health insurance agencies, coupled with the absence of clinical trial business processes in HIS, severely impacts subject enrollment efficiency and compliance. This project utilizes medical big data, information technology, and artificial intelligence to optimize and interconnect CTMS, HIS, and EDC. By embedding an intelligent quality control information module, we establish a high-quality, standardized, and comprehensive clinical trial data platform, overcoming information barriers and streamlining the conduct of clinical trials.
3. Establishment of an intelligent subject screening and remote monitoring system to address slow subject enrollment and temporal–spatial restrictions on on-site monitoring.
Slow subject enrollment is a critical bottleneck in the registration and marketing of trial products. Leveraging medical big data and natural language processing technology, this project integrates, standardizes, and structurally governs scattered electronic medical record data from healthcare institutions to enhance data quality. Using big data mining technology, we intelligently screen subjects, combining medical knowledge graphs and statistical correlation techniques to improve the efficiency of subject enrichment and enhance the accuracy of patient recruitment. Through the integration of big data, paper medical record scanning, secure anonymization technology, and trajectory audit technology, we establish a comprehensive clinical trial database, providing remote monitoring to project collaborators and other sponsors, thereby further improving project quality.
4. The platform will serve domestic and international pharmaceutical companies and clinical trial institutions, attracting high-quality clinical trial projects, and enhancing China's technological innovation and international competitiveness in drug development.
The construction of this platform will further enhance the capabilities and levels of national drug clinical trial institutions in serving research and development enterprises, significantly improving the quality and efficiency of drug clinical trial phases. This is conducive to promoting collaboration between domestic healthcare institutions and globally renowned research and development enterprises, attracting more international multicenter clinical trial projects to be conducted in China, thereby driving innovation in Chinese drug development technology and enhancing the competitiveness of domestic pharmaceutical companies.
2026 Publishing services by Elsevier B.V. on behalf of Higher Education Press and KeAi Communications Co. Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).