March 14, 2019 | As clinical trials gather more data from wearables, patient-reported outcomes, and real-world evidence in addition to traditional streams, systems for managing and using those data are becoming top priority. 

At the Bio-IT World Conference & Expo to be held April 16-18 in Boston, there is a track dedicated to Clinical and Translational Informatics. Researchers from Takeda will discuss their Data Hub (that grew out of their award-winning Platypus project). Researchers from Pfizer and Johnson & Johnson will share how they are using real world data. And sessions will cover innovative clinical trial design and blockchain for clinical trials.

But the program holds even more content. Speakers from pharma and major research institutions will share how they are applying data to clinical research. For instance, representatives from Pfizer will discuss how they use electronic clinical outcome assessments (eCOA) in clinical trials. Researchers from Mount Sinai will share how they are mining EMR data to drive trials. Janssen researchers will explore new trial design, and Bayer will report on using blockchain for trial efficiency.  

The Clinical Research News editorial staff is busy marking our programs for the week. In addition to the Clinical Research track, here are some of the presentations that have caught our attention.

--The Editors

Several teams are working to mine electronic health records and applying the learnings in the clinic. Milenko Tanasijevic at Brigham and Women’s Hospital, will report on the features and advantages of an integrated Electronic Health Record (EHR) and Laboratory Information System (LIS) laboratory ordering system at Brigham and Women’s. The system consists of an EHR-based computerized physician order entry system, positive patient identification system for both nursing and phlebotomy staff, order communication to the LIS and an automated, robotic routine chemistry and hematology systems with result auto-filing capabilities. The various components were introduced over a period of five years engaging multidisciplinary laboratory, informatics, nursing and clinical teams. He’ll present a detailed timeline of the system’s development along with benefits for patient care and lessons learned during the process. Thursday, May 16, 11:10am 

At Icahn School of Medicine at Mount Sinai, electronic medical record (EMR)-linked biobank data have emerged as a source to conduct genome-wide association scans on a broad spectrum of medical and clinical phenotypes. Ron Do will evaluate the utility of such data in the context of drug research and development. He will present results on using genetic association data from a large EMR-linked biobank, for the purposes of informing efficacy and side effect prediction of drug therapeutics in clinical trials. Thursday, May 16, 10:40am

The mission for Pfizer’s Digital Medicine group and the Pfizer Innovation Research (PfIRe) Lab is to solve key business problems using dynamical measures and advanced-STEM platforms. Tomasz Adamusiak is applying that mission to integrating digital biomarkers and electronic clinical outcome assessments (eCOA) in clinical trials. Our goal is to use digital remote monitoring of patients’ symptoms to develop and validate novel clinical endpoints for disease diagnosis and health state assessment. Adamusiak will highlight the unique challenges of digital endpoints including data consistency, quality, and fit for purpose, as well as explore ways to overcome those challenges.
Thursday, May 16, 10:40am

Tumor sequencing is important for guiding the treatment of cancer patients, but there are a wide variety of approaches ranging from paired whole genome tumor-normal sequencing to tumor-only small panel sequencing with many intermediate possibilities. Jeffrey Rosenfeld of Rutgers Cancer Institute of New Jersey compares costs and associated benefits of each approach. Wednesday, May 15, 4:00pm

Healthcare institutions are now recording more electronic health data about patients than ever before in hopes that this real world observational data can be leveraged to unearth insights to improve the quality of care. Adam Perer at Carnegie Mellon University focuses on building interactive visual systems that leverage machine learning so clinicians and researchers can derive such insights. He’ll report on visual analytics for exploration and prediction of clinical data. Wednesday, May 15, 11:00am 

Arlene E. Chung, University of North Carolina School of Medicine, calls it person-generated health data (PGHD)—data derived from wearables and other data streams. She’ll present on using interactive data visualization approaches to allow clinicians and patients to better understand the impact of lifestyle on symptoms and health outcomes, while overcoming data challenges including heterogeneity, missingness, and sparsity are inherent within these data. Thursday, May 16, 3:30pm

How would you set up a clinical data system if you could start from scratch? That was the opportunity afforded to Patrick Kemmeren in 2018 when Princess Máxima Center for Pediatric Oncology became the centralized pediatric oncology center for all children with cancer in the Netherlands. The Princess Máxima Center has had the opportunity to set up their research IT infrastructure right from the start, with limited legacy software to take into account, Kemmeren explains. By building a Central Subject Registry (CSR), the center’s researchers have full access to pseudonymized data from all relevant hospital data sources in a timely manner. At regular intervals the data from all hospital data sources are exported, transformed, and pseudonymized, to be loaded in both the tranSMART and cBioPortal data warehouses, where the center's researchers can easily create their 'shopping list’ for patients and samples of interest. Wednesday, May 15, 11:00am 

Dana-Farber Cancer Institute has clinically sequenced more than 30,000 tumors. However, the incompleteness and inconsistency of clinical data from EHRs and other sources present significant challenges to building the patient-specific diagnosis, treatment, and outcome data that are required to discover correlates to genomic data that inform diagnosis, prognosis, and personalized treatment. At DFCI, John Methot and Eva Lepisto are striving to improve the quality and coverage of clinical data for translational research and clinical decision support. The pair will describe the standards-based data model we have created for representing cancer patient phenotypes, along with a curation software platform we have developed to streamline abstraction of unstructured data into the standard data model and NLP approaches to populating the same model from clinical text. Wednesday, May 15, 11:30am

Both the 21st Century Cures Act and the PDUFA VI legislations call for wider use and acceptance of complex innovative clinical trial designs with the goal of streamlining drug development and bringing needed new medicines to patients in a more timely and efficient manner. Raj Malathker and Vlad Dragalin, both at Janssen Pharmaceuticals R&D, will describe Janssen’s in-house platform, aptly named ACTIVE (Adaptive Clinical Trial’s Interactive Virtual Environment), for efficient implementation of such complex innovative designs. Thursday, May 16, 10:40am

Basker Gummadi, Bayer, will dive into the business case for Blockchain in typical clinical trials, and how it can solve the patient’s lack of access to medical results, costs of maintaining data integrity and data provenance, and poor workflow in the patient informed consent process. Blockchain, in combination with other technology enablers, can provide possible solutions such as consolidating data from patient providers, offering a transparent final clinical summary report for regulatory authorities, and building a traceable patient consent workflow. Wednesday, May 15, 11:00am

LiMing Shen and David Deparday at Sanofi are using a cloud-based computing platform to enable large-scale modeling and simulation in clinical trial models, quantitative system pharmacology models, PKPD analyses, AI/deep learning projects, and to remove bottlenecks in NGS data storage and processing. The project has already made a significant business impact across R&D, they say. Wednesday, May 15, 1:55pm