Bridging the Past and Future of Clinical Data Management: The Transformative Impact of Artificial Intelligence

최근 국내 임상시험의 양적 증가와 더불어, 임상시험 자료를 효율적으로 관리할 수 있는 Electronic Data Capture(EDC) 시스템의 도입 요구가 증가하고 있다. 이에 따라 식품의약품안전청에서는 '임상시험 전자 자료 처리 및 관리를 위한 가이드라인'을 발표하였다. 이는 향후 국내 임상시험 전자 자료 관리에 관한 법률 제정을 위한 기초가 될 것으로 기대한다. 이 연구에서는 국내 임상시험 관련 기관인 병원과 임상시험 수탁기관(CRO), 그리고 제약회사에서의 EDC 시스템 이용 현황과 관계자들이 인식하는 가이드라인 및 전자 자료 표준의 중요성 및 적용 용이성과 이해도를 조사하였다. 국내 임상시험 관련 기관에서의 EDC 시스템 이용률은 77.6% 이었지만 EDC 시스템을 이용한 임상시험 건수는 5건 미만이 가장 많았다. EDC 시스템은 주로 약물동력학 시험을 하는 phase I과 임상효과와 안전성을 평가하는 phase II 임상시험에서 주로 이용되었고, 기관별로는 CRO의 이용률이 가장 높았다. 모든 집단에서 가이드라인의 중요성은 높게 인식하였으나, 적용 용이성 측면에서는 CRO에서 가장 높았다. 또한, 임상시험 전자 자료 표준의 중요성을 높게 인식하였고, 전자 자료 수집에 있어 표준의 필요성을 높게 인식하였다. 그러나 임상시험 전자 자료 국제표준인 Clinical Data Interchange Standard Consortium(CDISC)에 대한 이해도는 아직 낮은 수준이었다. 이 연구 결과는 국내 임상시험 전자화를 위한 기초자료로 활용될 수 있으며 임상시험 자료 표준에 관한 정책수립에도 활용될 수 있을 것이다. As the number of clinical trials conducted in Korea increases, the need of the Electronic Data Capture (EDC) system for effective clinical data management is also increased. Recently, the Korea Food and Drug Association published 'Guideline for the Electronic Clinical Trial Data Management and Processing' and it would be the foundation for establishing regulation of electronic clinical data management. In this research, we conducted the survey regarding adoption rate of EDC system in clinical trials in hospitals, Contract Research Organizations (CRO), and pharmaceutical companies. And the perceived importance and the ease of application for the Guideline were investigated. The adoption rates of EDC system was 77.6% but it mostly applied to less than five trials. Also EDC system was mostly used in phase I and phase II trials and the utilization rate of CRO was the highest. The perceived importance for the Guideline was high among all three organizations but, in case of the perceived ease of its application, CRO was the highest. Also, the perceived importance of the clinical data standard was high and the standard for data collection was mostly required. However, the comprehension for the global standard of the electronic data was relatively low, so that education is required. This result would be the foundation to increase the electronic clinical trials and develop proper regulation and principles for clinical data standards in Korea.

The purpose of this study is to answer the FDA’s call to action for new research paradigms that rely on real-world data (RWD) to increase the efficiency of clinical trials and to conduct research using an approach that is less disruptive to the patient-provider clinical care setting. With the expansion of electronic health record (EHR) vendor structured data models, clinical study data can be directly captured using the patient’s EHR data as documented in the health care organization’s (HCOs) electronic medical record (EMR) system(s) and other electronic data sources (eSources). In partnership with HCOs, the Optum Digital Research Network is conducting a pilot to enable effective RWD extraction, normalization, and transcription from EMRs and other eSource to a read-only electronic data capture (EDC) system, effectively eliminating the need for duplicative data entry during the study. Optum is developing custom database queries to extract structured EMR data (including demographics, medications, labs, vitals, and encounters) from the respective domains of each EMR into a staging database. The raw data are then curated, normalized, and mapped into a common data model study database. In this case, the Observational Medical Outcomes Partnership (OMOP) data standard is employed as the clinical data management (CDM) model. The curated data are then mapped to Clinical Data Acquisition Standards Harmonization (CDASH) variables and transmitted to an EDC system using the EDC vendor’s application programming interface (API). The entire process is scheduled on a daily cadence (removing any duplicate data) to capture any updated visit information, medications, labs, or vitals. The EDC form fields are read-only. If there is a discrepancy or query, sites are notified requesting to confirm or correct their EHR data, which may result in an update to the respective read-only EDC form fields. Through this pilot project, Optum’s successful transfer of structured EMR data to a read-only EDC system has substantial implications for clinical research. Using data and technology, this methodology is projected to improve the efficiency (and lower costs) of clinical trials while minimizing the burden on HCOs. Citation Format: Brook Norris, Lauren Neighbors, Lucas Wale. Streamlining data management for clinical trials [abstract]. In: Proceedings of the AACR Special Conference on Advancing Precision Medicine Drug Development: Incorporation of Real-World Data and Other Novel Strategies; Jan 9-12, 2020; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(12_Suppl_1):Abstract nr 06.

An eSource generally includes the direct capture, collection, and storage of electronic data to simplify clinical research. It can improve data quality and patient safety and reduce clinical trial costs. There has been some eSource-related research progress in relatively large projects. However, most of these studies focused on technical explorations to improve interoperability among systems to reuse retrospective data for research. Few studies have explored source data collection and quality control during prospective data collection from a methodological perspective. This study aimed to design a clinical source data collection method that is suitable for real-world studies and meets the data quality standards for clinical research and to improve efficiency when writing electronic medical records (EMRs). On the basis of our group's previous research experience, TransCelerate BioPharm Inc eSource logical architecture, and relevant regulations and guidelines, we designed a source data collection method and invited relevant stakeholders to optimize it. On the basis of this method, we proposed the eSource record (ESR) system as a solution and invited experts with different roles in the contract research organization company to discuss and design a flowchart for data connection between the ESR and electronic data capture (EDC). The ESR method included 5 steps: research project preparation, initial survey collection, in-hospital medical record writing, out-of-hospital follow-up, and electronic case report form (eCRF) traceability. The data connection between the ESR and EDC covered the clinical research process from creating the eCRF to collecting data for the analysis. The intelligent data acquisition function of the ESR will automatically complete the empty eCRF to create an eCRF with values. When the clinical research associate and data manager conduct data verification, they can query the certified copy database through interface traceability and send data queries. The data queries are transmitted to the ESR through the EDC interface. The EDC and EMR systems interoperate through the ESR. The EMR and EDC systems transmit data to the ESR system through the data standards of the Health Level Seven Clinical Document Architecture and the Clinical Data Interchange Standards Consortium operational data model, respectively. When the implemented data standards for a given system are not consistent, the ESR will approach the problem by first automating mappings between standards and then handling extensions or corrections to a given data format through human evaluation. The source data collection method proposed in this study will help to realize eSource's new strategy. The ESR solution is standardized and sustainable. It aims to ensure that research data meet the attributable, legible, contemporaneous, original, accurate, complete, consistent, enduring, and available standards for clinical research data quality and to provide a new model for prospective data collection in real-world studies.

With a passion for data, SCDM continues its mission and steps forward to progress the evolution of our industry toward Clinical Data Science (CDS).To some, the concept of data may seem abstract, cold, and complex.For our industry, however, data is the lifeblood of everything we do in clinical development and could mean the difference between a patient having an answer or having no answers at all.As the 2024 Chair of the SCDM Board, my personal objective is to move from reflection to action, establishing a new norm for Clinical Data Management (CDM) and drug development in general. So first, let's explore SCDM's decisive 2024 actions:2024 is the year in which we harvest the investments of 2023 and help our CDM industry to evolve toward CDS, in a Data Centric and Patient Driven world.On January 25 th , SCDM hosted its traditional chair address webinar on the State of the CDM Industry.During this webinar, I announced a new SCDM branding which visibly anchors our vision "to lead the clinical data science industry for a healthier world."To be meaningful, rebranding needs to be accompanied with tangible actions.So, in the same webinar, Carole Schaffer, our Vice Chair of the Board and Chair of the Education Committee released our new industry competency framework and the upcoming release of a new CCDA Exam planned for later this year.This, and other initiatives in 2024, will help SCDM to deliver on its mission to "Prepare our industry and professionals for the evolution of the management of health data through education and certification programs."Our new industry competency framework combines our traditional CDM competencies (e.g., our CDM roots) with the additional competencies required for evolve towards CDS to meet the demand of drug development today and in the future.It is a living framework that serves as a reference for delivering all SCDM contents (including webinars, JSCDM articles, new Good Clinical Data Management Practice (GCDMP) chapters, conferences and much more).You can also use it to compare the competencies in your own organization against where our industry is heading!Our strong desire to partner with global regulators and law makers was demonstrated when Andrew Thomson from the European Medicines Agency and Andrzej

<p>ABSTRACT<br />Over the last few decades, most of the pharmaceutical companies and research sponsors are facing a lot of challenges in clinical research for their<br />new drug approval. The sponsor research needs a high-quality data report for getting new drug approval from Food and Drug Administration for their<br />medical products. Clinical trial data are important for the drug and medical device development processing pharmaceutical companies to examine<br />and evaluate the efficacy and safety of the new medical product in human volunteers. The results of the clinical trial studies generate the most<br />valuable data and in recent years; there has been massive development in the field of clinical trials. A good clinical data management system reduces<br />the duration of the study and cost of drug development. Further a well-designed case report form (CRF) assists data collection and make facilitates<br />data management and statistical analysis. Nowadays, the electronic data capture (EDC) is very beneficial in data collection. EDC helps to speed up the<br />clinical trial process and reduces the duration, errors and make the work easy in the data management system. This article highlights the importance<br />of data management processes involved in the clinical trial and provides an overview of the clinical trial data management tools. The study concluded<br />that data management tools play a key role in the clinical trial and well-designed CRFs reduces the errors and save the time of the clinical trials and<br />facilitates the drug discovery and development.<br />Keywords: Pharmaceutical, Clinical trial, Clinical data management, Data capture.</p>

Clinical data management: Current status, challenges, and future directions from industry perspectives Zhengwu Lu1, Jing Su21Smith Hanley Consulting, Houston, Texas; 2Department of Chemical Engineering, University of Massachusetts, Amherst, MA, USAAbstract: To maintain a competitive position, the biopharmaceutical industry has been facing the challenge of increasing productivity both internally and externally. As the product of the clinical development process, clinical data are recognized to be the key corporate asset and provide critical evidence of a medicine’s efficacy and safety and of its potential economic value to the market. It is also well recognized that using effective technology-enabled methods to manage clinical data can enhance the speed with which the drug is developed and commercialized, hence enhancing the competitive advantage. The effective use of data-capture tools may ensure that high-quality data are available for early review and rapid decision-making. A well-designed, protocol-driven, standardized, site workflow-oriented and documented database, populated via efficient data feed mechanisms, will ensure regulatory and commercial questions receive rapid responses. When information from a sponsor’s clinical database or data warehouse develops into corporate knowledge, the value of the medicine can be realized. Moreover, regulators, payer groups, patients, activist groups, patient advocacy groups, and employers are becoming more educated consumers of medicine, requiring monetary value and quality, and seeking out up-todate medical information supplied by biopharmaceutical companies. All these developments in the current biopharmaceutical arena demand that clinical data management (CDM) is at the forefront, leading change, influencing direction, and providing objective evidence. Sustaining an integrated database or data repository for initial product registration and subsequent postmarketing uses is a long-term process to maximize return on investment for organizations. CDM should be the owner of driving clinical data-cleaning process in consultation with other stakeholders, such as clinical operations, safety, quality assurance, and sites, and responsible for building a knowledge base to add potential value in assisting further study designs or clinical programs. CDM needs to draw on a broad range of skills such as technical, scientific, project management, information technology (IT), systems engineering, and interpersonal skills to tackle, drive, and provide valued service in managing data within the anticipated e-clinical age. Commitment to regulatory compliance is required in this regulated industry; however, a can-do attitude with strong willingness to change and to seek ways to improve CDM functions and processes proactively are essential to continued success and to ensure quality data-driven productivity.Keywords: clinical trials, data management, standard, efficacy, safety, clinical systems, clinical data, electronic data-capturing

BackgroundThe use of Clinical Data Management Systems (CDMS) has become essential in clinical trials to handle the increasing amount of data that must be collected and analyzed. With a CDMS trial data are captured at investigator sites with "electronic Case Report Forms". Although more and more of these electronic data management systems are used in academic research centres an overview of CDMS products and of available data management and quality management resources for academic clinical trials in Europe is missing.MethodsThe ECRIN (European Clinical Research Infrastructure Network) data management working group conducted a two-part standardized survey on data management, software tools, and quality management for clinical trials. The questionnaires were answered by nearly 80 centres/units (with an overall response rate of 47% and 43%) from 12 European countries and EORTC.ResultsOur survey shows that about 90% of centres have a CDMS in routine use. Of these CDMS nearly 50% are commercial systems; Open Source solutions don't play a major role. In general, solutions used for clinical data management are very heterogeneous: 20 different commercial CDMS products (7 Open Source solutions) in addition to 17/18 proprietary systems are in use. The most widely employed CDMS products are MACRO™ and Capture System™, followed by solutions that are used in at least 3 centres: eResearch Network™, CleanWeb™, GCP Base™ and SAS™. Although quality management systems for data management are in place in most centres/units, there exist some deficits in the area of system validation.ConclusionsBecause the considerable heterogeneity of data management software solutions may be a hindrance to cooperation based on trial data exchange, standards like CDISC (Clinical Data Interchange Standard Consortium) should be implemented more widely. In a heterogeneous environment the use of data standards can simplify data exchange, increase the quality of data and prepare centres for new developments (e.g. the use of EHR for clinical research). Because data management and the use of electronic data capture systems in clinical trials are characterized by the impact of regulations and guidelines, ethical concerns are discussed. In this context quality management becomes an important part of compliant data management. To address these issues ECRIN will establish certified data centres to support electronic data management and associated compliance needs of clinical trial centres in Europe.

Data management is an important, complex and multidimensional process in clinical trials. The execution of this process is very difficult and expensive without the use of information technology. A clinical data management system is software that is vastly used for managing the data generated in clinical trials. The objective of this study was to review the technical features of clinical trial data management systems. Related articles were identified by searching databases, such as Web of Science, Scopus, Science Direct, ProQuest, Ovid and PubMed. All of the research papers related to clinical data management systems which were published between 2007 and 2017 (n=19) were included in the study. Most of the clinical data management systems were web-based systems developed based on the needs of a specific clinical trial in the shortest possible time. The SQL Server and MySQL databases were used in the development of the systems. These systems did not fully support the process of clinical data management. In addition, most of the systems lacked flexibility and extensibility for system development. It seems that most of the systems used in the research centers were weak in terms of supporting the process of data management and managing clinical trial's workflow. Therefore, more attention should be paid to design a more complete, usable, and high quality data management system for clinical trials. More studies are suggested to identify the features of the successful systems used in clinical trials.

Discovering and developing new drugs/ medicines is very crucial for the pharmaceutical industry. The increasing number of drugs approved in recent years demonstrates the impact of modern drug discovery approaches, digital technologies, and automated drug development methodologies. Drug development is a systematic and methodological process of developing a new pharmaceutical drug once the process of Drug discovery has identified the prime pharmacological component. The structured sequence of steps followed for drug development aims to ensure the safety and efficacy of the drug being developed. It includes pre-clinical research on microorganisms and animals, preparation of detailed data with respect to pharmacology, pharmacokinetics and toxicology details, application and approval by regulatory authorities and conduction of clinical trials. The conduction of clinical trials is an expensive affair as it needs a collaborative effort by multiple stakeholders along with a high level of monitoring and regulation. The data generated during the lifecycle of clinical trials is very critical for pharmacological scientific publications, regulatory approval for the target drug and post-marketing surveillance that ultimately leads to the development of better decision support systems for drug development. Hence, the data integrity of such data is of prime importance. Several Clinical data management (CDM) systems have been developed to ensure seamless collection and management of clinical trial data. These CDM systems enable useful analysis and decisions supported by authentic data. However, such systems face several security challenges with respect to privacy, integrity and authenticity of the clinical data. Another major challenge in conducting the clinical trials is finding the appropriate willing candidate who is physically and clinically suitable for the study. In view of the above, it is highly desirable to have a technology component that can address the above-mentioned issues. In this chapter, the technologies like blockchain and cloud computing have been introduced to address the challenges posed by clinical trial data management. The paper also proposes a blockchain based secure clinical data management system. The proposed system intends to help the data security issues like data integrity, privacy, ease and quick access to immutable clinical trial data with thorough access control enabling greater transparency and accountability.

Field-based learning opportunities are considered to be an important and increasingly relevant part of professional learning in the biomedical sciences. The purpose of this study was to document internship opportunities in the combined fields of clinical data management and clinical data science among those attending the Society for Clinical Data Management 2022 annual conference. At the time of the survey there were 276 internship positions staffed across 47 organizations representing pharmaceutical, academic, clinical research, software development, and medical device companies, suggesting ample opportunities for those who wished to gain experience in such organizations. The greatest percentage of internships reported were in the United States, but with a wide range of opportunities worldwide.

This unique text and reference instills a fundamental understanding of how clinical data is gathered, used, and analyzed, and how to incorporate this data into a quality DNP project. The new third edition is updated to reflect changes in national health policy such as quality measurements, bundled payments for specialty care, and advances to the Affordable Care Act (<abbrev>ACA</abbrev>) and evolving programs through the Centers for Medicare & Medicaid Services (<abbrev>CMS</abbrev>). The third edition reflects the revision of 2021 <italic><abbrev>AACN</abbrev> Essentials</italic> and provides data sets and other examples in Excel and <abbrev>SPSS</abbrev> format, along with several new chapters. This resource takes the <abbrev>DNP</abbrev> student step-by-step through the complete process of data management, from planning through presentation, clinical applications of data management that are discipline-specific, and customization of statistical techniques to address clinical data management goals. Chapters include descriptions, resources, and exemplars that are helpful to both faculty and students. Topics spotlight requisite competencies for <abbrev>DNP</abbrev> clinicians and leaders such as phases of clinical data management, statistics and analytics, assessment of clinical and economic outcomes, value-based care, quality improvement, benchmarking, and data visualization. A progressive case study highlights multiple techniques and methods throughout the text.

Clinical Study Data Management Systems (CSDMSs) support the process of managing data gathered during clinical research. Clinical research involves much more than clinical data management – for example, research-grant tracking and reporting to the sponsor and to institutional review boards (IRBs, also called Human Investigations Committees) as well as financial management. I’ll focus on the data-capture, reporting and query aspects, as these are the components that benefit from metadata.

Integrating biomedical research and patient care is a challenging issue requiring interoperability solutions. During a clinical trial, clinical data are captured twice, first in the Electronic Health Record (EHR) and then in the Clinical trials Data Management System (CDMS). The aim of REUSE (Retrieving EHR Useful data for Secondary Exploitation) project is to provide a single source solution for electronic data capture to the investigators of a university hospitals involved in a multi-centric clinical trial. We first investigated the differences between the workflows of patient care and biomedical research to specify the use of EHR for clinical trials. Then we defined a semantic interoperability framework in order to enable the reuse of EHR clinical data and implemented a mediator that transforms CDISC Operational Data Model (ODM) XML into proprietary XML document templates of different EHR solutions and vice-versa. Implementing electronic data capture for biomedical research within EHR eliminates redundant data entry, thus improving data quality and processing speed. Moreover, unlike other initiatives such as IHE integration profile &amp;ldquo;Retrieve Form for Data Capture&amp;rdquo; (RFD), the REUSE approach ensures that all clinical data is kept in the EHR whatever the context of data capture is.

Best practices for multimodal clinical data management and integration: An atopic dermatitis research case

The management of clinical trial data is an essential component of medical research, where accuracy, security, and transparency directly impact the validity of outcomes. However, conventional methods often face challenges in maintaining data integrity and compliance with regulatory standards. The transformative role of Artificial Intelligence (AI) in enhancing these aspects by leveraging machine learning and analytics offers promising capabilities to improve data validation, detect inconsistencies, and secure sensitive information, thereby increasing credibility among researchers, participants, and regulators. The aim of this study is to explore the transformative potential of artificial intelligence in enhancing clinical trial data management. It specifically investigates whether AI can improve data integrity, transparency, and security, thus making the results credible to the researcher, participant, and regulatory bodies involved. The study employs machine learning algorithms and advanced analytics to investigate the role of AI in identifying data anomalies, verifying the accuracy of information, and validating data processes. Case studies and real-world applications are presented to highlight how AI enables real-time monitoring, reporting, and verification of regulatory compliance. It also analyzes encryption and access control systems powered by AI, ensuring that sensitive clinical trial data is protected against breaches and unlawful access. The findings demonstrate that AI significantly streamlines the management of clinical trial data through automated data validation processes, the detection of inconsistent data, and the capability for real-time data monitoring. AI encryptions and access control systems minimize data security risks to safeguard sensitive information. Case studies demonstrate that transparency, regulatory compliance, and stakeholder trust improve when AI is integrated into clinical trial processes. The study shows AI significantly enhances clinical trial data management through automated validation, real-time monitoring, and anomaly detection. Throughout the trial process, these capabilities reduce errors, ensure regulatory compliance, and improve transparency. Additionally, AI-driven encryption and access control systems offer robust protection against data breaches, reinforcing participant confidentiality and stakeholder trust. Case study analysis demonstrates that AI not only streamlines data workflows but also fosters greater confidence in trial outcomes, signaling a shift toward more efficient, secure, and credible AI-enabled clinical trials. The study highlights the potential of AI to revolutionize the management of clinical trial data with aspects such as data integrity, transparency, and security. The incorporation of AI ensures the credibility of trial outcomes among all stakeholders. This study advocates for a paradigm shift toward AI-enabled clinical trials, shedding light on the revolutionary approach it proposes for healthcare data management practices.