Case Studies of Effective & Efficient Monitoring of Data Quality using RBM
Chairperson: Shobhit Shrotriya
Risk-based monitoring (RBM) is now considered as a pro-active & adaptive approach that directs clinical trial monitoring focus and associated activities. RBM as an approach promises to improve clinical trial efficiency while ensuring data quality. As industry adoption of RBM increases manifolds, it is imperative to reflect on lessons learned to further refine the process as well as focus on leveraging RBM data for clinical operations. This conference offers case studies and practical solutions from across global biopharma and CROs on effectively implementing RBM as well as looking into the future of RBM.
Data Management in the world of Virtual Trials
Chairperson: Suraj Ravindran
Technology is emerging and evolving by the second. This is to re-assure that the human intelligence is by far racing towards the advancements in the clinical research techniques, strategies and of course basic practices to bridge the gap between patient & time taken to release the drugs required for patient care. In the event of narrowing the gap, companies, manufacturers and scientists are brainstorming in various ways to iron out the complexities that arise between patient and release of the patented product. The professionals invited to speak on this topic have multitudes of scenarios and world-wide practice examples that’ll open your mind to newer ideas, provide food for thought to either implement in your current processes or improvise on the current research practices that the world is following today. Be there to know more!
Descriptive, Predictive, Prescriptive Analytics & Visualizations for better decision making - Case Studies
Chairperson: Arghya Chattopadhya
The large volume of operational and scientific data collected from clinical trials and healthcare systems may contains hidden knowledge and insights that needs to be considered in decision making. However, the insights cannot just be gathered from the data itself, we need to curate, summarize and analyze the data in order to bring new insights. Visual analytics combines information visualization and data analysis to allow simultaneous exploration of human perceptual power and machines' processing power. In this session, we would discuss how we use the science and technology to ingest, curate and analyze and visualize the big volume of data to bring new insights that may help us making better decision.
CDISC Standards in the Age of Aritifical Intelligence & Machine Learning
Chairperson: Sarvesh Singh
We are in era of Industry 4.0 and its having an impact on all sectors including Pharmaceutical Clinical Research. CDISC standards which started in 1990’s have evolved a lot in past two decades and are going to evolve further in years to come with introduction of artificial intelligence and machine learning. Consumers and providers are more readily adopting technologies that leverage AI because they are becoming increasingly familiar with them in other parts of their lives. Just as any other standard and other industry, Clinical industry is also trying to take advantage of Artificial Intelligence and machine learning to identify hidden patterns in the data and identify novel solutions. In this session; you will get to know more about the evolution of CDISC standards until now, current status of CDISC standards and also to have a brief look at what’s in store for future. We will also cover the specific challenges with CDISC standards in terms of machine readability and on-going efforts towards optimizing machine learning of CDISC standards.
Leadership Forum (By Invitation Only)
Chair Person Name : Arshad Mohammed
Clinical Research has come a long way since using paper in the 1990s. Most studies have adopted electronic solutions with rapid improvements in connectivity and wide availability of clinical technology solutions. With the growth of the clinical research industry in established geographies and expansion of research in emerging countries, organizations have been using electronic data capture to improve accuracy and speeds of patient data collection methods, which has helped to increase compliance with regulations as well as reduce costs. With improving technology, mobile and handheld device proliferation, innovative study designs and evolving regulations including those for global data security and privacy, we are witnessing trends in clinical development that are looking to better utilize the latest technology and appropriate data collection devices. Clinical research is expanding use of automated and advanced approaches to day-to-day tasks, adoption of more sophisticated methods of mining study data and metadata, identifying and cleaning anomalous data, and working with a wider variety of data sources. In this special session, we will discuss such latest developments, benefits and challenges of such technological and process advances.
Data Science - Changing Healthcare Landscape
Chairperson: Prasida Dinesh
One of the major advances happening in digital space is how we can capture the data efficiently at source and analyze both structured and unstructured data to make meaningful inferences to the same. This stream of science is called data science which has been changing the way we live across all walks of life, lot of times even without us realizing this. Healthcare industry is no exception. All of us would have noticed disruptive changes in the last decade or two in our areas of work, making activities more predictable, efficient and ensuring the desired output. In this session, we would hear industry leaders enlightening us on how Data science is expected to drastically change healthcare industry – Be it in the areas of -Public health, Preventive medicine, Drug development, Clinical trials. Looking forward to an interactive session and hope to get insights into what is instore for us in the near future.
Data Lake - For Accelerating Data Analytics & Informed Business Decision
Chairperson: Deven Babre
Data Centricity - with structured and unstructured data constantly being pumped into a data lake – has resulted in a huge unstructured store of data. Mining this data and applying meaningful analytics has amplified various challenges that industry professionals are hard-pressed to address. The industry is enthusiastically embracing new emerging technologies to create innovative approaches and a lucrative habitat that can leverage analytic-ready data for improvements in drug development and clinical trials. Defining Metadata for data has resulted in various data services that allow data lakes to improve data quality, innovate medical treatment procedures, and assist patients in determining care protocols or regimens that offer best value. The use of Monitoring medical devices and analysing fast-moving data in real-time for safety monitoring and adverse event prediction, has enabled payers to monitor adherence to drug and treatment regimens and detect trends that lead to individual and population wellness benefits. With this, the focus is now on improving predictive modelling to lower attrition and produce a leaner, faster, more targeted R&D pipeline for drugs and devices.
Emerging trends in Clinical Data Capture
Chairperson: Dr.Anita Kumar - Associate Vice President : Operational Head - Medical Solutions
1. Trial Initiation and Study Design Visualisation
2. Transforming how technology drives patient-centric clinical research data base build.
3. The clinical trial landscape is ever-changing with technological advancements, changing attitudes to partnerships and new types of drug impacting the industry and Technology is playing a massive role in improving many aspects of trials and is rightly seen as one of the great hopes for future.
4. With technology, so much is happening so fast, the challenge is how to select and use the RIGHT technology, and for that technology to gain the acceptance of Users
Challenges that Study set up faces:
- Complexity of Clinical Trials - Clinical trials have been growing increasingly complex for years. Study teams are particularly concerned with meeting the ‘challenge of focussing on the best study design’ for ‘modern clinical trials’. Such concerns are borne out in the ‘high rate of failure to meet primary endpoints due to poor or complex design’.
- Tight Timelines & Spiralling cost - Increasing complexity and tight timelines is putting more pressure on the need for resources to implement and control every step and the cost of trials is at an all-time high.
- Handling Multiple Documents - It’s a challenge to handle multiple versions of specification (Requirements, UT & UAT) documents and track the difference from one version to the other eventually leading to lot of rework. Start-up phase is time-consuming, labour-intensive, and expensive, so it helps to establish realistic expectations especially while drafting the User requirements and performing various testing’s (UT & UAT). Pricewaterhouse (PWC) Coopers estimates that the industry will need to reduce the cost of drug development by between 20 and 40 percent in order to sustain profitability. To avoid such difficulties a Study Trial management system that reduces trial design and build time by 50% compared with paper-based designs can be used.
- TxDesigner A solution for the Visual Specification creation. Provides visual platform to create/update Trial specifications & progress of study build with version history’s & audit trails.
Eliminates Manual Validations and Task allocations.
Reduced timelines & hence lesser costs.
Efficient & Better control of Study.
Highly secure and technologically advanced set up interface which dramatically reduces IT costs.
Workshop - Bridging gap between Data Management & Data Science
Key Note Speaker : Dr Krishna Asvalayan , Amit Upadhyay
Data Analytics and Data Science based solutions have touched and impacted almost all walks of our day to day life. Our cumulative digital footprint is getting bigger with each passing day and a recent study* envisages exponential growth of global datasphere from 16.3 Zettabytes (ZB) in 2016 to humongous 163 ZB by 2025.
Healthcare domain including clinical data management is fast catching up with this trend and new and innovative data science based technologies are being recognized and adopted by enterprises all over the world as need of the hour.
Adoption of these new technologies to analyze patient data and extracting valuable insights has brought with it many challenges. Almost 80 percent of data generated in healthcare is unstructured and thus difficult for organizations to access and integrate this data. Integration of data is kind of prerequisite to adoption of any predictive analysis tools. Considering the fact that more and more real time patient data is being generated at clinical research sites, the orthodox data management methods may become obsolete down few years giving way to new and innovative technologies.
Data Managers, entrusted with clinical trial data stewardship, have an exciting opportunity to grab here in terms of upgrading and arming themselves with new data analysis tools and technologies. Data Managers must think beyond submissions and perceive data as an asset for future.
Data science tools like Python, R, Hadoop, SQL, Java, SAS, Spark, Matlab, Spotfire and Tableau are already here for quite a while now for efficient and real time decision making when it comes to applying statistical models and predictive analysis. Python and R are fast emerging as widely accepted tools of choice.
Time is ripe for Data Manager’s metamorphosis into Data Scientist. All we need is, to step into this completely new realm filled with immense possibilities. The path is wide enough for Data Managers and Data Scientists to walk abreast. Sooner we recognize and adapt to upcoming change, better equipped we will be to retain our relevance and demand in future.