'Magicians of the Life Sciences' Collaborate at Data Viz Symposium
January 30, 2022: Big companies in the pharmaceutical industry are investing in the ability to collect and mine massive amounts of data, in their effort to accelerate the discovery and development of new therapies and vaccines to improve the health and well-being of people around the world. Digital transformation technologies, artificial intelligence, and machine learning have led to intense interest in this area, making data a central part of their strategy.
In the midst of this paradigm shift, a little-known set of creatives — the data visualization specialists — will become more essential than ever for companies that want to differentiate themselves through innovation and collaboration. Data visualization experts are like the renaissance magicians of the life sciences. They are skilled in such diverse areas as life sciences, data science, technology, design, and communication. They constantly think about how they can exploit subtle attributes such as shape, size, color, and movement to convey important insights to scientists looking at the same data from a different scientific lens.
“Data visualization allows us to make big data accessible and understandable by ‘ordinary’ scientists and other professionals who are not trained in statistics and data science,” said Dimitris K. Agrafiotis, Ph.D., Vice President of Pfizer Digital, during a January 2022 Pistoia Alliance Data Visualization Symposium. During his talk, Agrafiotis highlighted some of the principles that guide the effective visual exploration, representation, and communication of data, by walking the audience through an example from the world of clinical trials.
Using cutting-edge data visualization techniques implemented in a highly interactive and responsive software program that he and his team had developed in one of his previous roles, clinical study teams are able to gain near real-time access to all patient data collected during the course of a clinical trial. They can identify protocol deviations, safety concerns, site misconduct, and other issues that could adversely impact patient safety, data quality, and protocol compliance.
The tool, known as Xcellerate Medical Review, combines intuitive, clinically-aware aggregate visualizations, enabling findings at a glance. It provides the ability to identify and focus on outliers or subgroups of importance, highlight and compare arbitrary cohorts, drill-down to the patient and site-level data. Users can track previously reviewed data to focus on new information, issue automated alerts and notifications, create, manage and communicate auditable observations, and execute configurable workflows to enable efficient and effective clinical and safety review.
“This is the power and beauty of data visualization at its best,” Agrafiotis said. “To use the words of John Tukey, it forces people to notice what they never expected to see.”
“Communicating information effectively is a dance between form and function,” Agrafiotis said. “Data visualizations must appeal to our minds, our senses, and our hearts.”
If data is not presented in a clear, objective, and understandable format, it can lead to costly mistakes, Agrafiotis said. During the symposium, data visualization practitioners discussed solutions to common problems in their field, such as not showing important data, showing data incorrectly, manipulating scales, cherry-picking or obfuscating data, cluttering the view with excessive objects, or misusing visual elements, such as colors, labels, and text.
One of the main goals of the gathering, said organizer and Pistoia Alliance Data Visualization Project Manager Paula de Matos, was to inspire a new set of best practices for this growing profession. The 166 Data Viz experts who attended the event had ample opportunity to share their ideas and visions during a series of hands-on workshops, in addition to the roster of top speakers in the field. In doing so, they also achieved the second goal, which was to build a growing and thriving Data Viz community, with Pistoia Alliance support.
Pistoia Alliance encourages member companies to keep this momentum going by considering sponsorship of future data visualization symposia and conferences. Meanwhile, the project also needs additional funding to continue with these valuable educational and networking opportunities, de Matos said: “We’re looking for contributions from all member companies.” She feels Pistoia Alliance members can greatly benefit by putting data visualization on their priority list.
“There is a career path in the pharmaceutical industry for Data Viz experts, but there are too few people coming in,” she said. “We need to attract the best in class — with more programs and training.”
Symposium speaker Charlotta Fruechtenicht, Ph.D., Senior Data Scientist in Personalized Healthcare Data Science at Roche introduced visR, a software package created by a big pharma collaboration. She said hot trends in life sciences, such as big data, quantum computing, and digital transformation can only succeed with the help of an effective, thoughtful data visualization plan. Marc Streit, Ph.D., Full Professor at JKU Linz in Austria and a co-founder of datavisyn, gave an insightful talk on cutting-edge research in Data Visualization.
The symposium also included a talk from Pistoia Alliance’s Data Viz Project Champion, Bang Wong, now at Vertex Pharmaceuticals, a new member company that recently joined the alliance’s Data Viz community. The event was sponsored by Collaborative Drug Discovery (CDD), represented by speaker Will Richards.
As Data Viz expert Agrafiotis said in his speech, this burgeoning new field incorporates so many important elements — from design and tech to UX and basic communication skills: “It needs to be powerful, it needs to be functional and it needs to be beautiful.”
So often, data visualization is an afterthought, de Matos added. For future success, companies need to value their Data Viz experts and bring these creatives into the process earlier, so they can work their magic.
“You need to think about the question you want to answer upfront,” she said. “We want smart tools that will accurately predict what we want to do and how we want to explore within the data. Data Viz is the key to effectively communicating results and enabling discovery.”
Interested in funding this innovative Pistoia Alliance project? For more details, send an email to: ProjectInquiry@PistoiaAlliance.org.
About the Pistoia Alliance
The Pistoia Alliance is a global, not-for-profit members’ organization made up of life science companies, technology, and service providers, publishers, and academic groups working to lower barriers to innovation in life science and healthcare R&D. It was conceived in 2007 and incorporated in 2009 by representatives of AstraZeneca, GSK, Novartis and Pfizer who met at a conference in Pistoia, Italy. Its projects transform R&D through pre-competitive collaboration. It overcomes common R&D obstacles by identifying the root causes, developing standards and best practices, sharing pre-competitive data and knowledge, and implementing technology pilots. There are currently over 150 member companies; members collaborate on projects that generate significant value for the worldwide life sciences R&D community, using The Pistoia Alliance’s proven framework for open innovation.